annotate sdf_to_tab.py @ 6:d68bf44e1f5c draft

"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit a03b1b7b283901a1510562f1e6eba41f70afaac4"
author bgruening
date Mon, 23 Mar 2020 15:58:09 -0400
parents 1cf3bab54ddd
children a1c53f0533b0
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
3
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
1 #!/usr/bin/env python3
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
2 import argparse
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
3 import pandas as pd
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
4 from rdkit import Chem
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
5
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
6 def sdf_to_tab(vars):
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
7 mols = Chem.SDMolSupplier(vars.inp, sanitize=False)
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
8 df = pd.DataFrame() # for output
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
9
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
10 for n in range(len(mols)):
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
11 if mols[n]:
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
12 d = mols[n].GetPropsAsDict()
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
13 # filter dict for desired props
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
14 if vars.props.strip() == '': # none specified, return all
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
15 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
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
16 else:
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
17 d = {prop: val for (prop, val) in d.items() if prop in vars.props.replace(' ', '').split(',')} # remove items not requested via CLI
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
18 if vars.name:
5
1cf3bab54ddd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 09b22cceacb34dd4c6c1b42890f93232df128208"
bgruening
parents: 3
diff changeset
19 d['SDFMoleculeName'] = mols[n].GetProp('_Name')
3
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
20 if vars.smiles:
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
21 d['SMILES'] = Chem.MolToSmiles(mols[n], isomericSmiles=False)
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
22 d['Index'] = int(n)
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
23
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
24 df = df.append(d, ignore_index=True)
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
25 else:
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
26 print("Molecule could not be read - skipped.")
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
27
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
28 df = df.astype({'Index': int}).set_index('Index')
6
d68bf44e1f5c "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit a03b1b7b283901a1510562f1e6eba41f70afaac4"
bgruening
parents: 5
diff changeset
29 sorted_cols = sorted(df.columns.values.tolist())
d68bf44e1f5c "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit a03b1b7b283901a1510562f1e6eba41f70afaac4"
bgruening
parents: 5
diff changeset
30 df.to_csv(vars.out, sep='\t', header=vars.header, columns=sorted_cols)
3
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
31
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
32 def main():
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
33 parser = argparse.ArgumentParser(description="Convert SDF to tabular")
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
34 parser.add_argument('--inp', '-i', help="The input file", required=True)
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
35 parser.add_argument('--out', '-o', help="The output file", required=True)
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
36 parser.add_argument('--props', '-p', help="Properties to filter (leave blank for all)", required=True)
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
37 parser.add_argument('--header', '-t', action='store_true',
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
38 help="Write property name as the first row.")
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
39 parser.add_argument('--smiles', '-s', action='store_true',
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
40 help="Include SMILES in output.")
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
41 parser.add_argument('--name', '-n', action='store_true',
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
42 help="Include molecule name in output.")
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
43 sdf_to_tab(parser.parse_args())
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
44
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
45
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
46 if __name__ == "__main__":
617d4555d8d3 "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 714e984db6ba1198cacf4dcf325320a5889fa02c"
bgruening
parents:
diff changeset
47 main()