Mercurial > repos > recetox > biotransformer

comparison wrapper_biotransformer.py @ 0:0b86600b715e 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 9b8e9941cdf0689518021bc0aa4b7196b28d25d7
author recetox
date Tue, 06 Jun 2023 11:23:51 +0000
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:0b86600b715e
1 import re
2 import subprocess
3 import sys
4 import tempfile
5
6 import pandas
7 from openbabel import openbabel, pybel
8 openbabel.obErrorLog.StopLogging()
9
10
11 def InchiToSmiles(df):
12 '''Translate inchi to smiles'''
13 sm = []
14 for item in df['InChI']:
15 tmp = pybel.readstring("inchi", item)
16 sm.append(tmp.write("smi"))
17 return sm
18
19
20 executable = ["biotransformer"]
21
22 argv = sys.argv[1:]
23 icsv = argv.pop(argv.index("-icsv") + 1)
24 argv.remove("-icsv")
25 ocsv = argv.pop(argv.index("-ocsv") + 1)
26 argv.remove("-ocsv")
27 ocsv_dup = argv.pop(argv.index("-ocsvDup") + 1)
28 argv.remove("-ocsvDup")
29 ocsv_dup2 = argv.pop(argv.index("-ocsvDup2") + 1)
30 argv.remove("-ocsvDup2")
31
32 in_df = pandas.read_csv(icsv, header=None)
33 out_df1 = pandas.DataFrame() # all results
34 out_df2 = pandas.DataFrame() # filtered results based on 6 columns
35 out_df3 = pandas.DataFrame() # filtered results based on 3 columns
36
37 smList1 = [] # list with smiles string
38 smList2 = []
39 smList3 = []
40 for _, (smiles,) in in_df.iterrows():
41 with tempfile.NamedTemporaryFile() as out:
42 print("Working on compound: " + smiles)
43 if not re.search(r'\.', smiles):
44 subprocess.run(executable + argv + ["-ismi", smiles] + ["-ocsv", out.name])
45 try:
46 bio_out = pandas.read_csv(out.name)
47 tmp2 = bio_out.drop_duplicates(subset=["InChI", "InChIKey", "Synonyms", "Molecular formula", "Major Isotope Mass", "ALogP"])
48 tmp3 = bio_out.drop_duplicates(subset=["Molecular formula", "Major Isotope Mass", "ALogP"])
49
50 smList1.append([smiles] * bio_out.shape[0])
51 smList2.append([smiles] * tmp2.shape[0])
52 smList3.append([smiles] * tmp3.shape[0])
53
54 out_df1 = pandas.concat([out_df1, bio_out])
55 out_df2 = pandas.concat([out_df2, tmp2])
56 out_df3 = pandas.concat([out_df3, tmp3])
57 except pandas.errors.EmptyDataError:
58 continue
59 else:
60 print("ERROR: Input compound cannot be a mixture.")
61 smList1 = sum(smList1, []) # merge sublists into one list
62 smList2 = sum(smList2, [])
63 smList3 = sum(smList3, [])
64
65 out_df1.insert(0, "SMILES query", smList1)
66 out_df1.insert(1, "SMILES target", InchiToSmiles(out_df1))
67 out_df1.to_csv(ocsv, sep='\t')
68
69 out_df2.insert(0, "SMILES query", smList2)
70 out_df2.insert(1, "SMILES target", InchiToSmiles(out_df2))
71 out_df2.to_csv(ocsv_dup, sep='\t')
72
73 out_df3.insert(0, "SMILES query", smList3)
74 out_df3.insert(1, "SMILES target", InchiToSmiles(out_df3))
75 out_df3.to_csv(ocsv_dup2, sep='\t')