Mercurial > repos > greg > genetrack

comparison genetrack.py @ 5:551630d1fae3 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author greg
date Sat, 21 Nov 2015 08:57:27 -0500
parents fcc2f5992551
children 1a9f1a4fa36c
comparison
equal deleted inserted replaced
4:a952b6740fb9 5:551630d1fae3
1 """ 1 """
2 genetrack.py 2 genetrack.py
3 3
4 Input: either ssccidx or gff format of reads 4 Input: either scidx or gff format of reads
5 .ssccidx format: tab-separated chromosome (chr##), index, + reads, - reads 5 Output: Called peaks in gff format
6 .gff format: standard gff, score interpreted as number of reads
7
8 Output: Called peaks in either gff or txt format
9 .txt format: tab-separated chromosome, strand, start, end, read count
10 .gff format: standard gff, score is read count
11 """ 6 """
12 import optparse 7 import optparse
13 import csv 8 import csv
14 import os 9 import os
15 import genetrack_util 10 import genetrack_util
31 for (dataset_path, hid) in options.inputs: 26 for (dataset_path, hid) in options.inputs:
32 if options.input_format == 'gff': 27 if options.input_format == 'gff':
33 # Make sure the reads for each chromosome are sorted by index. 28 # Make sure the reads for each chromosome are sorted by index.
34 input_path = genetrack_util.sort_chromosome_reads_by_index(dataset_path) 29 input_path = genetrack_util.sort_chromosome_reads_by_index(dataset_path)
35 else: 30 else:
36 # We're processing ssccidx data. 31 # We're processing scidx data.
37 input_path = dataset_path 32 input_path = dataset_path
38 output_name = 's%se%su%sd%sF%s_on_data_%s' % (str(options.sigma), 33 output_name = 's%se%su%sd%sF%s_on_data_%s' % (str(options.sigma),
39 str(options.exclusion), 34 str(options.exclusion),
40 str(options.up_width), 35 str(options.up_width),
41 str(options.down_width), 36 str(options.down_width),