def _transform_mol(self, mol):
"""Private method to transform a skchem molecule.
Use `transform` for the public method, which genericizes the argument
to iterables of mols.
Args:
mol (skchem.Mol): Molecule to calculate fingerprint for.
Returns:
np.array or dict:
Fingerprint as an array (or a dict if sparse).
"""
if self.as_bits and self.n_feats > 0:
fp = GetMorganFingerprintAsBitVect(
mol,
self.radius,
nBits=self.n_feats,
useFeatures=self.use_features,
useBondTypes=self.use_bond_types,
useChirality=self.use_chirality)
res = np.array(0)
ConvertToNumpyArray(fp, res)
res = res.astype(np.uint8)
else:
if self.n_feats <= 0:
res = GetMorganFingerprint(mol,
self.radius,
useFeatures=self.use_features,
useBondTypes=self.use_bond_types,
useChirality=self.use_chirality)
res = res.GetNonzeroElements()
if self.as_bits:
res = {k: int(v > 0) for k, v in res.items()}
else:
res = GetHashedMorganFingerprint(
mol,
self.radius,
nBits=self.n_feats,
useFeatures=self.use_features,
useBondTypes=self.use_bond_types,
useChirality=self.use_chirality)
res = np.array(list(res))
return res
def test__hashed_binary_fingerprints__ecfp(self) -> None:
fprintr = CircularFPFeaturizer(fp_mode="binary")
fps_mat_smi = fprintr.fit_transform(self.smis) # using SMILES
fps_mat_mol = fprintr.fit_transform(self.mols) # using Mol objects
# Output shape
self.assertEqual(fps_mat_smi.shape[0], self.n_mols)
self.assertEqual(fps_mat_smi.shape[1], fprintr.max_hash_value_)
self.assertEqual(fps_mat_mol.shape[0], self.n_mols)
self.assertEqual(fps_mat_mol.shape[1], fprintr.max_hash_value_)
# Fingerprint matrix structure
for i, mol in enumerate(self.mols):
fps_ref = GetMorganFingerprint(mol, radius=fprintr.radius, useFeatures=fprintr.use_features_,
useChirality=fprintr.use_chirality, useCounts=fprintr.use_counts_)
for hash in fps_ref.GetNonzeroElements():
self.assertTrue(fps_mat_smi[i, hash])
self.assertTrue(fps_mat_mol[i, hash])
# No other elements are set
self.assertEqual(np.sum(fps_mat_smi[i, :].data), len(fps_ref.GetNonzeroElements()))
self.assertEqual(np.sum(fps_mat_mol[i, :].data), len(fps_ref.GetNonzeroElements()))
def transform_mol(self,
molecule: Chem.rdchem.Mol) -> Tuple[np.ndarray, bool]:
use_chirality = self.__dict__.get('use_chirality', False)
fp = GetMorganFingerprint(
molecule,
radius=self.radius,
useFeatures=self.use_features,
useCounts=self.use_counts,
useChirality=use_chirality,
**self.fingerprint_extra_args,
)
fp = rdkit_sparse_array_to_np(fp.GetNonzeroElements().items(),
use_counts=self.use_counts,
fp_size=self.fp_size)
return fp, True
def test__string_output_format(self) -> None:
fprintr = CircularFPFeaturizer(output_format="sparse_string")
fps_str = fprintr.fit_transform(self.smis) # using SMILES
# Output shape
self.assertEqual(self.n_mols, len(fps_str))
# Fingerprint matrix structure
for i, mol in enumerate(self.mols):
fps_ref = GetMorganFingerprint(mol, radius=fprintr.radius, useFeatures=fprintr.use_features_,
useChirality=fprintr.use_chirality, useCounts=fprintr.use_counts_)
fp_i_from_str = eval("{" + fps_str[i] + "}")
for hash, cnt in fps_ref.GetNonzeroElements().items():
self.assertEqual(fp_i_from_str[hash], cnt)
def test__hashed_counting_fingerprints__fcfp(self) -> None:
fprintr = CircularFPFeaturizer(fp_type="FCFP")
fps_mat_smi = fprintr.fit_transform(self.smis) # using SMILES
fps_mat_mol = fprintr.fit_transform(self.mols) # using Mol objects
# Output shape
self.assertEqual(fps_mat_smi.shape[0], self.n_mols)
self.assertEqual(fps_mat_smi.shape[1], fprintr.max_hash_value_)
self.assertEqual(fps_mat_mol.shape[0], self.n_mols)
self.assertEqual(fps_mat_mol.shape[1], fprintr.max_hash_value_)
# Fingerprint matrix structure
for i, mol in enumerate(self.mols):
fps_ref = GetMorganFingerprint(mol, radius=fprintr.radius, useFeatures=fprintr.use_features_,
useChirality=fprintr.use_chirality, useCounts=fprintr.use_counts_)
for hash, cnt in fps_ref.GetNonzeroElements().items():
self.assertEqual(fps_mat_smi[i, hash], cnt)
self.assertEqual(fps_mat_mol[i, hash], cnt)