def calculate_unhashed_fps(self,draw_substructures=False,image_directory='./images_substructures'):
# get the dictionary for the substructures
idxs = []
substr_ids = []
counts=[]
substructure_dictionaries = []
for mol_index,mol in enumerate(self.mols):
info={}
fp = _GetMorganFingerprint(mol,radius=self.max_radius,bitInfo=info)
substructure_dictionary = {k:mol_index for k,v in info.iteritems() if v[0][1] in self.radii}
substructure_dictionaries.append({k:mol_index for k,v in info.iteritems() if v[0][1] in self.radii})
substr_ids.append(substructure_dictionary.keys())
idxs.append([mol_index]*len(substructure_dictionary.keys()))
counts.append([ len(info.values()[x]) for x in _arange(0,len(info)) if info.values()[x][0][1] in self.radii])
# get the smiles for the substructures
amap = {}
substructures_smiles = {k:[_MolToSmiles(_PathToSubmol(mol,_FindAtomEnvironmentOfRadiusN(mol,v[0][1],v[0][0]),atomMap=amap))] for k,v in info.iteritems() if v[0][1] in self.radii}
self.substructures_smiles.update(substructures_smiles)
# generate the images for the substructures if required..
if draw_substructures:
if not _exists(image_directory):
_makedirs(image_directory)
for k,v in info.iteritems():
if k not in self.substructure_dictionary.keys() and v[0][1] in self.radii:
image_name="%s/Molecule_%d_substr_%d.pdf"%(image_directory,mol_index,k)
env=_FindAtomEnvironmentOfRadiusN(mol,v[0][1],v[0][0])
amap={}
submol=_PathToSubmol(mol,env,atomMap=amap)
_MolToFile(mol,image_name,size=(300,300),wedgeBonds=True,kekulize=True,highlightAtoms=amap.keys())
#self.substructure_dictionary = self._combine_dicts(substructure_dictionary,self.substructure_dictionary)
for d in substructure_dictionaries:
for k, v in d.iteritems():
l=self.substructure_dictionary.setdefault(k,[])
if v not in l:
l.append(v)
idxs = _array([val for sublist in idxs for val in sublist])
counts = _array([val for sublist in counts for val in sublist])
substr_ids_flattened = [val for sublist in substr_ids for val in sublist]
substr_ids = _array(substr_ids_flattened)
self.substructure_ids = substr_ids
if len(self.reference_substructure_keys)==0:
print "No input set of keys for the substructures. \nThus, the substructures present in the input molecules will be considered for the calculation of unhashed fingerprints."
columns = _array(list(set(self.substructure_dictionary.keys())))
columns = _sort(columns)
self.columns_unhashed = columns
dimensionality_unhashed = len(columns)
else:
columns = _array(self.reference_substructure_keys)
columns = _sort(columns)
self.columns_unhashed = columns
dimensionality_unhashed = len(columns)
fps_unhashed_binary = _zeros((len(self.mols),dimensionality_unhashed), dtype=int)
fps_unhashed_counts = _zeros((len(self.mols),dimensionality_unhashed), dtype=int)
mapping = _array([(substr_ids[x]==columns).nonzero() for x in _arange(0,len(substr_ids))])
mapping = mapping.flatten()
idxs = _array([idxs[x] for x in _arange(0,len(mapping)) if mapping[x].size != 0])
counts = _array([counts[x] for x in _arange(0,len(mapping)) if mapping[x].size != 0])
mapping = _array([mapping[x] for x in _arange(0,len(mapping)) if mapping[x].size != 0])
if len(mapping) == 0:
print "There is no intersection between the substructures \n(i)provided in the reference key set, and\n(ii) the substructures found in the input molecules."
return
fps_unhashed_binary[idxs,mapping] = _ones(len(mapping))
fps_unhashed_counts[idxs,mapping] = counts
self.fps_unhashed_binary = fps_unhashed_binary
self.fps_unhashed_counts = fps_unhashed_counts
def ones(*shp, dtype='float64'):
return _ones(shp, dtype=dtype)
def calculate_unhashed_fps(self,
draw_substructures=False,
image_directory='./images_substructures'):
# get the dictionary for the substructures
idxs = []
substr_ids = []
counts = []
for mol_index, mol in enumerate(self.mols):
info = {}
fp = _GetMorganFingerprint(mol,
radius=self.max_radius,
bitInfo=info)
substructure_dictionary = {
k: [mol_index]
for k, v in info.iteritems() if v[0][1] in self.radii
}
substr_ids.append(substructure_dictionary.keys())
idxs.append([mol_index] * len(substructure_dictionary.keys()))
counts.append([
len(info.values()[x]) for x in _arange(0, len(info))
if info.values()[x][0][1] in self.radii
])
# get the smiles for the substructures
amap = {}
substructures_smiles = {
k: [
_MolToSmiles(
_PathToSubmol(mol,
_FindAtomEnvironmentOfRadiusN(
mol, v[0][1], v[0][0]),
atomMap=amap))
]
for k, v in info.iteritems() if v[0][1] in self.radii
}
self.substructures_smiles.update(substructures_smiles)
# generate the images for the substructures if required..
if draw_substructures:
if not _exists(image_directory):
_makedirs(image_directory)
for k, v in info.iteritems():
if k not in self.substructure_dictionary.keys(
) and v[0][1] in self.radii:
image_name = "%s/Molecule_%d_substr_%d.pdf" % (
image_directory, mol_index, k)
env = _FindAtomEnvironmentOfRadiusN(
mol, v[0][1], v[0][0])
amap = {}
submol = _PathToSubmol(mol, env, atomMap=amap)
_MolToFile(mol,
image_name,
size=(300, 300),
wedgeBonds=True,
kekulize=True,
highlightAtoms=amap.keys())
self.substructure_dictionary = self._combine_dicts(
substructure_dictionary, self.substructure_dictionary)
idxs = _array([val for sublist in idxs for val in sublist])
counts = _array([val for sublist in counts for val in sublist])
substr_ids_flattened = [
val for sublist in substr_ids for val in sublist
]
substr_ids = _array(substr_ids_flattened)
self.substructure_ids = substr_ids
if len(self.reference_substructure_keys) == 0:
print "No input set of keys for the substructures. \nThus, the substructures present in the input molecules will be considered for the calculation of unhashed fingerprints."
columns = _array(list(set(self.substructure_dictionary.keys())))
columns = _sort(columns)
self.columns_unhashed = columns
dimensionality_unhashed = len(columns)
else:
columns = _array(self.reference_substructure_keys)
columns = _sort(columns)
self.columns_unhashed = columns
dimensionality_unhashed = len(columns)
fps_unhashed_binary = _zeros((len(self.mols), dimensionality_unhashed),
dtype=int)
fps_unhashed_counts = _zeros((len(self.mols), dimensionality_unhashed),
dtype=int)
mapping = _array([(substr_ids[x] == columns).nonzero()
for x in _arange(0, len(substr_ids))])
mapping = mapping.flatten()
idxs = _array([
idxs[x] for x in _arange(0, len(mapping)) if mapping[x].size != 0
])
counts = _array([
counts[x] for x in _arange(0, len(mapping)) if mapping[x].size != 0
])
mapping = _array([
mapping[x] for x in _arange(0, len(mapping))
if mapping[x].size != 0
])
if len(mapping) == 0:
print "There is no intersection between the substructures \n(i)provided in the reference key set, and\n(ii) the substructures found in the input molecules."
return
fps_unhashed_binary[idxs, mapping] = _ones(len(mapping))
fps_unhashed_counts[idxs, mapping] = counts
self.fps_unhashed_binary = fps_unhashed_binary
self.fps_unhashed_counts = fps_unhashed_counts
def ones(*shp, dtype="float64"):
return _ones(shp, dtype=dtype)