comparison mordred_descriptors.py @ 2:d074b0c2b54f draft

"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/mordred commit 7efc367809c29ff5939ea971bd00c69b7f9f5903"

1:e2f40a02f31a

        return [Chem.MolFromSmiles(mol, sanitize=True) for mol in mols if mol != '']
    if ext == 'inchi':
        return [Chem.inchi.MolFromInchi(mol, sanitize=True) for mol in mols if mol != '']


def mordred_descriptors(mols, output, header, use_3d):
    """
    Calculate Mordred descriptors and save as tabular
    """
    calc = Calculator(descriptors, ignore_3D=(not use_3d))
    invalid_mols = np.where(np.array(mols) == None)[0]  # indices of invalid SMILES/SDMols

    df = calc.pandas(mols, quiet=True)  # calculate descriptors
    for mol in invalid_mols:  # remove placeholders
        df.iloc[mol] = np.nan
    df = df.applymap(convert_errors_to_nan)  # remove descriptors which errored
    df = df.round(6)
    df.to_csv(output, na_rep='', sep='\t', index=False, header=header)  # write output


if __name__ == "__main__":
    parser = argparse.ArgumentParser()

                    help="Use 3d descriptors - only with SDF input.")

    parser.add_argument("--header", dest="header", action="store_true",
                    default=False,
                    help="Write header line.")
    args = parser.parse_args()

    mols = mol_supplier(args.infile, args.iformat)
    mordred_descriptors(mols, args.outfile, args.header, args.use_3d)

2:d074b0c2b54f

        return [Chem.MolFromSmiles(mol, sanitize=True) for mol in mols if mol != '']
    if ext == 'inchi':
        return [Chem.inchi.MolFromInchi(mol, sanitize=True) for mol in mols if mol != '']


def mordred_descriptors(mols, output, header, use_3d, smi_as_col):
    """
    Calculate Mordred descriptors and save as tabular
    """
    calc = Calculator(descriptors, ignore_3D=(not use_3d))
    invalid_mols = np.where(np.array(mols) == None)[0]  # indices of invalid SMILES/SDMols

    df = calc.pandas(mols, quiet=True)  # calculate descriptors
    for mol in invalid_mols:  # remove placeholders
        df.iloc[mol] = np.nan
    df = df.applymap(convert_errors_to_nan)  # remove descriptors which errored
    df = df.round(6)
    if smi_as_col:
        smiles = [Chem.MolToSmiles(mol) for mol in mols]
        df['SMILES'] = smiles

    df.to_csv(output, na_rep='', sep='\t', index=False, header=header)  # write output


if __name__ == "__main__":
    parser = argparse.ArgumentParser()

                    help="Use 3d descriptors - only with SDF input.")

    parser.add_argument("--header", dest="header", action="store_true",
                    default=False,
                    help="Write header line.")

    parser.add_argument("--smiles", dest="smiles", action="store_true",
                    default=False,
                    help="Add a column with compound SMILES.")
    args = parser.parse_args()

    mols = mol_supplier(args.infile, args.iformat)
    mordred_descriptors(mols, args.outfile, args.header, args.use_3d, args.smiles)