def test__string_output_format__binary(self) -> None:
fprintr = CircularFPFeaturizer(output_format="sparse_string", fp_mode="binary_folded")
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 = GetMorganFingerprintAsBitVect(
mol, radius=fprintr.radius, useFeatures=fprintr.use_features_, useChirality=fprintr.use_chirality,
nBits=fprintr.n_bits_
)
fp_i_from_str = eval("{" + fps_str[i] + "}")
for idx in fps_ref.GetOnBits():
self.assertIn(idx, fp_i_from_str)
def test__folded_binary_fingerprints__ecfp(self) -> None:
fprintr = CircularFPFeaturizer(fp_mode="binary_folded", n_bits_folded=512)
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.n_bits_folded)
self.assertEqual(fps_mat_mol.shape[0], self.n_mols)
self.assertEqual(fps_mat_mol.shape[1], fprintr.n_bits_folded)
# Fingerprint matrix structure
for i, mol in enumerate(self.mols):
fps_ref = GetMorganFingerprintAsBitVect(mol, radius=fprintr.radius, useFeatures=fprintr.use_features_,
useChirality=fprintr.use_chirality, nBits=fprintr.n_bits_folded)
on_bits = list(fps_ref.GetOnBits())
for j in range(fprintr.n_bits_folded):
if j in on_bits:
self.assertTrue(fps_mat_smi[i, j])
self.assertTrue(fps_mat_mol[i, j])
else:
self.assertFalse(fps_mat_smi[i, j])
self.assertFalse(fps_mat_mol[i, j])