mqppep_anova: mqppep_mrgfltr.py annotate

annotate mqppep_mrgfltr.py @ 0:d9b68bedbc91 draft

planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe

author	galaxyp
date	Mon, 11 Jul 2022 19:20:41 +0000
parents
children	2276e88d5a1f

rev	line source
0 d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1 #!/usr/bin/env python
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	2
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	3 # Import the packages needed
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	4 import argparse
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	5 import operator # for operator.itemgetter
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	6 import os.path
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	7 import re
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	8 import shutil # for shutil.copyfile(src, dest)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	9 import sqlite3 as sql
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	10 import sys # import the sys module for exc_info
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	11 import time
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	12 import traceback # for formatting stack-trace
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	13 from codecs import getreader as cx_getreader
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	14
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	15 import numpy as np
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	16 import pandas
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	17
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	18 # global constants
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	19 N_A = "N/A"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	20
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	21
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	22 # ref: https://stackoverflow.com/a/8915613/15509512
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	23 # answers: "How to handle exceptions in a list comprehensions"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	24 # usage:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	25 # from math import log
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	26 # eggs = [1,3,0,3,2]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	27 # print([x for x in [catch(log, egg) for egg in eggs] if x is not None])
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	28 # producing:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	29 # for <built-in function log>
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	30 # with args (0,)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	31 # exception: math domain error
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	32 # [0.0, 1.0986122886681098, 1.0986122886681098, 0.6931471805599453]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	33 def catch(func, args, handle=lambda e: e, *kwargs):
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	34
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	35 try:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	36 return func(args, *kwargs)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	37 except Exception as e:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	38 print("For %s" % str(func))
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	39 print(" with args %s" % str(args))
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	40 print(" caught exception: %s" % str(e))
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	41 (ty, va, tb) = sys.exc_info()
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	42 print(" stack trace: " + str(traceback.format_exception(ty, va, tb)))
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	43 exit(-1)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	44 return None
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	45
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	46
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	47 def whine(func, args, handle=lambda e: e, *kwargs):
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	48
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	49 try:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	50 return func(args, *kwargs)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	51 except Exception as e:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	52 print("Warning: For %s" % str(func))
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	53 print(" with args %s" % str(args))
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	54 print(" caught exception: %s" % str(e))
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	55 (ty, va, tb) = sys.exc_info()
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	56 print(" stack trace: " + str(traceback.format_exception(ty, va, tb)))
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	57 return None
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	58
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	59
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	60 def ppep_join(x):
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	61 x = [i for i in x if N_A != i]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	62 result = "%s" % " \| ".join(x)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	63 if result != "":
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	64 return result
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	65 else:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	66 return N_A
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	67
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	68
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	69 def melt_join(x):
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	70 tmp = {key.lower(): key for key in x}
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	71 result = "%s" % " \| ".join([tmp[key] for key in tmp])
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	72 return result
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	73
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	74
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	75 def __main__():
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	76 # Parse Command Line
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	77 parser = argparse.ArgumentParser(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	78 description="Phopsphoproteomic Enrichment Pipeline Merge and Filter."
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	79 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	80
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	81 # inputs:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	82 # Phosphopeptide data for experimental results, including the intensities
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	83 # and the mapping to kinase domains, in tabular format.
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	84 parser.add_argument(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	85 "--phosphopeptides",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	86 "-p",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	87 nargs=1,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	88 required=True,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	89 dest="phosphopeptides",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	90 help="Phosphopeptide data for experimental results, including the intensities and the mapping to kinase domains, in tabular format",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	91 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	92 # UniProtKB/SwissProt DB input, SQLite
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	93 parser.add_argument(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	94 "--ppep_mapping_db",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	95 "-d",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	96 nargs=1,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	97 required=True,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	98 dest="ppep_mapping_db",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	99 help="UniProtKB/SwissProt SQLite Database",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	100 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	101 # species to limit records chosed from PhosPhositesPlus
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	102 parser.add_argument(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	103 "--species",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	104 "-x",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	105 nargs=1,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	106 required=False,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	107 default=[],
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	108 dest="species",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	109 help="limit PhosphoSitePlus records to indicated species (field may be empty)",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	110 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	111
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	112 # outputs:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	113 # tabular output
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	114 parser.add_argument(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	115 "--mrgfltr_tab",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	116 "-o",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	117 nargs=1,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	118 required=True,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	119 dest="mrgfltr_tab",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	120 help="Tabular output file for results",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	121 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	122 # CSV output
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	123 parser.add_argument(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	124 "--mrgfltr_csv",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	125 "-c",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	126 nargs=1,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	127 required=True,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	128 dest="mrgfltr_csv",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	129 help="CSV output file for results",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	130 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	131 # SQLite output
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	132 parser.add_argument(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	133 "--mrgfltr_sqlite",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	134 "-S",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	135 nargs=1,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	136 required=True,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	137 dest="mrgfltr_sqlite",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	138 help="SQLite output file for results",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	139 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	140
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	141 # "Make it so!" (parse the arguments)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	142 options = parser.parse_args()
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	143 print("options: " + str(options))
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	144
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	145 # determine phosphopeptide ("upstream map") input tabular file access
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	146 if options.phosphopeptides is None:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	147 exit('Argument "phosphopeptides" is required but not supplied')
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	148 try:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	149 upstream_map_filename_tab = os.path.abspath(options.phosphopeptides[0])
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	150 input_file = open(upstream_map_filename_tab, "r")
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	151 input_file.close()
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	152 except Exception as e:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	153 exit("Error parsing phosphopeptides argument: %s" % str(e))
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	154
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	155 # determine input SQLite access
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	156 if options.ppep_mapping_db is None:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	157 exit('Argument "ppep_mapping_db" is required but not supplied')
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	158 try:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	159 uniprot_sqlite = os.path.abspath(options.ppep_mapping_db[0])
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	160 input_file = open(uniprot_sqlite, "rb")
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	161 input_file.close()
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	162 except Exception as e:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	163 exit("Error parsing ppep_mapping_db argument: %s" % str(e))
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	164
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	165 # copy input SQLite dataset to output SQLite dataset
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	166 if options.mrgfltr_sqlite is None:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	167 exit('Argument "mrgfltr_sqlite" is required but not supplied')
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	168 try:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	169 output_sqlite = os.path.abspath(options.mrgfltr_sqlite[0])
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	170 shutil.copyfile(uniprot_sqlite, output_sqlite)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	171 except Exception as e:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	172 exit("Error copying ppep_mapping_db to mrgfltr_sqlite: %s" % str(e))
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	173
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	174 # determine species to limit records from PSP_Regulatory_Sites
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	175 if options.species is None:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	176 exit(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	177 'Argument "species" is required (and may be empty) but not supplied'
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	178 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	179 try:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	180 if len(options.species) > 0:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	181 species = options.species[0]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	182 else:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	183 species = ""
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	184 except Exception as e:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	185 exit("Error parsing species argument: %s" % str(e))
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	186
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	187 # determine tabular output destination
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	188 if options.mrgfltr_tab is None:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	189 exit('Argument "mrgfltr_tab" is required but not supplied')
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	190 try:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	191 output_filename_tab = os.path.abspath(options.mrgfltr_tab[0])
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	192 output_file = open(output_filename_tab, "w")
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	193 output_file.close()
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	194 except Exception as e:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	195 exit("Error parsing mrgfltr_tab argument: %s" % str(e))
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	196
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	197 # determine CSV output destination
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	198 if options.mrgfltr_csv is None:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	199 exit('Argument "mrgfltr_csv" is required but not supplied')
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	200 try:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	201 output_filename_csv = os.path.abspath(options.mrgfltr_csv[0])
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	202 output_file = open(output_filename_csv, "w")
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	203 output_file.close()
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	204 except Exception as e:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	205 exit("Error parsing mrgfltr_csv argument: %s" % str(e))
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	206
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	207 def mqpep_getswissprot():
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	208
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	209 #
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	210 # copied from Excel Output Script.ipynb BEGIN #
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	211 #
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	212
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	213 # String Constants #################
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	214 DEPHOSPHOPEP = "DephosphoPep"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	215 DESCRIPTION = "Description"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	216 FUNCTION_PHOSPHORESIDUE = (
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	217 "Function Phosphoresidue(PSP=PhosphoSitePlus.org)"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	218 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	219 GENE_NAME = "Gene_Name" # Gene Name from UniProtKB
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	220 ON_FUNCTION = (
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	221 "ON_FUNCTION" # ON_FUNCTION column from PSP_Regulatory_Sites
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	222 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	223 ON_NOTES = "NOTES" # NOTES column from PSP_Regulatory_Sites
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	224 ON_OTHER_INTERACT = "ON_OTHER_INTERACT" # ON_OTHER_INTERACT column from PSP_Regulatory_Sites
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	225 ON_PROCESS = (
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	226 "ON_PROCESS" # ON_PROCESS column from PSP_Regulatory_Sites
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	227 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	228 ON_PROT_INTERACT = "ON_PROT_INTERACT" # ON_PROT_INTERACT column from PSP_Regulatory_Sites
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	229 PHOSPHOPEPTIDE = "Phosphopeptide"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	230 PHOSPHOPEPTIDE_MATCH = "Phosphopeptide_match"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	231 PHOSPHORESIDUE = "Phosphoresidue"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	232 PUTATIVE_UPSTREAM_DOMAINS = "Putative Upstream Kinases(PSP=PhosphoSitePlus.org)/Phosphatases/Binding Domains"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	233 SEQUENCE = "Sequence"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	234 SEQUENCE10 = "Sequence10"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	235 SEQUENCE7 = "Sequence7"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	236 SITE_PLUSMINUS_7AA_SQL = "SITE_PLUSMINUS_7AA"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	237 UNIPROT_ID = "UniProt_ID"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	238 UNIPROT_SEQ_AND_META_SQL = """
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	239 select Uniprot_ID, Description, Gene_Name, Sequence,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	240 Organism_Name, Organism_ID, PE, SV
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	241 from UniProtKB
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	242 order by Sequence, UniProt_ID
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	243 """
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	244 UNIPROT_UNIQUE_SEQ_SQL = """
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	245 select distinct Sequence
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	246 from UniProtKB
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	247 group by Sequence
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	248 """
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	249 PPEP_PEP_UNIPROTSEQ_SQL = """
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	250 select distinct phosphopeptide, peptide, sequence
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	251 from uniprotkb_pep_ppep_view
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	252 order by sequence
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	253 """
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	254 PPEP_MELT_SQL = """
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	255 SELECT DISTINCT
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	256 phospho_peptide AS 'p_peptide',
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	257 kinase_map AS 'characterization',
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	258 'X' AS 'X'
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	259 FROM ppep_gene_site_view
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	260 """
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	261 # CREATE TABLE PSP_Regulatory_site (
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	262 # site_plusminus_7AA TEXT PRIMARY KEY ON CONFLICT IGNORE,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	263 # domain TEXT,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	264 # ON_FUNCTION TEXT,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	265 # ON_PROCESS TEXT,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	266 # ON_PROT_INTERACT TEXT,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	267 # ON_OTHER_INTERACT TEXT,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	268 # notes TEXT,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	269 # organism TEXT
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	270 # );
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	271 PSP_REGSITE_SQL = """
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	272 SELECT DISTINCT
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	273 SITE_PLUSMINUS_7AA ,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	274 DOMAIN ,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	275 ON_FUNCTION ,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	276 ON_PROCESS ,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	277 ON_PROT_INTERACT ,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	278 ON_OTHER_INTERACT ,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	279 NOTES ,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	280 ORGANISM
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	281 FROM PSP_Regulatory_site
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	282 """
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	283 PPEP_ID_SQL = """
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	284 SELECT
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	285 id AS 'ppep_id',
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	286 seq AS 'ppep_seq'
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	287 FROM ppep
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	288 """
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	289 MRGFLTR_DDL = """
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	290 DROP VIEW IF EXISTS mrgfltr_metadata_view;
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	291 DROP TABLE IF EXISTS mrgfltr_metadata;
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	292 CREATE TABLE mrgfltr_metadata
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	293 ( ppep_id INTEGER REFERENCES ppep(id)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	294 , Sequence10 TEXT
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	295 , Sequence7 TEXT
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	296 , GeneName TEXT
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	297 , Phosphoresidue TEXT
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	298 , UniProtID TEXT
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	299 , Description TEXT
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	300 , FunctionPhosphoresidue TEXT
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	301 , PutativeUpstreamDomains TEXT
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	302 , PRIMARY KEY (ppep_id) ON CONFLICT IGNORE
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	303 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	304 ;
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	305 CREATE VIEW mrgfltr_metadata_view AS
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	306 SELECT DISTINCT
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	307 ppep.seq AS phospho_peptide
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	308 , Sequence10
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	309 , Sequence7
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	310 , GeneName
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	311 , Phosphoresidue
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	312 , UniProtID
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	313 , Description
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	314 , FunctionPhosphoresidue
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	315 , PutativeUpstreamDomains
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	316 FROM
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	317 ppep, mrgfltr_metadata
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	318 WHERE
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	319 mrgfltr_metadata.ppep_id = ppep.id
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	320 ORDER BY
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	321 ppep.seq
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	322 ;
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	323 """
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	324
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	325 CITATION_INSERT_STMT = """
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	326 INSERT INTO Citation (
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	327 ObjectName,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	328 CitationData
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	329 ) VALUES (?,?)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	330 """
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	331 CITATION_INSERT_PSP = 'PhosphoSitePlus(R) (PSP) was created by Cell Signaling Technology Inc. It is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License. When using PSP data or analyses in printed publications or in online resources, the following acknowledgements must be included: (a) the words "PhosphoSitePlus(R), www.phosphosite.org" must be included at appropriate places in the text or webpage, and (b) the following citation must be included in the bibliography: "Hornbeck PV, Zhang B, Murray B, Kornhauser JM, Latham V, Skrzypek E PhosphoSitePlus, 2014: mutations, PTMs and recalibrations. Nucleic Acids Res. 2015 43:D512-20. PMID: 25514926."'
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	332 CITATION_INSERT_PSP_REF = 'Hornbeck, 2014, "PhosphoSitePlus, 2014: mutations, PTMs and recalibrations.", https://pubmed.ncbi.nlm.nih.gov/22135298, https://doi.org/10.1093/nar/gkr1122'
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	333
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	334 MRGFLTR_METADATA_COLUMNS = [
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	335 "ppep_id",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	336 "Sequence10",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	337 "Sequence7",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	338 "GeneName",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	339 "Phosphoresidue",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	340 "UniProtID",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	341 "Description",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	342 "FunctionPhosphoresidue",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	343 "PutativeUpstreamDomains",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	344 ]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	345
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	346 # String Constants (end) ############
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	347
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	348 class Error(Exception):
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	349 """Base class for exceptions in this module."""
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	350
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	351 pass
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	352
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	353 class PreconditionError(Error):
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	354 """Exception raised for errors in the input.
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	355
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	356 Attributes:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	357 expression -- input expression in which the error occurred
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	358 message -- explanation of the error
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	359 """
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	360
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	361 def __init__(self, expression, message):
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	362 self.expression = expression
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	363 self.message = message
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	364
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	365 # start_time = time.clock() #timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	366 start_time = time.process_time() # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	367
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	368 # get keys from upstream tabular file using readline()
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	369 # ref: https://stackoverflow.com/a/16713581/15509512
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	370 # answer to "Use codecs to read file with correct encoding"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	371 file1_encoded = open(upstream_map_filename_tab, "rb")
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	372 file1 = cx_getreader("latin-1")(file1_encoded)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	373
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	374 count = 0
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	375 upstream_map_p_peptide_list = []
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	376 re_tab = re.compile("^[^\t]*")
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	377 while True:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	378 count += 1
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	379 # Get next line from file
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	380 line = file1.readline()
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	381 # if line is empty
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	382 # end of file is reached
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	383 if not line:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	384 break
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	385 if count > 1:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	386 m = re_tab.match(line)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	387 upstream_map_p_peptide_list.append(m[0])
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	388 file1.close()
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	389 file1_encoded.close()
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	390
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	391 # Get the list of phosphopeptides with the p's that represent the phosphorylation sites removed
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	392 re_phos = re.compile("p")
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	393
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	394 end_time = time.process_time() # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	395 print(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	396 "%0.6f pre-read-SwissProt [0.1]" % (end_time - start_time,),
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	397 file=sys.stderr,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	398 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	399
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	400 # ----------- Get SwissProt data from SQLite database (start) -----------
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	401 # build UniProt sequence LUT and list of unique SwissProt sequences
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	402
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	403 # Open SwissProt SQLite database
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	404 conn = sql.connect(uniprot_sqlite)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	405 cur = conn.cursor()
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	406
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	407 # Set up structures to hold SwissProt data
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	408
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	409 uniprot_Sequence_List = []
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	410 UniProtSeqLUT = {}
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	411
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	412 # Execute query for unique seqs without fetching the results yet
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	413 uniprot_unique_seq_cur = cur.execute(UNIPROT_UNIQUE_SEQ_SQL)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	414
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	415 while 1:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	416 batch = uniprot_unique_seq_cur.fetchmany(size=50)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	417 if not batch:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	418 # handle case where no records are returned
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	419 break
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	420 for row in batch:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	421 Sequence = row[0]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	422 UniProtSeqLUT[(Sequence, DESCRIPTION)] = []
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	423 UniProtSeqLUT[(Sequence, GENE_NAME)] = []
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	424 UniProtSeqLUT[(Sequence, UNIPROT_ID)] = []
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	425 UniProtSeqLUT[Sequence] = []
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	426
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	427 # Execute query for seqs and metadata without fetching the results yet
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	428 uniprot_seq_and_meta = cur.execute(UNIPROT_SEQ_AND_META_SQL)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	429
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	430 while 1:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	431 batch = uniprot_seq_and_meta.fetchmany(size=50)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	432 if not batch:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	433 # handle case where no records are returned
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	434 break
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	435 for (
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	436 UniProt_ID,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	437 Description,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	438 Gene_Name,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	439 Sequence,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	440 OS,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	441 OX,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	442 PE,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	443 SV,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	444 ) in batch:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	445 uniprot_Sequence_List.append(Sequence)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	446 UniProtSeqLUT[Sequence] = Sequence
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	447 UniProtSeqLUT[(Sequence, UNIPROT_ID)].append(UniProt_ID)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	448 UniProtSeqLUT[(Sequence, GENE_NAME)].append(Gene_Name)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	449 if OS != N_A:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	450 Description += " OS=" + OS
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	451 if OX != -1:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	452 Description += " OX=" + str(OX)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	453 if Gene_Name != N_A:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	454 Description += " GN=" + Gene_Name
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	455 if PE != N_A:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	456 Description += " PE=" + PE
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	457 if SV != N_A:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	458 Description += " SV=" + SV
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	459 UniProtSeqLUT[(Sequence, DESCRIPTION)].append(Description)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	460
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	461 # Close SwissProt SQLite database; clean up local variables
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	462 conn.close()
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	463 Sequence = ""
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	464 UniProt_ID = ""
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	465 Description = ""
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	466 Gene_Name = ""
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	467
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	468 # ----------- Get SwissProt data from SQLite database (finish) -----------
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	469
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	470 end_time = time.process_time() # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	471 print(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	472 "%0.6f post-read-SwissProt [0.2]" % (end_time - start_time,),
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	473 file=sys.stderr,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	474 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	475
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	476 # ----------- Get SwissProt data from SQLite database (start) -----------
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	477 # Open SwissProt SQLite database
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	478 conn = sql.connect(uniprot_sqlite)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	479 cur = conn.cursor()
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	480
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	481 # Set up dictionary to aggregate results for phosphopeptides correspounding to dephosphoeptide
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	482 DephosphoPep_UniProtSeq_LUT = {}
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	483
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	484 # Set up dictionary to accumulate results
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	485 PhosphoPep_UniProtSeq_LUT = {}
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	486
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	487 # Execute query for tuples without fetching the results yet
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	488 ppep_pep_uniprotseq_cur = cur.execute(PPEP_PEP_UNIPROTSEQ_SQL)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	489
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	490 while 1:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	491 batch = ppep_pep_uniprotseq_cur.fetchmany(size=50)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	492 if not batch:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	493 # handle case where no records are returned
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	494 break
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	495 for (phospho_pep, dephospho_pep, sequence) in batch:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	496 # do interesting stuff here...
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	497 PhosphoPep_UniProtSeq_LUT[phospho_pep] = phospho_pep
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	498 PhosphoPep_UniProtSeq_LUT[
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	499 (phospho_pep, DEPHOSPHOPEP)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	500 ] = dephospho_pep
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	501 if dephospho_pep not in DephosphoPep_UniProtSeq_LUT:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	502 DephosphoPep_UniProtSeq_LUT[dephospho_pep] = set()
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	503 DephosphoPep_UniProtSeq_LUT[
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	504 (dephospho_pep, DESCRIPTION)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	505 ] = []
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	506 DephosphoPep_UniProtSeq_LUT[
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	507 (dephospho_pep, GENE_NAME)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	508 ] = []
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	509 DephosphoPep_UniProtSeq_LUT[
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	510 (dephospho_pep, UNIPROT_ID)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	511 ] = []
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	512 DephosphoPep_UniProtSeq_LUT[(dephospho_pep, SEQUENCE)] = []
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	513 DephosphoPep_UniProtSeq_LUT[dephospho_pep].add(phospho_pep)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	514
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	515 if (
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	516 sequence
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	517 not in DephosphoPep_UniProtSeq_LUT[
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	518 (dephospho_pep, SEQUENCE)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	519 ]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	520 ):
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	521 DephosphoPep_UniProtSeq_LUT[
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	522 (dephospho_pep, SEQUENCE)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	523 ].append(sequence)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	524 for phospho_pep in DephosphoPep_UniProtSeq_LUT[dephospho_pep]:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	525 if phospho_pep != phospho_pep:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	526 print(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	527 "phospho_pep:'%s' phospho_pep:'%s'"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	528 % (phospho_pep, phospho_pep)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	529 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	530 if phospho_pep not in PhosphoPep_UniProtSeq_LUT:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	531 PhosphoPep_UniProtSeq_LUT[phospho_pep] = phospho_pep
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	532 PhosphoPep_UniProtSeq_LUT[
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	533 (phospho_pep, DEPHOSPHOPEP)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	534 ] = dephospho_pep
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	535 r = list(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	536 zip(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	537 [s for s in UniProtSeqLUT[(sequence, UNIPROT_ID)]],
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	538 [s for s in UniProtSeqLUT[(sequence, GENE_NAME)]],
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	539 [
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	540 s
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	541 for s in UniProtSeqLUT[(sequence, DESCRIPTION)]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	542 ],
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	543 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	544 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	545 # Sort by `UniProt_ID`
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	546 # ref: https://stackoverflow.com/a/4174955/15509512
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	547 r = sorted(r, key=operator.itemgetter(0))
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	548 # Get one tuple for each `phospho_pep`
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	549 # in DephosphoPep_UniProtSeq_LUT[dephospho_pep]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	550 for (upid, gn, desc) in r:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	551 # Append pseudo-tuple per UniProt_ID but only when it is not present
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	552 if (
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	553 upid
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	554 not in DephosphoPep_UniProtSeq_LUT[
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	555 (dephospho_pep, UNIPROT_ID)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	556 ]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	557 ):
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	558 DephosphoPep_UniProtSeq_LUT[
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	559 (dephospho_pep, UNIPROT_ID)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	560 ].append(upid)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	561 DephosphoPep_UniProtSeq_LUT[
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	562 (dephospho_pep, DESCRIPTION)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	563 ].append(desc)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	564 DephosphoPep_UniProtSeq_LUT[
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	565 (dephospho_pep, GENE_NAME)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	566 ].append(gn)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	567
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	568 # Close SwissProt SQLite database; clean up local variables
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	569 conn.close()
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	570 # wipe local variables
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	571 phospho_pep = dephospho_pep = sequence = 0
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	572 upid = gn = desc = r = ""
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	573
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	574 # ----------- Get SwissProt data from SQLite database (finish) -----------
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	575
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	576 end_time = time.process_time() # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	577 print(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	578 "%0.6f finished reading and decoding '%s' [0.4]"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	579 % (end_time - start_time, upstream_map_filename_tab),
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	580 file=sys.stderr,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	581 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	582
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	583 print(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	584 "{:>10} unique upstream phosphopeptides tested".format(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	585 str(len(upstream_map_p_peptide_list))
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	586 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	587 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	588
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	589 # Read in Upstream tabular file
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	590 # We are discarding the intensity data; so read it as text
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	591 upstream_data = pandas.read_table(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	592 upstream_map_filename_tab, dtype="str", index_col=0
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	593 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	594
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	595 end_time = time.process_time() # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	596 print(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	597 "%0.6f read Upstream Map from file [1g_1]"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	598 % (end_time - start_time,),
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	599 file=sys.stderr,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	600 ) # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	601
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	602 upstream_data.index = upstream_map_p_peptide_list
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	603
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	604 end_time = time.process_time() # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	605 print(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	606 "%0.6f added index to Upstream Map [1g_2]"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	607 % (end_time - start_time,),
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	608 file=sys.stderr,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	609 ) # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	610
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	611 # ########################################################################
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	612 # # trim upstream_data to include only the upstream map columns
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	613 # old_cols = upstream_data.columns.tolist()
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	614 # i = 0
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	615 # first_intensity = -1
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	616 # last_intensity = -1
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	617 # intensity_re = re.compile("Intensity.*")
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	618 # for col_name in old_cols:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	619 # m = intensity_re.match(col_name)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	620 # if m:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	621 # last_intensity = i
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	622 # if first_intensity == -1:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	623 # first_intensity = i
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	624 # i += 1
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	625 # # print('last intensity = %d' % last_intensity)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	626 # col_PKCalpha = last_intensity + 2
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	627 #
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	628 # data_in_cols = [old_cols[0]] + old_cols[
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	629 # first_intensity: last_intensity + 1
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	630 # ]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	631 #
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	632 # if upstream_data.empty:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	633 # print("upstream_data is empty")
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	634 # exit(0)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	635 #
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	636 # data_in = upstream_data.copy(deep=True)[data_in_cols]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	637 ########################################################################
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	638 # trim upstream_data to include only the upstream map columns
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	639 old_cols = upstream_data.columns.tolist()
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	640 i = 0
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	641 first_intensity = -1
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	642 last_intensity = -1
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	643 intensity_re = re.compile("Intensity.*")
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	644 for col_name in old_cols:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	645 m = intensity_re.match(col_name)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	646 if m:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	647 last_intensity = i
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	648 if first_intensity == -1:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	649 first_intensity = i
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	650 i += 1
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	651 # print('last intensity = %d' % last_intensity)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	652 col_PKCalpha = last_intensity + 2
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	653
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	654 data_in_cols = [old_cols[0]] + old_cols[
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	655 first_intensity - 1: last_intensity
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	656 ]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	657 data_col_names = [old_cols[0]] + old_cols[
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	658 first_intensity: last_intensity + 1
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	659 ]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	660
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	661 if upstream_data.empty:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	662 print("upstream_data is empty")
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	663 exit(0)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	664
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	665 data_in = upstream_data.copy(deep=True)[data_in_cols]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	666 data_in.columns = data_col_names
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	667 print("data_in")
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	668 print(data_in)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	669 ########################################################################
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	670
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	671 # Convert floating-point integers to int64 integers
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	672 # ref: https://stackoverflow.com/a/68497603/15509512
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	673 data_in[list(data_in.columns[1:])] = (
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	674 data_in[list(data_in.columns[1:])]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	675 .astype("float64")
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	676 .apply(np.int64)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	677 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	678
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	679 # create another phosphopeptide column that will be used to join later;
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	680 # MAY need to change depending on Phosphopeptide column position
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	681 # data_in[PHOSPHOPEPTIDE_MATCH] = data_in[data_in.columns.tolist()[0]]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	682 data_in[PHOSPHOPEPTIDE_MATCH] = data_in.index
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	683
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	684 end_time = time.process_time() # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	685 print(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	686 "%0.6f set data_in[PHOSPHOPEPTIDE_MATCH] [A]"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	687 % (end_time - start_time,),
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	688 file=sys.stderr,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	689 ) # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	690
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	691 # Produce a dictionary of metadata for a single phosphopeptide.
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	692 # This is a replacement of `UniProtInfo_subdict` in the original code.
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	693 def pseq_to_subdict(phospho_pep):
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	694 # Strip "p" from phosphopeptide sequence
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	695 dephospho_pep = re_phos.sub("", phospho_pep)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	696
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	697 # Determine number of phosphoresidues in phosphopeptide
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	698 numps = len(phospho_pep) - len(dephospho_pep)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	699
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	700 # Determine location(s) of phosphoresidue(s) in phosphopeptide
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	701 # (used later for Phosphoresidue, Sequence7, and Sequence10)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	702 ploc = [] # list of p locations
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	703 i = 0
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	704 p = phospho_pep
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	705 while i < numps:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	706 ploc.append(p.find("p"))
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	707 p = p[: p.find("p")] + p[p.find("p") + 1:]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	708 i += 1
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	709
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	710 # Establish nested dictionary
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	711 result = {}
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	712 result[SEQUENCE] = []
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	713 result[UNIPROT_ID] = []
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	714 result[DESCRIPTION] = []
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	715 result[GENE_NAME] = []
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	716 result[PHOSPHORESIDUE] = []
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	717 result[SEQUENCE7] = []
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	718 result[SEQUENCE10] = []
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	719
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	720 # Add stripped sequence to dictionary
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	721 result[SEQUENCE].append(dephospho_pep)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	722
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	723 # Locate phospho_pep in PhosphoPep_UniProtSeq_LUT
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	724 # Caller may elect to:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	725 # try:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	726 # ...
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	727 # except PreconditionError as pe:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	728 # print("'{expression}': {message}".format(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	729 # expression = pe.expression,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	730 # message = pe.message))
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	731 # )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	732 # )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	733 if phospho_pep not in PhosphoPep_UniProtSeq_LUT:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	734 raise PreconditionError(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	735 phospho_pep,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	736 "no matching phosphopeptide found in PhosphoPep_UniProtSeq_LUT",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	737 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	738 if dephospho_pep not in DephosphoPep_UniProtSeq_LUT:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	739 raise PreconditionError(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	740 dephospho_pep,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	741 "dephosphorylated phosphopeptide not found in DephosphoPep_UniProtSeq_LUT",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	742 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	743 if (
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	744 dephospho_pep != PhosphoPep_UniProtSeq_LUT[(phospho_pep, DEPHOSPHOPEP)]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	745 ):
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	746 my_err_msg = "dephosphorylated phosphopeptide does not match "
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	747 my_err_msg += "PhosphoPep_UniProtSeq_LUT[(phospho_pep,DEPHOSPHOPEP)] = "
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	748 my_err_msg += PhosphoPep_UniProtSeq_LUT[(phospho_pep, DEPHOSPHOPEP)]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	749 raise PreconditionError(dephospho_pep, my_err_msg)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	750
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	751 result[SEQUENCE] = [dephospho_pep]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	752 result[UNIPROT_ID] = DephosphoPep_UniProtSeq_LUT[
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	753 (dephospho_pep, UNIPROT_ID)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	754 ]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	755 result[DESCRIPTION] = DephosphoPep_UniProtSeq_LUT[
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	756 (dephospho_pep, DESCRIPTION)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	757 ]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	758 result[GENE_NAME] = DephosphoPep_UniProtSeq_LUT[
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	759 (dephospho_pep, GENE_NAME)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	760 ]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	761 if (dephospho_pep, SEQUENCE) not in DephosphoPep_UniProtSeq_LUT:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	762 raise PreconditionError(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	763 dephospho_pep,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	764 "no matching phosphopeptide found in DephosphoPep_UniProtSeq_LUT",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	765 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	766 UniProtSeqList = DephosphoPep_UniProtSeq_LUT[
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	767 (dephospho_pep, SEQUENCE)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	768 ]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	769 if len(UniProtSeqList) < 1:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	770 print(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	771 "Skipping DephosphoPep_UniProtSeq_LUT[('%s',SEQUENCE)] because value has zero length"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	772 % dephospho_pep
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	773 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	774 # raise PreconditionError(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	775 # "DephosphoPep_UniProtSeq_LUT[('" + dephospho_pep + ",SEQUENCE)",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	776 # 'value has zero length'
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	777 # )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	778 for UniProtSeq in UniProtSeqList:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	779 i = 0
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	780 phosphoresidues = []
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	781 seq7s_set = set()
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	782 seq7s = []
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	783 seq10s_set = set()
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	784 seq10s = []
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	785 while i < len(ploc):
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	786 start = UniProtSeq.find(dephospho_pep)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	787 # handle case where no sequence was found for dep-pep
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	788 if start < 0:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	789 i += 1
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	790 continue
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	791 psite = (
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	792 start + ploc[i]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	793 ) # location of phosphoresidue on protein sequence
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	794
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	795 # add Phosphoresidue
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	796 phosphosite = "p" + str(UniProtSeq)[psite] + str(psite + 1)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	797 phosphoresidues.append(phosphosite)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	798
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	799 # Add Sequence7
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	800 if psite < 7: # phospho_pep at N terminus
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	801 seq7 = str(UniProtSeq)[: psite + 8]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	802 if seq7[psite] == "S": # if phosphosresidue is serine
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	803 pres = "s"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	804 elif (
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	805 seq7[psite] == "T"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	806 ): # if phosphosresidue is threonine
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	807 pres = "t"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	808 elif (
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	809 seq7[psite] == "Y"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	810 ): # if phosphoresidue is tyrosine
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	811 pres = "y"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	812 else: # if not pSTY
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	813 pres = "?"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	814 seq7 = (
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	815 seq7[:psite] + pres + seq7[psite + 1: psite + 8]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	816 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	817 while (
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	818 len(seq7) < 15
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	819 ): # add appropriate number of "_" to the front
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	820 seq7 = "_" + seq7
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	821 elif (
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	822 len(UniProtSeq) - psite < 8
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	823 ): # phospho_pep at C terminus
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	824 seq7 = str(UniProtSeq)[psite - 7:]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	825 if seq7[7] == "S":
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	826 pres = "s"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	827 elif seq7[7] == "T":
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	828 pres = "t"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	829 elif seq7[7] == "Y":
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	830 pres = "y"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	831 else:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	832 pres = "?"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	833 seq7 = seq7[:7] + pres + seq7[8:]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	834 while (
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	835 len(seq7) < 15
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	836 ): # add appropriate number of "_" to the back
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	837 seq7 = seq7 + "_"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	838 else:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	839 seq7 = str(UniProtSeq)[psite - 7: psite + 8]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	840 pres = "" # phosphoresidue
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	841 if seq7[7] == "S": # if phosphosresidue is serine
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	842 pres = "s"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	843 elif seq7[7] == "T": # if phosphosresidue is threonine
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	844 pres = "t"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	845 elif seq7[7] == "Y": # if phosphoresidue is tyrosine
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	846 pres = "y"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	847 else: # if not pSTY
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	848 pres = "?"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	849 seq7 = seq7[:7] + pres + seq7[8:]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	850 if seq7 not in seq7s_set:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	851 seq7s.append(seq7)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	852 seq7s_set.add(seq7)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	853
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	854 # add Sequence10
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	855 if psite < 10: # phospho_pep at N terminus
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	856 seq10 = (
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	857 str(UniProtSeq)[:psite] + "p" + str(UniProtSeq)[psite: psite + 11]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	858 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	859 elif (
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	860 len(UniProtSeq) - psite < 11
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	861 ): # phospho_pep at C terminus
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	862 seq10 = (
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	863 str(UniProtSeq)[psite - 10: psite] + "p" + str(UniProtSeq)[psite:]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	864 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	865 else:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	866 seq10 = str(UniProtSeq)[psite - 10: psite + 11]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	867 seq10 = seq10[:10] + "p" + seq10[10:]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	868 if seq10 not in seq10s_set:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	869 seq10s.append(seq10)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	870 seq10s_set.add(seq10)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	871
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	872 i += 1
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	873
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	874 result[PHOSPHORESIDUE].append(phosphoresidues)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	875 result[SEQUENCE7].append(seq7s)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	876 # result[SEQUENCE10] is a list of lists of strings
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	877 result[SEQUENCE10].append(seq10s)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	878
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	879 r = list(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	880 zip(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	881 result[UNIPROT_ID],
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	882 result[GENE_NAME],
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	883 result[DESCRIPTION],
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	884 result[PHOSPHORESIDUE],
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	885 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	886 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	887 # Sort by `UniProt_ID`
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	888 # ref: https://stackoverflow.com//4174955/15509512
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	889 s = sorted(r, key=operator.itemgetter(0))
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	890
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	891 result[UNIPROT_ID] = []
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	892 result[GENE_NAME] = []
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	893 result[DESCRIPTION] = []
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	894 result[PHOSPHORESIDUE] = []
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	895
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	896 for r in s:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	897 result[UNIPROT_ID].append(r[0])
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	898 result[GENE_NAME].append(r[1])
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	899 result[DESCRIPTION].append(r[2])
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	900 result[PHOSPHORESIDUE].append(r[3])
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	901
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	902 # convert lists to strings in the dictionary
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	903 for key, value in result.items():
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	904 if key not in [PHOSPHORESIDUE, SEQUENCE7, SEQUENCE10]:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	905 result[key] = "; ".join(map(str, value))
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	906 elif key in [SEQUENCE10]:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	907 # result[SEQUENCE10] is a list of lists of strings
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	908 joined_value = ""
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	909 joined_set = set()
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	910 sep = ""
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	911 for valL in value:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	912 # valL is a list of strings
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	913 for val in valL:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	914 # val is a string
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	915 if val not in joined_set:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	916 joined_set.add(val)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	917 joined_value += sep + val
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	918 sep = "; "
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	919 # joined_value is a string
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	920 result[key] = joined_value
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	921
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	922 newstring = "; ".join(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	923 [", ".join(prez) for prez in result[PHOSPHORESIDUE]]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	924 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	925 # #separate the isoforms in PHOSPHORESIDUE column with ";"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	926 # oldstring = result[PHOSPHORESIDUE]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	927 # oldlist = list(oldstring)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	928 # newstring = ""
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	929 # i = 0
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	930 # for e in oldlist:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	931 # if e == ";":
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	932 # if numps > 1:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	933 # if i%numps:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	934 # newstring = newstring + ";"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	935 # else:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	936 # newstring = newstring + ","
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	937 # else:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	938 # newstring = newstring + ";"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	939 # i +=1
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	940 # else:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	941 # newstring = newstring + e
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	942 result[PHOSPHORESIDUE] = newstring
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	943
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	944 # separate sequence7's by \|
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	945 oldstring = result[SEQUENCE7]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	946 oldlist = oldstring
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	947 newstring = ""
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	948 for ol in oldlist:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	949 for e in ol:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	950 if e == ";":
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	951 newstring = newstring + " \|"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	952 elif len(newstring) > 0 and 1 > newstring.count(e):
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	953 newstring = newstring + " \| " + e
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	954 elif 1 > newstring.count(e):
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	955 newstring = newstring + e
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	956 result[SEQUENCE7] = newstring
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	957
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	958 return [phospho_pep, result]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	959
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	960 # Construct list of [string, dictionary] lists
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	961 # where the dictionary provides the SwissProt metadata
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	962 # for a phosphopeptide
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	963 result_list = [
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	964 whine(pseq_to_subdict, psequence)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	965 for psequence in data_in[PHOSPHOPEPTIDE_MATCH]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	966 ]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	967
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	968 end_time = time.process_time() # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	969 print(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	970 "%0.6f added SwissProt annotations to phosphopeptides [B]"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	971 % (end_time - start_time,),
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	972 file=sys.stderr,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	973 ) # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	974
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	975 # Construct dictionary from list of lists
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	976 # ref: https://www.8bitavenue.com/how-to-convert-list-of-lists-to-dictionary-in-python/
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	977 UniProt_Info = {
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	978 result[0]: result[1]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	979 for result in result_list
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	980 if result is not None
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	981 }
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	982
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	983 end_time = time.process_time() # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	984 print(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	985 "%0.6f create dictionary mapping phosphopeptide to metadata dictionary [C]"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	986 % (end_time - start_time,),
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	987 file=sys.stderr,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	988 ) # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	989
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	990 # cosmetic: add N_A to phosphopeptide rows with no hits
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	991 p_peptide_list = []
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	992 for key in UniProt_Info:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	993 p_peptide_list.append(key)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	994 for nestedKey in UniProt_Info[key]:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	995 if UniProt_Info[key][nestedKey] == "":
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	996 UniProt_Info[key][nestedKey] = N_A
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	997
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	998 end_time = time.process_time() # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	999 print(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1000 "%0.6f performed cosmetic clean-up [D]" % (end_time - start_time,),
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1001 file=sys.stderr,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1002 ) # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1003
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1004 # convert UniProt_Info dictionary to dataframe
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1005 uniprot_df = pandas.DataFrame.transpose(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1006 pandas.DataFrame.from_dict(UniProt_Info)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1007 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1008
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1009 # reorder columns to match expected output file
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1010 uniprot_df[
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1011 PHOSPHOPEPTIDE
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1012 ] = uniprot_df.index # make index a column too
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1013
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1014 cols = uniprot_df.columns.tolist()
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1015 # cols = [cols[-1]]+cols[4:6]+[cols[1]]+[cols[2]]+[cols[6]]+[cols[0]]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1016 # uniprot_df = uniprot_df[cols]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1017 uniprot_df = uniprot_df[
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1018 [
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1019 PHOSPHOPEPTIDE,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1020 SEQUENCE10,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1021 SEQUENCE7,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1022 GENE_NAME,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1023 PHOSPHORESIDUE,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1024 UNIPROT_ID,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1025 DESCRIPTION,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1026 ]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1027 ]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1028
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1029 end_time = time.process_time() # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1030 print(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1031 "%0.6f reordered columns to match expected output file [1]"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1032 % (end_time - start_time,),
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1033 file=sys.stderr,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1034 ) # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1035
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1036 # concat to split then groupby to collapse
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1037 seq7_df = pandas.concat(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1038 [
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1039 pandas.Series(row[PHOSPHOPEPTIDE], row[SEQUENCE7].split(" \| "))
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1040 for _, row in uniprot_df.iterrows()
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1041 ]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1042 ).reset_index()
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1043 seq7_df.columns = [SEQUENCE7, PHOSPHOPEPTIDE]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1044
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1045 # --- -------------- begin read PSP_Regulatory_sites ---------------------------------
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1046 # read in PhosphoSitePlus Regulatory Sites dataset
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1047 # ----------- Get PhosphoSitePlus Regulatory Sites data from SQLite database (start) -----------
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1048 conn = sql.connect(uniprot_sqlite)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1049 regsites_df = pandas.read_sql_query(PSP_REGSITE_SQL, conn)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1050 # Close SwissProt SQLite database
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1051 conn.close()
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1052 # ... -------------- end read PSP_Regulatory_sites ------------------------------------
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1053
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1054 # keep only the human entries in dataframe
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1055 if len(species) > 0:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1056 print(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1057 'Limit PhosphoSitesPlus records to species "' + species + '"'
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1058 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1059 regsites_df = regsites_df[regsites_df.ORGANISM == species]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1060
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1061 # merge the seq7 df with the regsites df based off of the sequence7
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1062 merge_df = seq7_df.merge(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1063 regsites_df,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1064 left_on=SEQUENCE7,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1065 right_on=SITE_PLUSMINUS_7AA_SQL,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1066 how="left",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1067 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1068
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1069 # after merging df, select only the columns of interest;
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1070 # note that PROTEIN is absent here
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1071 merge_df = merge_df[
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1072 [
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1073 PHOSPHOPEPTIDE,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1074 SEQUENCE7,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1075 ON_FUNCTION,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1076 ON_PROCESS,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1077 ON_PROT_INTERACT,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1078 ON_OTHER_INTERACT,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1079 ON_NOTES,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1080 ]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1081 ]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1082 # combine column values of interest
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1083 # into one FUNCTION_PHOSPHORESIDUE column"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1084 merge_df[FUNCTION_PHOSPHORESIDUE] = merge_df[ON_FUNCTION].str.cat(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1085 merge_df[ON_PROCESS], sep="; ", na_rep=""
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1086 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1087 merge_df[FUNCTION_PHOSPHORESIDUE] = merge_df[
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1088 FUNCTION_PHOSPHORESIDUE
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1089 ].str.cat(merge_df[ON_PROT_INTERACT], sep="; ", na_rep="")
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1090 merge_df[FUNCTION_PHOSPHORESIDUE] = merge_df[
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1091 FUNCTION_PHOSPHORESIDUE
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1092 ].str.cat(merge_df[ON_OTHER_INTERACT], sep="; ", na_rep="")
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1093 merge_df[FUNCTION_PHOSPHORESIDUE] = merge_df[
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1094 FUNCTION_PHOSPHORESIDUE
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1095 ].str.cat(merge_df[ON_NOTES], sep="; ", na_rep="")
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1096
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1097 # remove the columns that were combined
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1098 merge_df = merge_df[
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1099 [PHOSPHOPEPTIDE, SEQUENCE7, FUNCTION_PHOSPHORESIDUE]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1100 ]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1101
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1102 end_time = time.process_time() # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1103 print(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1104 "%0.6f merge regsite metadata [1a]" % (end_time - start_time,),
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1105 file=sys.stderr,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1106 ) # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1107
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1108 # cosmetic changes to Function Phosphoresidue column
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1109 fp_series = pandas.Series(merge_df[FUNCTION_PHOSPHORESIDUE])
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1110
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1111 end_time = time.process_time() # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1112 print(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1113 "%0.6f more cosmetic changes [1b]" % (end_time - start_time,),
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1114 file=sys.stderr,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1115 ) # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1116
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1117 i = 0
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1118 while i < len(fp_series):
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1119 # remove the extra ";" so that it looks more professional
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1120 if fp_series[i] == "; ; ; ; ": # remove ; from empty hits
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1121 fp_series[i] = ""
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1122 while fp_series[i].endswith("; "): # remove ; from the ends
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1123 fp_series[i] = fp_series[i][:-2]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1124 while fp_series[i].startswith("; "): # remove ; from the beginning
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1125 fp_series[i] = fp_series[i][2:]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1126 fp_series[i] = fp_series[i].replace("; ; ; ; ", "; ")
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1127 fp_series[i] = fp_series[i].replace("; ; ; ", "; ")
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1128 fp_series[i] = fp_series[i].replace("; ; ", "; ")
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1129
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1130 # turn blanks into N_A to signify the info was searched for but cannot be found
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1131 if fp_series[i] == "":
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1132 fp_series[i] = N_A
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1133
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1134 i += 1
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1135 merge_df[FUNCTION_PHOSPHORESIDUE] = fp_series
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1136
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1137 end_time = time.process_time() # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1138 print(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1139 "%0.6f cleaned up semicolons [1c]" % (end_time - start_time,),
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1140 file=sys.stderr,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1141 ) # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1142
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1143 # merge uniprot df with merge df
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1144 uniprot_regsites_merged_df = uniprot_df.merge(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1145 merge_df,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1146 left_on=PHOSPHOPEPTIDE,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1147 right_on=PHOSPHOPEPTIDE,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1148 how="left",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1149 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1150
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1151 # collapse the merged df
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1152 uniprot_regsites_collapsed_df = pandas.DataFrame(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1153 uniprot_regsites_merged_df.groupby(PHOSPHOPEPTIDE)[
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1154 FUNCTION_PHOSPHORESIDUE
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1155 ].apply(lambda x: ppep_join(x))
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1156 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1157 # .apply(lambda x: "%s" % ' \| '.join(x)))
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1158
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1159 end_time = time.process_time() # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1160 print(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1161 "%0.6f collapsed pandas dataframe [1d]" % (end_time - start_time,),
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1162 file=sys.stderr,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1163 ) # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1164
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1165 uniprot_regsites_collapsed_df[
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1166 PHOSPHOPEPTIDE
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1167 ] = (
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1168 uniprot_regsites_collapsed_df.index
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1169 ) # add df index as its own column
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1170
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1171 # rename columns
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1172 uniprot_regsites_collapsed_df.columns = [
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1173 FUNCTION_PHOSPHORESIDUE,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1174 "ppp",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1175 ]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1176
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1177 end_time = time.process_time() # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1178 print(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1179 "%0.6f selected columns to be merged to uniprot_df [1e]"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1180 % (end_time - start_time,),
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1181 file=sys.stderr,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1182 ) # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1183
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1184 # add columns based on Sequence7 matching site_+/-7_AA
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1185 uniprot_regsite_df = pandas.merge(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1186 left=uniprot_df,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1187 right=uniprot_regsites_collapsed_df,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1188 how="left",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1189 left_on=PHOSPHOPEPTIDE,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1190 right_on="ppp",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1191 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1192
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1193 end_time = time.process_time() # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1194 print(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1195 "%0.6f added columns based on Sequence7 matching site_+/-7_AA [1f]"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1196 % (end_time - start_time,),
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1197 file=sys.stderr,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1198 ) # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1199
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1200 data_in.rename(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1201 {"Protein description": PHOSPHOPEPTIDE},
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1202 axis="columns",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1203 inplace=True,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1204 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1205
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1206 # data_in.sort_values(PHOSPHOPEPTIDE_MATCH, inplace=True, kind='mergesort')
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1207 res2 = sorted(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1208 data_in[PHOSPHOPEPTIDE_MATCH].tolist(), key=lambda s: s.casefold()
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1209 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1210 data_in = data_in.loc[res2]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1211
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1212 end_time = time.process_time() # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1213 print(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1214 "%0.6f sorting time [1f]" % (end_time - start_time,),
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1215 file=sys.stderr,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1216 ) # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1217
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1218 print("old_cols[:col_PKCalpha]")
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1219 print(old_cols[:col_PKCalpha])
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1220 cols = [old_cols[0]] + old_cols[col_PKCalpha - 1:]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1221 upstream_data = upstream_data[cols]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1222 print("upstream_data.columns")
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1223 print(upstream_data.columns)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1224
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1225 end_time = time.process_time() # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1226 print(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1227 "%0.6f refactored columns for Upstream Map [1g]"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1228 % (end_time - start_time,),
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1229 file=sys.stderr,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1230 ) # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1231
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1232 # #rename upstream columns in new list
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1233 # new_cols = []
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1234 # for name in cols:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1235 # if "_NetworKIN" in name:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1236 # name = name.split("_")[0]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1237 # if " motif" in name:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1238 # name = name.split(" motif")[0]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1239 # if " sequence " in name:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1240 # name = name.split(" sequence")[0]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1241 # if "_Phosida" in name:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1242 # name = name.split("_")[0]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1243 # if "_PhosphoSite" in name:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1244 # name = name.split("_")[0]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1245 # new_cols.append(name)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1246
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1247 # rename upstream columns in new list
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1248 def col_rename(name):
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1249 if "_NetworKIN" in name:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1250 name = name.split("_")[0]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1251 if " motif" in name:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1252 name = name.split(" motif")[0]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1253 if " sequence " in name:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1254 name = name.split(" sequence")[0]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1255 if "_Phosida" in name:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1256 name = name.split("_")[0]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1257 if "_PhosphoSite" in name:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1258 name = name.split("_")[0]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1259 return name
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1260
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1261 new_cols = [col_rename(col) for col in cols]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1262 upstream_data.columns = new_cols
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1263
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1264 end_time = time.process_time() # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1265 print(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1266 "%0.6f renamed columns for Upstream Map [1h_1]"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1267 % (end_time - start_time,),
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1268 file=sys.stderr,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1269 ) # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1270
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1271 # Create upstream_data_cast as a copy of upstream_data
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1272 # but with first column substituted by the phosphopeptide sequence
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1273 upstream_data_cast = upstream_data.copy()
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1274 new_cols_cast = new_cols
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1275 new_cols_cast[0] = "p_peptide"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1276 upstream_data_cast.columns = new_cols_cast
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1277 upstream_data_cast["p_peptide"] = upstream_data.index
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1278
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1279 # --- -------------- begin read upstream_data_melt ------------------------------------
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1280 # ----------- Get melted kinase mapping data from SQLite database (start) -----------
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1281 conn = sql.connect(uniprot_sqlite)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1282 upstream_data_melt_df = pandas.read_sql_query(PPEP_MELT_SQL, conn)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1283 # Close SwissProt SQLite database
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1284 conn.close()
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1285 upstream_data_melt = upstream_data_melt_df.copy()
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1286 upstream_data_melt.columns = ["p_peptide", "characterization", "X"]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1287 upstream_data_melt["characterization"] = [
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1288 col_rename(s) for s in upstream_data_melt["characterization"]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1289 ]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1290
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1291 print(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1292 "%0.6f upstream_data_melt_df initially has %d rows"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1293 % (end_time - start_time, len(upstream_data_melt.axes[0])),
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1294 file=sys.stderr,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1295 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1296 # ref: https://stackoverflow.com/a/27360130/15509512
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1297 # e.g. df.drop(df[df.score < 50].index, inplace=True)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1298 upstream_data_melt.drop(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1299 upstream_data_melt[upstream_data_melt.X != "X"].index, inplace=True
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1300 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1301 print(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1302 "%0.6f upstream_data_melt_df pre-dedup has %d rows"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1303 % (end_time - start_time, len(upstream_data_melt.axes[0])),
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1304 file=sys.stderr,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1305 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1306 # ----------- Get melted kinase mapping data from SQLite database (finish) -----------
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1307 # ... -------------- end read upstream_data_melt --------------------------------------
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1308
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1309 end_time = time.process_time() # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1310 print(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1311 "%0.6f melted and minimized Upstream Map dataframe [1h_2]"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1312 % (end_time - start_time,),
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1313 file=sys.stderr,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1314 ) # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1315 # ... end read upstream_data_melt
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1316
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1317 end_time = time.process_time() # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1318 print(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1319 "%0.6f indexed melted Upstream Map [1h_2a]"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1320 % (end_time - start_time,),
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1321 file=sys.stderr,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1322 ) # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1323
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1324 upstream_delta_melt_LoL = upstream_data_melt.values.tolist()
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1325
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1326 melt_dict = {}
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1327 for key in upstream_map_p_peptide_list:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1328 melt_dict[key] = []
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1329
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1330 for el in upstream_delta_melt_LoL:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1331 (p_peptide, characterization, X) = tuple(el)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1332 if p_peptide in melt_dict:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1333 melt_dict[p_peptide].append(characterization)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1334 else:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1335 exit(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1336 'Phosphopeptide %s not found in ppep_mapping_db: "phopsphopeptides" and "ppep_mapping_db" must both originate from the same run of mqppep_kinase_mapping'
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1337 % (p_peptide)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1338 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1339
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1340 end_time = time.process_time() # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1341 print(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1342 "%0.6f appended peptide characterizations [1h_2b]"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1343 % (end_time - start_time,),
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1344 file=sys.stderr,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1345 ) # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1346
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1347 # for key in upstream_map_p_peptide_list:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1348 # melt_dict[key] = ' \| '.join(melt_dict[key])
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1349
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1350 for key in upstream_map_p_peptide_list:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1351 melt_dict[key] = melt_join(melt_dict[key])
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1352
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1353 end_time = time.process_time() # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1354 print(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1355 "%0.6f concatenated multiple characterizations [1h_2c]"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1356 % (end_time - start_time,),
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1357 file=sys.stderr,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1358 ) # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1359
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1360 # map_dict is a dictionary of dictionaries
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1361 map_dict = {}
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1362 for key in upstream_map_p_peptide_list:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1363 map_dict[key] = {}
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1364 map_dict[key][PUTATIVE_UPSTREAM_DOMAINS] = melt_dict[key]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1365
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1366 end_time = time.process_time() # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1367 print(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1368 "%0.6f instantiated map dictionary [2]" % (end_time - start_time,),
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1369 file=sys.stderr,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1370 ) # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1371
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1372 # convert map_dict to dataframe
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1373 map_df = pandas.DataFrame.transpose(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1374 pandas.DataFrame.from_dict(map_dict)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1375 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1376 map_df["p-peptide"] = map_df.index # make index a column too
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1377 cols_map_df = map_df.columns.tolist()
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1378 cols_map_df = [cols_map_df[1]] + [cols_map_df[0]]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1379 map_df = map_df[cols_map_df]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1380
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1381 # join map_df to uniprot_regsite_df
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1382 output_df = uniprot_regsite_df.merge(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1383 map_df, how="left", left_on=PHOSPHOPEPTIDE, right_on="p-peptide"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1384 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1385
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1386 output_df = output_df[
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1387 [
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1388 PHOSPHOPEPTIDE,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1389 SEQUENCE10,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1390 SEQUENCE7,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1391 GENE_NAME,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1392 PHOSPHORESIDUE,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1393 UNIPROT_ID,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1394 DESCRIPTION,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1395 FUNCTION_PHOSPHORESIDUE,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1396 PUTATIVE_UPSTREAM_DOMAINS,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1397 ]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1398 ]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1399
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1400 # cols_output_prelim = output_df.columns.tolist()
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1401 #
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1402 # print("cols_output_prelim")
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1403 # print(cols_output_prelim)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1404 #
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1405 # cols_output = cols_output_prelim[:8]+[cols_output_prelim[9]]+[cols_output_prelim[10]]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1406 #
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1407 # print("cols_output with p-peptide")
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1408 # print(cols_output)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1409 #
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1410 # cols_output = [col for col in cols_output if not col == "p-peptide"]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1411 #
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1412 # print("cols_output")
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1413 # print(cols_output)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1414 #
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1415 # output_df = output_df[cols_output]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1416
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1417 # join output_df back to quantitative columns in data_in df
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1418 quant_cols = data_in.columns.tolist()
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1419 quant_cols = quant_cols[1:]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1420 quant_data = data_in[quant_cols]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1421
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1422 # ----------- Write merge/filter metadata to SQLite database (start) -----------
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1423 # Open SwissProt SQLite database
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1424 conn = sql.connect(output_sqlite)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1425 cur = conn.cursor()
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1426
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1427 cur.executescript(MRGFLTR_DDL)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1428
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1429 cur.execute(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1430 CITATION_INSERT_STMT,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1431 ("mrgfltr_metadata_view", CITATION_INSERT_PSP),
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1432 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1433 cur.execute(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1434 CITATION_INSERT_STMT, ("mrgfltr_metadata", CITATION_INSERT_PSP)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1435 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1436 cur.execute(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1437 CITATION_INSERT_STMT,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1438 ("mrgfltr_metadata_view", CITATION_INSERT_PSP_REF),
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1439 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1440 cur.execute(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1441 CITATION_INSERT_STMT, ("mrgfltr_metadata", CITATION_INSERT_PSP_REF)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1442 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1443
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1444 # Read ppep-to-sequence LUT
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1445 ppep_lut_df = pandas.read_sql_query(PPEP_ID_SQL, conn)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1446 # write only metadata for merged/filtered records to SQLite
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1447 mrgfltr_metadata_df = output_df.copy()
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1448 # replace phosphopeptide seq with ppep.id
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1449 mrgfltr_metadata_df = ppep_lut_df.merge(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1450 mrgfltr_metadata_df,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1451 left_on="ppep_seq",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1452 right_on=PHOSPHOPEPTIDE,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1453 how="inner",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1454 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1455 mrgfltr_metadata_df.drop(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1456 columns=[PHOSPHOPEPTIDE, "ppep_seq"], inplace=True
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1457 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1458 # rename columns
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1459 mrgfltr_metadata_df.columns = MRGFLTR_METADATA_COLUMNS
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1460 mrgfltr_metadata_df.to_sql(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1461 "mrgfltr_metadata",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1462 con=conn,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1463 if_exists="append",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1464 index=False,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1465 method="multi",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1466 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1467
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1468 # Close SwissProt SQLite database
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1469 conn.close()
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1470 # ----------- Write merge/filter metadata to SQLite database (finish) -----------
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1471
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1472 output_df = output_df.merge(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1473 quant_data,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1474 how="right",
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1475 left_on=PHOSPHOPEPTIDE,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1476 right_on=PHOSPHOPEPTIDE_MATCH,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1477 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1478 output_cols = output_df.columns.tolist()
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1479 output_cols = output_cols[:-1]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1480 output_df = output_df[output_cols]
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1481
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1482 # cosmetic changes to Upstream column
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1483 output_df[PUTATIVE_UPSTREAM_DOMAINS] = output_df[
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1484 PUTATIVE_UPSTREAM_DOMAINS
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1485 ].fillna(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1486 ""
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1487 ) # fill the NaN with "" for those Phosphopeptides that got a "WARNING: Failed match for " in the upstream mapping
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1488 us_series = pandas.Series(output_df[PUTATIVE_UPSTREAM_DOMAINS])
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1489 i = 0
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1490 while i < len(us_series):
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1491 # turn blanks into N_A to signify the info was searched for but cannot be found
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1492 if us_series[i] == "":
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1493 us_series[i] = N_A
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1494 i += 1
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1495 output_df[PUTATIVE_UPSTREAM_DOMAINS] = us_series
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1496
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1497 end_time = time.process_time() # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1498 print(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1499 "%0.6f establisheed output [3]" % (end_time - start_time,),
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1500 file=sys.stderr,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1501 ) # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1502
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1503 (output_rows, output_cols) = output_df.shape
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1504
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1505 output_df = output_df.convert_dtypes(convert_integer=True)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1506
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1507 # Output onto Final CSV file
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1508 output_df.to_csv(output_filename_csv, index=False)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1509 output_df.to_csv(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1510 output_filename_tab, quoting=None, sep="\t", index=False
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1511 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1512
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1513 end_time = time.process_time() # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1514 print(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1515 "%0.6f wrote output [4]" % (end_time - start_time,),
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1516 file=sys.stderr,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1517 ) # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1518
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1519 print(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1520 "{:>10} phosphopeptides written to output".format(str(output_rows))
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1521 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1522
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1523 end_time = time.process_time() # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1524 print(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1525 "%0.6f seconds of non-system CPU time were consumed"
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1526 % (end_time - start_time,),
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1527 file=sys.stderr,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1528 ) # timer
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1529
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1530 # Rev. 7/1/2016
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1531 # Rev. 7/3/2016 : fill NaN in Upstream column to replace to N/A's
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1532 # Rev. 7/3/2016: renamed Upstream column to PUTATIVE_UPSTREAM_DOMAINS
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1533 # Rev. 12/2/2021: Converted to Python from ipynb; use fast Aho-Corasick searching; \
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1534 # read from SwissProt SQLite database
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1535 # Rev. 12/9/2021: Transfer code to Galaxy tool wrapper
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1536
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1537 #
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1538 # copied from Excel Output Script.ipynb END #
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1539 #
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1540
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1541 try:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1542 catch(
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1543 mqpep_getswissprot,
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1544 )
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1545 exit(0)
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1546 except Exception as e:
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1547 exit("Internal error running mqpep_getswissprot(): %s" % (e))
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1548
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1549
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1550 if __name__ == "__main__":
d9b68bedbc91 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe galaxyp parents: diff changeset	1551 __main__()

Mercurial > repos > galaxyp > mqppep_anova

annotate mqppep_mrgfltr.py @ 0:d9b68bedbc91 draft