def _searchSubStructure (self, numsel, metric):
if metric is None:
metric = 'Substructural'
elif metric != 'Substructural':
LOG.warning (f'Metric {metric} is not compatible with the descriptors present in this space. Using Substructural')
metric = 'Substructural'
results = []
t1 = time.time()
# for each compound in the search set
for i, ivector in enumerate(self.X):
bitestring="".join(ivector.astype(str))
ifp = DataStructs.cDataStructs.CreateFromBitString(bitestring)
nselected = 0
selected_i = []
selected_d = []
# for each compound in the space
for j, jfp in enumerate(self.Xref):
if DataStructs.AllProbeBitsMatch(ifp, jfp):
# if True:
mi = Chem.MolFromSmiles(self.objinfo['SMILES'][i])
# mi = Chem.MolFromSmarts('C[!C](C)CC1*C=CCC1')
mj = Chem.MolFromSmiles(self.objinforef['SMILES'][j])
if mj.HasSubstructMatch(mi):
selected_i.append(j)
selected_d.append(1.00)
nselected+=1
if nselected >= numsel:
break
# results for molecule i are stored in a dictionary
results_info = {}
results_info['distances'] = [] # distances are allways stored
for oi in self.objinforef:
results_info[oi] = [] # all the objects information (name, smiles, ID, activity, etc.)
for sd,si in zip(selected_d, selected_i):
results_info['distances'].append(sd)
for oi in self.objinforef:
results_info[oi].append(self.objinforef[oi][si])
results.append(results_info)
LOG.info (f'search completed in time: {time.time()-t1:.4f} secs')
return True, results
def get_on_bits(self, mol):
if isinstance(mol, str):
mol = Chem.MolFromSmiles(mol)
mol_fp = Chem.RDKFingerprint(mol)
on_bits = []
for i, s_fp_i in enumerate(self.scaffold_fps):
if DataStructs.AllProbeBitsMatch(s_fp_i, mol_fp):
if mol.HasSubstructMatch(self.scaffolds[i]):
on_bits.append(i)
return on_bits
def _searchSubStructure (self, numsel, metric):
LOG.info ('searching for similar compounds using Substructure similarity')
results = []
t1 = time.time()
if self.isSMARTS:
nselected = 0
selected_i = []
selected_d = []
# for each compound in the space
for j, jfp in enumerate(self.Xref):
# mi = Chem.MolFromSmarts('C[!C](C)CC1*C=CCC1')
mi = Chem.MolFromSmarts(self.conveyor.getVal('SMARTS'))
mj = Chem.MolFromSmiles(self.objinforef['SMILES'][j])
if mj.HasSubstructMatch(mi):
selected_i.append(j)
selected_d.append(1.00)
nselected+=1
if nselected >= numsel:
break
# results for molecule i are stored in a dictionary
results_info = {}
results_info['distances'] = [] # distances are allways stored
for oi in self.objinforef:
results_info[oi] = [] # all the objects information (name, smiles, ID, activity, etc.)
for sd,si in zip(selected_d, selected_i):
results_info['distances'].append(sd)
for oi in self.objinforef:
results_info[oi].append(self.objinforef[oi][si])
results.append(results_info)
LOG.info (f'search completed in time: {time.time()-t1:.4f} secs')
return True, results
# for each compound in the search set
for i, ivector in enumerate(self.X):
bitestring="".join(ivector.astype(str))
ifp = DataStructs.cDataStructs.CreateFromBitString(bitestring)
nselected = 0
selected_i = []
selected_d = []
# for each compound in the space
for j, jfp in enumerate(self.Xref):
if DataStructs.AllProbeBitsMatch(ifp, jfp):
# if True:
mi = Chem.MolFromSmiles(self.objinfo['SMILES'][i])
mj = Chem.MolFromSmiles(self.objinforef['SMILES'][j])
if mj.HasSubstructMatch(mi):
selected_i.append(j)
selected_d.append(1.00)
nselected+=1
if nselected >= numsel:
break
# results for molecule i are stored in a dictionary
results_info = {}
results_info['distances'] = [] # distances are allways stored
for oi in self.objinforef:
results_info[oi] = [] # all the objects information (name, smiles, ID, activity, etc.)
for sd,si in zip(selected_d, selected_i):
results_info['distances'].append(sd)
for oi in self.objinforef:
results_info[oi].append(self.objinforef[oi][si])
results.append(results_info)
LOG.info (f'search completed in time: {time.time()-t1:.4f} secs')
return True, results
