Splitting multicomponent molecules

A program that splits multicomponent molecules into their constituent parts. The program will output the molecules to stdout as SMILES if no output file is set. The program will print the number of input and output molecules to stderr.

Example

prompt> parts2mols.py inputfile1.oeb.gz output.oeb.gz

If the output-file argument is omitted, the output is written to standard output.

Code

Download code

parts2mols.py

#!/usr/bin/env python
# (C) 2022 Cadence Design Systems, Inc. (Cadence) 
# All rights reserved.
# TERMS FOR USE OF SAMPLE CODE The software below ("Sample Code") is
# provided to current licensees or subscribers of Cadence products or
# SaaS offerings (each a "Customer").
# Customer is hereby permitted to use, copy, and modify the Sample Code,
# subject to these terms. Cadence claims no rights to Customer's
# modifications. Modification of Sample Code is at Customer's sole and
# exclusive risk. Sample Code may require Customer to have a then
# current license or subscription to the applicable Cadence offering.
# THE SAMPLE CODE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
# EXPRESS OR IMPLIED.  OPENEYE DISCLAIMS ALL WARRANTIES, INCLUDING, BUT
# NOT LIMITED TO, WARRANTIES OF MERCHANTABILITY, FITNESS FOR A
# PARTICULAR PURPOSE AND NONINFRINGEMENT. In no event shall Cadence be
# liable for any damages or liability in connection with the Sample Code
# or its use.

#############################################################################
# Writes each component of a molecule as a separate molecule
#############################################################################

import sys
from openeye import oechem


def main(argv=[__name__]):
    if len(argv) != 3:
        oechem.OEThrow.Usage("%s <infile> <outfile>" % argv[0])

    ifs = oechem.oemolistream()
    ifs.SetFlavor(oechem.OEFormat_PDB, oechem.OEIFlavor_PDB_Default ^ oechem.OEIFlavor_PDB_DATA)
    if not ifs.open(argv[1]):
        oechem.OEThrow.Fatal("Unable to open %s for reading" % argv[1])

    ofs = oechem.oemolostream()
    if not ofs.open(argv[2]):
        oechem.OEThrow.Fatal("Unable to open %s for writing" % argv[2])

    for mol in ifs.GetOEGraphMols():
        numparts, partlist = oechem.OEDetermineComponents(mol)
        pred = oechem.OEPartPredAtom(partlist)

        for i in range(1, numparts + 1):
            pred.SelectPart(i)
            partmol = oechem.OEGraphMol()
            oechem.OESubsetMol(partmol, mol, pred)
            oechem.OEWriteMolecule(ofs, partmol)


if __name__ == "__main__":
    sys.exit(main(sys.argv))