Align molecules by clique match

A program that aligns a database of molecules with a reference molecule based on the clique of matches between the reference and each query. Clique detection is the process of finding all possible correspondences between two graphs within a set of bounds, the upper bound being the MCS, and in the this example, the lower bound is up to five atoms different to the MCS.

Example

prompt > cliquealign.py ligand.pdb dbase.oeb.gz output.oeb.gz

Code

Download code

cliquealign.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.

#############################################################################
# Align two compounds based on the clique match
#############################################################################
import sys
from openeye import oechem


def CliqueAlign(refmol, fitmol, ofs):
    cs = oechem.OECliqueSearch(refmol, oechem.OEExprOpts_DefaultAtoms,
                               oechem.OEExprOpts_DefaultBonds)
    cs.SetSaveRange(5)
    cs.SetMinAtoms(6)
    for mi in cs.Match(fitmol):
        rmat = oechem.OEDoubleArray(9)
        trans = oechem.OEDoubleArray(3)
        overlay = True
        oechem.OERMSD(cs.GetPattern(), fitmol, mi, overlay, rmat, trans)
        oechem.OERotate(fitmol, rmat)
        oechem.OETranslate(fitmol, trans)
        oechem.OEWriteMolecule(ofs, fitmol)


def main(argv=[__name__]):
    if len(argv) != 4:
        oechem.OEThrow.Usage("%s <refmol> <fitmol> <outfile>" % argv[0])

    reffs = oechem.oemolistream()
    if not reffs.open(argv[1]):
        oechem.OEThrow.Fatal("Unable to open %s for reading" % argv[1])
    if not oechem.OEIs3DFormat(reffs.GetFormat()):
        oechem.OEThrow.Fatal("Invalid input format: need 3D coordinates")
    refmol = oechem.OEGraphMol()
    if not oechem.OEReadMolecule(reffs, refmol):
        oechem.OEThrow.Fatal("Unable to read molecule in %s" % argv[1])
    if not refmol.GetDimension() == 3:
        oechem.OEThrow.Fatal("%s doesn't have 3D coordinates" % refmol.GetTitle())

    fitfs = oechem.oemolistream()
    if not fitfs.open(argv[2]):
        oechem.OEThrow.Fatal("Unable to open %s for reading" % argv[2])
    if not oechem.OEIs3DFormat(fitfs.GetFormat()):
        oechem.OEThrow.Fatal("Invalid input format: need 3D coordinates")

    ofs = oechem.oemolostream()
    if not ofs.open(argv[3]):
        oechem.OEThrow.Fatal("Unable to open %s for writing" % argv[3])
    if not oechem.OEIs3DFormat(ofs.GetFormat()):
        oechem.OEThrow.Fatal("Invalid output format: need 3D coordinates")

    oechem.OEWriteConstMolecule(ofs, refmol)
    oechem.OESuppressHydrogens(refmol)

    for fitmol in fitfs.GetOEGraphMols():
        if not fitmol.GetDimension() == 3:
            oechem.OEThrow.Warning("%s doesn't have 3D coordinates" % fitmol.GetTitle())
            continue
        CliqueAlign(refmol, fitmol, ofs)


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