def process():
if len(sys.argv) < 4:
print('Usage:',
sys.argv[0],
'[input.sdf] [exclude-molecules.sdf] [output.sdf]',
file=sys.stderr)
sys.exit(2)
ifs = Base.FileIOStream(sys.argv[1], 'r')
xifs = Base.FileIOStream(sys.argv[2], 'r')
ofs = Base.FileIOStream(sys.argv[3], 'w')
reader = Chem.SDFMoleculeReader(ifs)
xreader = Chem.SDFMoleculeReader(xifs)
writer = Chem.SDFMolecularGraphWriter(ofs)
mol = Chem.BasicMolecule()
Chem.setMultiConfImportParameter(reader, False)
Chem.setMultiConfImportParameter(xreader, False)
Chem.setMultiConfExportParameter(writer, False)
stats = Stats()
stats.read = 0
stats.dropped = 0
xhashes = set()
while xreader.read(mol):
setupMolecule(mol)
hashcode = Chem.calcHashCode(mol)
xhashes.add(hashcode)
while reader.read(mol):
#print('Processing Molecule ' + str(stats.read)
setupMolecule(mol)
hashcode = Chem.calcHashCode(mol)
if hashcode in xhashes:
stats.dropped += 1
print('Dropped Molecule ' + str(stats.read) + ': ' +
Chem.generateSMILES(mol) + ' ' + Chem.getName(mol),
file=sys.stderr)
else:
writer.write(mol)
stats.read += 1
if stats.read % 10000 == 0:
print('Processed ' + str(stats.read) + ' Molecules...',
file=sys.stderr)
print('', file=sys.stderr)
print('-- Summary --', file=sys.stderr)
print('Molecules processed: ' + str(stats.read), file=sys.stderr)
print('Molecules dropped: ' + str(stats.dropped), file=sys.stderr)
def calculate_molecule_hashcode(mol, stereo=True):
Chem.makeHydrogenDeplete(mol)
Chem.calcImplicitHydrogenCounts(mol, True)
if stereo:
Chem.calcAtomStereoDescriptors(mol, True)
Chem.calcBondStereoDescriptors(mol, True)
Chem.calcCIPPriorities(mol, True)
Chem.calcAtomCIPConfigurations(mol, True)
Chem.calcBondCIPConfigurations(mol, True)
return Chem.calcHashCode(mol)
else:
return Chem.calcHashCode(mol,
atom_flags=Chem.AtomPropertyFlag.TYPE
| Chem.AtomPropertyFlag.H_COUNT
| Chem.AtomPropertyFlag.FORMAL_CHARGE
| Chem.AtomPropertyFlag.AROMATICITY,
bond_flags=Chem.BondPropertyFlag.ORDER
| Chem.BondPropertyFlag.TOPOLOGY
| Chem.BondPropertyFlag.AROMATICITY)