Mercurial > repos > bgruening > ctb_rdkit_descriptors

comparison sdf_to_tab.py @ 9:0993ac4f4a23 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit c1d813d3f0fec60ea6efe8a11e59d98bfdc1636f"
author bgruening
date Sat, 04 Dec 2021 16:40:00 +0000
parents a1c53f0533b0
children
comparison
equal deleted inserted replaced
8:a1c53f0533b0 9:0993ac4f4a23
11 11
12 for n in range(len(mols)): 12 for n in range(len(mols)):
13 if mols[n]: 13 if mols[n]:
14 d = mols[n].GetPropsAsDict() 14 d = mols[n].GetPropsAsDict()
15 # filter dict for desired props 15 # filter dict for desired props
16 if vars.props.strip() == '': # none specified, return all 16 if vars.props.strip() == "": # none specified, return all
17 d = {prop: val for (prop, val) in d.items() if not any(x in str(val) for x in ['\n', '\t'])} # remove items containing newlines or tabs 17 d = {
18 prop: val
19 for (prop, val) in d.items()
20 if not any(x in str(val) for x in ["\n", "\t"])
21 } # remove items containing newlines or tabs
18 else: 22 else:
19 d = {prop: val for (prop, val) in d.items() if prop in vars.props.replace(' ', '').split(',')} # remove items not requested via CLI 23 d = {
24 prop: val
25 for (prop, val) in d.items()
26 if prop in vars.props.replace(" ", "").split(",")
27 } # remove items not requested via CLI
20 if vars.name: 28 if vars.name:
21 d['SDFMoleculeName'] = mols[n].GetProp('_Name') 29 d["SDFMoleculeName"] = mols[n].GetProp("_Name")
22 if vars.smiles: 30 if vars.smiles:
23 d['SMILES'] = Chem.MolToSmiles(mols[n], isomericSmiles=False) 31 d["SMILES"] = Chem.MolToSmiles(mols[n], isomericSmiles=False)
24 d['Index'] = int(n) 32 d["Index"] = int(n)
25 33
26 df = df.append(d, ignore_index=True) 34 df = df.append(d, ignore_index=True)
27 else: 35 else:
28 print("Molecule could not be read - skipped.") 36 print("Molecule could not be read - skipped.")
29 37
30 df = df.astype({'Index': int}).set_index('Index') 38 df = df.astype({"Index": int}).set_index("Index")
31 sorted_cols = sorted(df.columns.values.tolist()) 39 sorted_cols = sorted(df.columns.values.tolist())
32 df.to_csv(vars.out, sep='\t', header=vars.header, columns=sorted_cols) 40 df.to_csv(vars.out, sep="\t", header=vars.header, columns=sorted_cols)
33 41
34 42
35 def main(): 43 def main():
36 parser = argparse.ArgumentParser(description="Convert SDF to tabular") 44 parser = argparse.ArgumentParser(description="Convert SDF to tabular")
37 parser.add_argument('--inp', '-i', help="The input file", required=True) 45 parser.add_argument("--inp", "-i", help="The input file", required=True)
38 parser.add_argument('--out', '-o', help="The output file", required=True) 46 parser.add_argument("--out", "-o", help="The output file", required=True)
39 parser.add_argument('--props', '-p', help="Properties to filter (leave blank for all)", required=True) 47 parser.add_argument(
40 parser.add_argument('--header', '-t', action='store_true', 48 "--props",
41 help="Write property name as the first row.") 49 "-p",
42 parser.add_argument('--smiles', '-s', action='store_true', 50 help="Properties to filter (leave blank for all)",
43 help="Include SMILES in output.") 51 required=True,
44 parser.add_argument('--name', '-n', action='store_true', 52 )
45 help="Include molecule name in output.") 53 parser.add_argument(
54 "--header",
55 "-t",
56 action="store_true",
57 help="Write property name as the first row.",
58 )
59 parser.add_argument(
60 "--smiles", "-s", action="store_true", help="Include SMILES in output."
61 )
62 parser.add_argument(
63 "--name", "-n", action="store_true", help="Include molecule name in output."
64 )
46 sdf_to_tab(parser.parse_args()) 65 sdf_to_tab(parser.parse_args())
47 66
48 67
49 if __name__ == "__main__": 68 if __name__ == "__main__":
50 main() 69 main()