Mercurial > repos > bgruening > mordred

comparison mordred_descriptors.py @ 2:d074b0c2b54f draft

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/mordred commit 7efc367809c29ff5939ea971bd00c69b7f9f5903"
author bgruening
date Wed, 06 Nov 2019 13:59:30 -0500
parents e2f40a02f31a
children
comparison
equal deleted inserted replaced
1:e2f40a02f31a 2:d074b0c2b54f
33 return [Chem.MolFromSmiles(mol, sanitize=True) for mol in mols if mol != ''] 33 return [Chem.MolFromSmiles(mol, sanitize=True) for mol in mols if mol != '']
34 if ext == 'inchi': 34 if ext == 'inchi':
35 return [Chem.inchi.MolFromInchi(mol, sanitize=True) for mol in mols if mol != ''] 35 return [Chem.inchi.MolFromInchi(mol, sanitize=True) for mol in mols if mol != '']
36 36
37 37
38 def mordred_descriptors(mols, output, header, use_3d): 38 def mordred_descriptors(mols, output, header, use_3d, smi_as_col):
39 """ 39 """
40 Calculate Mordred descriptors and save as tabular 40 Calculate Mordred descriptors and save as tabular
41 """ 41 """
42 calc = Calculator(descriptors, ignore_3D=(not use_3d)) 42 calc = Calculator(descriptors, ignore_3D=(not use_3d))
43 invalid_mols = np.where(np.array(mols) == None)[0] # indices of invalid SMILES/SDMols 43 invalid_mols = np.where(np.array(mols) == None)[0] # indices of invalid SMILES/SDMols
45 df = calc.pandas(mols, quiet=True) # calculate descriptors 45 df = calc.pandas(mols, quiet=True) # calculate descriptors
46 for mol in invalid_mols: # remove placeholders 46 for mol in invalid_mols: # remove placeholders
47 df.iloc[mol] = np.nan 47 df.iloc[mol] = np.nan
48 df = df.applymap(convert_errors_to_nan) # remove descriptors which errored 48 df = df.applymap(convert_errors_to_nan) # remove descriptors which errored
49 df = df.round(6) 49 df = df.round(6)
50 if smi_as_col:
51 smiles = [Chem.MolToSmiles(mol) for mol in mols]
52 df['SMILES'] = smiles
53
50 df.to_csv(output, na_rep='', sep='\t', index=False, header=header) # write output 54 df.to_csv(output, na_rep='', sep='\t', index=False, header=header) # write output
51 55
52 56
53 if __name__ == "__main__": 57 if __name__ == "__main__":
54 parser = argparse.ArgumentParser() 58 parser = argparse.ArgumentParser()
63 help="Use 3d descriptors - only with SDF input.") 67 help="Use 3d descriptors - only with SDF input.")
64 68
65 parser.add_argument("--header", dest="header", action="store_true", 69 parser.add_argument("--header", dest="header", action="store_true",
66 default=False, 70 default=False,
67 help="Write header line.") 71 help="Write header line.")
72
73 parser.add_argument("--smiles", dest="smiles", action="store_true",
74 default=False,
75 help="Add a column with compound SMILES.")
68 args = parser.parse_args() 76 args = parser.parse_args()
69 77
70 mols = mol_supplier(args.infile, args.iformat) 78 mols = mol_supplier(args.infile, args.iformat)
71 mordred_descriptors(mols, args.outfile, args.header, args.use_3d) 79 mordred_descriptors(mols, args.outfile, args.header, args.use_3d, args.smiles)