def _unfolded_ecfps_nodupes(self):
if self._ecfps_no_dupes is None:
ecfp_nodupes_file = op.join(manysources_dataset_root(self.name),
'03-ecfps-nodupes', '%s.ecfps.h5' % self.name)
if not op.exists(ecfp_nodupes_file):
ecfps = self._unfolded_ecfps()
ufp = UnfoldedFingerprints(ecfps.molids,
ecfps.i2s,
zero_dupes(ecfps.csr, by_rows=False), # Hack 1, this should be Configurable
failed_molids=ecfps.failed_molids)
ensure_dir(op.dirname(ecfp_nodupes_file))
with open(op.join(op.dirname(ecfp_nodupes_file), 'config.txt'), 'w') as writer:
writer.write('Same as 02-ecfps, but removed columns that have the same value accross all rows.')
ufp.save(ecfp_nodupes_file)
self._ecfps = UnfoldedFingerprints.load(ecfp_nodupes_file)
return self._ecfps
def _unfolded_ecfps(self):
if self._ecfps is None:
ecfp_file = op.join(manysources_dataset_root(self.name), '02-ecfps', '%s.ecfps.h5' % self.name)
if not op.exists(ecfp_file):
fingerprinter = RDKMorganFingerprinter()
for molid, mol in self.mols():
print molid
fingerprinter.add_mol(molid, mol)
ensure_dir(op.dirname(ecfp_file))
with open(op.join(op.dirname(ecfp_file), 'config.json'), 'w') as writer:
writer.write(fingerprinter.what().id())
fingerprinter.fingerprints().save(ecfp_file)
self._ecfps = UnfoldedFingerprints.load(ecfp_file)
return self._ecfps