Mercurial > repos > recetox > biotransformer

comparison wrapper_biotransformer.py @ 1:362a66a3889c draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/biotransformer commit 833817386e90cca9ac4737e6857fcaf672f2a011"
author recetox
date Tue, 22 Sep 2020 14:42:15 +0000
parents
children 6080aee7c4f6
comparison
equal deleted inserted replaced
0:b5b62d04625a 1:362a66a3889c
1 import subprocess
2 import sys
3 import tempfile
4
5 import pandas
6 from openbabel import pybel
7
8
9 # function for translating inchi to smiles
10 def InchiToSmiles(df):
11 sm = []
12 for item in df['InChI']:
13 tmp = pybel.readstring("inchi", item)
14 sm.append(tmp.write("smi"))
15 return(sm)
16
17
18 executable = ["biotransformer"]
19 # executable_r = ["Rscript", "inchi_to_smiles.r"]
20
21 argv = sys.argv[1:]
22 if "-icsv" in argv:
23 icsv = argv.pop(argv.index("-icsv") + 1)
24 argv.remove("-icsv")
25
26 if "-ocsv" not in argv:
27 sys.stderr.write("excpected -ocsv parameter\n")
28 sys.exit(1)
29 ocsv = argv.pop(argv.index("-ocsv") + 1)
30 argv.remove("-ocsv")
31 ocsv_dup = argv.pop(argv.index("-ocsvDup") + 1)
32 argv.remove("-ocsvDup")
33 ocsv_dup2 = argv.pop(argv.index("-ocsvDup2") + 1)
34 argv.remove("-ocsvDup2")
35
36 in_df = pandas.read_csv(icsv, header=None)
37 out_df1 = pandas.DataFrame() # all results
38 out_df2 = pandas.DataFrame() # filtered results based on 6 columns
39 out_df3 = pandas.DataFrame() # filtered results based on 3 columns
40
41 tmp2 = pandas.DataFrame()
42 tmp3 = pandas.DataFrame()
43
44 smList1 = [] # list with smiles string
45 smList2 = []
46 smList3 = []
47 for _, (smiles,) in in_df.iterrows():
48 with tempfile.NamedTemporaryFile() as out:
49 subprocess.run(executable + argv + ["-ismi", smiles] + ["-ocsv", out.name])
50 tmp2 = pandas.read_csv(out.name)
51 tmp3 = pandas.read_csv(out.name)
52 tmp2.drop_duplicates(inplace=True, subset=["InChI", "InChIKey", "Synonyms", "Molecular formula", "Major Isotope Mass", "ALogP"])
53 tmp3.drop_duplicates(inplace=True, subset=["Molecular formula", "Major Isotope Mass", "ALogP"])
54 smList2.append([smiles] * tmp2.shape[0])
55 smList3.append([smiles] * tmp3.shape[0])
56 out_df1 = pandas.concat([out_df1, pandas.read_csv(out.name)])
57 out_df2 = pandas.concat([out_df2, tmp2])
58 out_df3 = pandas.concat([out_df3, tmp3])
59 smList1.append([smiles] * pandas.read_csv(out.name).shape[0])
60 smList1 = sum(smList1, []) # merge sublists into one list
61 smList2 = sum(smList2, [])
62 smList3 = sum(smList3, [])
63
64 out_df1.insert(0, "SMILES query", smList1)
65 out_df1.drop_duplicates(inplace=True)
66 out_df1.insert(1, "SMILES target", InchiToSmiles(out_df1))
67 out_df1.to_csv(ocsv)
68
69 out_df2.insert(0, "SMILES query", smList2)
70 out_df3.insert(0, "SMILES query", smList3)
71 out_df2.drop_duplicates(inplace=True)
72 out_df3.drop_duplicates(inplace=True)
73 out_df2.insert(1, "SMILES target", InchiToSmiles(out_df2))
74 out_df3.insert(1, "SMILES target", InchiToSmiles(out_df3))
75 # out_df.drop_duplicates(inplace=True, subset=["InChI", "InChIKey", "Synonyms", "Molecular formula", "Major Isotope Mass", "ALogP"])
76 out_df2.to_csv(ocsv_dup)
77 out_df3.to_csv(ocsv_dup2)
78 else:
79 # code = subprocess.run(executable + argv).returncode
80 # sys.exit(code)
81 subprocess.run(executable + argv)
82 smile = argv.pop(argv.index("-ismi") + 1)
83 tmp = pandas.DataFrame()
84 out = argv.pop(argv.index("-ocsv") + 1)
85 tmp = pandas.read_csv(out) # reads created output file
86 tmp.insert(0, "SMILES query", smile) # add SMILES string for query
87 tmp.insert(1, "SMILES target", InchiToSmiles(tmp)) # add SMILES string for target
88 tmp.to_csv(out)