def CalculateMinHashFingerprint(mol: Chem.Mol,
radius: int = 3,
rtype: str = 'bitstring',
bits: int = 2048) -> Tuple[str, dict, Any]:
"""Calculate the MinHash Fingerprint (MHFP) of molecule.
doi: 10.1186/s13321-018-0321-8.
:param radius: maximum radius of atom-centered substructures.
:param rtype: Type of output, may either be:
bitstring (default), returns a binary string
numpy, return the underlying numpy array
dict, for a dict of bits turned on
:param bits: Number of folded bits (ignored if rtype != 'bitstring')
"""
mhfp = MHFPEncoder()
shingles = mhfp.shingling_from_mol(mol, radius, True, True, 1)
hash_values = mhfp.hash(shingles)
if rtype == 'numpy':
return hash_values
elif rtype == 'dict':
return {x: 1 for x in hash_values.tolist()}
else:
folded = mhfp.fold(hash_values, bits)
return ''.join(map(str, folded))
class MAP4Calculator:
def __init__(self, dimensions=1024, radius=2, is_counted=False, is_folded=False):
"""
MAP4 calculator class
"""
self.radius = radius
self.is_counted = is_counted
self.is_folded = is_folded
if self.is_folded:
self.encoder = MHFPEncoder(dimensions)
else:
self.encoder = tm.Minhash(dimensions)
def calculate(self, mol):
"""Calculates the atom pair minhashed fingerprint
Arguments:
mol -- rdkit mol object
Returns:
tmap VectorUint -- minhashed fingerprint
"""
atom_env_pairs = self._calculate(mol)
if self.is_folded:
return self._fold(atom_env_pairs)
return self.encoder.from_string_array(atom_env_pairs)
def calculate_many(self, mols):
""" Calculates the atom pair minhashed fingerprint
Arguments:
mols -- list of mols
Returns:
list of tmap VectorUint -- minhashed fingerprints list
"""
atom_env_pairs_list = [self._calculate(mol) for mol in mols]
if self.is_folded:
return [self._fold(pairs) for pairs in atom_env_pairs_list]
return self.encoder.batch_from_string_array(atom_env_pairs_list)
def _calculate(self, mol):
return self._all_pairs(mol, self._get_atom_envs(mol))
def _fold(self, pairs):
fp_hash = self.encoder.hash(set(pairs))
return self.encoder.fold(fp_hash)
def _get_atom_envs(self, mol):
atoms_env = {}
for atom in mol.GetAtoms():
idx = atom.GetIdx()
for radius in range(1, self.radius + 1):
if idx not in atoms_env:
atoms_env[idx] = []
atoms_env[idx].append(MAP4Calculator._find_env(mol, idx, radius))
return atoms_env
@classmethod
def _find_env(cls, mol, idx, radius):
env = rdmolops.FindAtomEnvironmentOfRadiusN(mol, radius, idx)
atom_map = {}
submol = Chem.PathToSubmol(mol, env, atomMap=atom_map)
if idx in atom_map:
smiles = Chem.MolToSmiles(submol, rootedAtAtom=atom_map[idx], canonical=True, isomericSmiles=False)
return smiles
return ''
def _all_pairs(self, mol, atoms_env):
atom_pairs = []
distance_matrix = GetDistanceMatrix(mol)
num_atoms = mol.GetNumAtoms()
shingle_dict = defaultdict(int)
for idx1, idx2 in itertools.combinations(range(num_atoms), 2):
dist = str(int(distance_matrix[idx1][idx2]))
for i in range(self.radius):
env_a = atoms_env[idx1][i]
env_b = atoms_env[idx2][i]
ordered = sorted([env_a, env_b])
shingle = '{}|{}|{}'.format(ordered[0], dist, ordered[1])
if self.is_counted:
shingle_dict[shingle] += 1
shingle += '|' + str(shingle_dict[shingle])
atom_pairs.append(shingle.encode('utf-8'))
return list(set(atom_pairs))
class Map4Fingerprint:
"""Calculates the atom pair minmashed fingerprint for a given molecular object.
Fingerprint is as described by `DOI: 10.1186/1758-2946-5-26` and implemented in the
[corresponding repository](https://github.com/reymond-group/map4).
"""
def __init__(self,
dimensions=1024,
radius=2,
is_counted=False,
is_folded=False,
return_strings=False):
"""
Parameters
----------
dimensions : int
(default = 1024)
Number of entries in the output map4 fingerprint.
radius : int
(default = 2)
Number of bonds away from atom centre to consider.
is_counted : bool
(default = False)
is_folded : bool
(default = False)
return_strings : bool
(default = False)
If True then returns substructure strings rather than hashed fingerprint.
"""
self.dimensions = int(dimensions)
self.radius = int(radius)
self.is_counted = bool(is_counted)
self.is_folded = bool(is_folded)
self.return_strings = bool(return_strings)
if self.is_folded:
self.encoder = MHFPEncoder(dimensions)
else:
self.encoder = tm.Minhash(dimensions)
def __call__(self, mol):
"""Calculates the atom pair minmashed fingerprint for a given molecular object.
Fingerprint is as described by `DOI: 10.1186/1758-2946-5-26` and implemented in the
[corresponding repository](https://github.com/reymond-group/map4).
Parameters
----------
mol : rdkit.Chem.rdchem.Mol
`rdkit` mol object.
Returns
-------
fp_arr : np.ndarray
shape(self.dimensions, )
Map4 fingerprint.
"""
atom_envs = self._get_atom_envs(mol)
atom_env_pairs = self._all_pairs(mol, atom_envs)
if self.is_folded:
fp_arr = self._fold(atom_env_pairs)
elif self.return_strings:
fp_arr = atom_env_pairs
else:
fp_arr = self.encoder.from_string_array(atom_env_pairs)
return np.asarray(fp_arr)
def _fold(self, pairs):
fp_hash = self.encoder.hash(set(pairs))
return self.encoder.fold(fp_hash, self.dimensions)
def _get_atom_envs(self, mol):
atoms_env = {}
for atom in mol.GetAtoms():
idx = atom.GetIdx()
for radius in range(1, self.radius + 1):
if idx not in atoms_env:
atoms_env[idx] = []
atoms_env[idx].append(
Map4Fingerprint._find_env(mol, idx, radius))
return atoms_env
@classmethod
def _find_env(cls, mol, idx, radius):
env = rdmolops.FindAtomEnvironmentOfRadiusN(mol, radius, idx)
atom_map = {}
submol = Chem.PathToSubmol(mol, env, atomMap=atom_map)
if idx in atom_map:
smiles = Chem.MolToSmiles(submol,
rootedAtAtom=atom_map[idx],
canonical=True,
isomericSmiles=False)
return smiles
return ''
def _all_pairs(self, mol, atoms_env):
atom_pairs = []
distance_matrix = GetDistanceMatrix(mol)
num_atoms = mol.GetNumAtoms()
shingle_dict = defaultdict(int)
for idx1, idx2 in itertools.combinations(range(num_atoms), 2):
dist = str(int(distance_matrix[idx1][idx2]))
for i in range(self.radius):
env_a = atoms_env[idx1][i]
env_b = atoms_env[idx2][i]
ordered = sorted([env_a, env_b])
shingle = '{}|{}|{}'.format(ordered[0], dist, ordered[1])
if self.is_counted:
shingle_dict[shingle] += 1
shingle += '|' + str(shingle_dict[shingle])
atom_pairs.append(shingle.encode('utf-8'))
return list(set(atom_pairs))