Datasets
Models
Diff of
/tests/test_fingerprints.py
[000000]
..
[3b722e]
Switch to unified view
| a | b/tests/test_fingerprints.py | ||
|---|---|---|---|
| 1 | import os |
||
| 2 | import sys |
||
| 3 | from itertools import combinations |
||
| 4 | |||
| 5 | import numpy as np |
||
| 6 | from scipy.sparse import vstack as sparse_vstack |
||
| 7 | from numpy.testing import (assert_array_equal, |
||
| 8 | assert_array_almost_equal, |
||
| 9 | assert_almost_equal) |
||
| 10 | |||
| 11 | import pytest |
||
| 12 | |||
| 13 | import oddt |
||
| 14 | from oddt.fingerprints import (InteractionFingerprint, |
||
| 15 | SimpleInteractionFingerprint, |
||
| 16 | ECFP, |
||
| 17 | _ECFP_atom_repr, |
||
| 18 | SPLIF, |
||
| 19 | similarity_SPLIF, |
||
| 20 | PLEC, |
||
| 21 | fold, |
||
| 22 | MIN_HASH_VALUE, |
||
| 23 | MAX_HASH_VALUE, |
||
| 24 | sparse_to_dense, |
||
| 25 | sparse_to_csr_matrix, |
||
| 26 | csr_matrix_to_sparse, |
||
| 27 | dense_to_sparse, |
||
| 28 | get_molecular_shingles, |
||
| 29 | hash_fnv1a_python, |
||
| 30 | dice, |
||
| 31 | tanimoto) |
||
| 32 | from .utils import shuffle_mol |
||
| 33 | |||
| 34 | |||
| 35 | test_data_dir = os.path.dirname(os.path.abspath(__file__)) |
||
| 36 | |||
| 37 | protein = next(oddt.toolkit.readfile('pdb', os.path.join( |
||
| 38 | test_data_dir, 'data/pdbbind/10gs/10gs_pocket.pdb'))) |
||
| 39 | protein.protein = True |
||
| 40 | protein.addh(only_polar=True) |
||
| 41 | |||
| 42 | ligand = next(oddt.toolkit.readfile('sdf', os.path.join( |
||
| 43 | test_data_dir, 'data/pdbbind/10gs/10gs_ligand.sdf'))) |
||
| 44 | ligand.addh(only_polar=True) |
||
| 45 | |||
| 46 | |||
| 47 | def test_folding(): |
||
| 48 | """FP Folding""" |
||
| 49 | # Upper bound |
||
| 50 | assert_array_equal(fold([MAX_HASH_VALUE], 1024), [1023]) |
||
| 51 | assert_array_equal(fold([MAX_HASH_VALUE], 1234567890), [1234567889]) |
||
| 52 | assert_array_equal(fold([MAX_HASH_VALUE], MAX_HASH_VALUE / 2), |
||
| 53 | [MAX_HASH_VALUE / 2 - 1]) |
||
| 54 | assert_array_equal(fold([MAX_HASH_VALUE], MAX_HASH_VALUE - 1), |
||
| 55 | [MAX_HASH_VALUE - 2]) |
||
| 56 | # Lower bound |
||
| 57 | assert_array_equal(fold([MIN_HASH_VALUE], 1024), [0]) |
||
| 58 | assert_array_equal(fold([MIN_HASH_VALUE], 1234567890), [0]) |
||
| 59 | assert_array_equal(fold([MIN_HASH_VALUE], MAX_HASH_VALUE / 2), [0]) |
||
| 60 | assert_array_equal(fold([MIN_HASH_VALUE], MAX_HASH_VALUE - 1), [0]) |
||
| 61 | |||
| 62 | # Range check |
||
| 63 | fp = np.arange(1, MAX_HASH_VALUE, 1e6, dtype=int) |
||
| 64 | assert_array_equal(fold(fp, MAX_HASH_VALUE), fp - 1) |
||
| 65 | |||
| 66 | @pytest.mark.skipif(sys.version_info > (3, 7), reason="Only testable with old Python Hash implementation") |
||
| 67 | def test_hashing_function(): |
||
| 68 | """Verify the implementation of Python 2.4-3.7 hash function in Python""" |
||
| 69 | sample_list = list(range(-10, 10)) |
||
| 70 | # add nested structure |
||
| 71 | sample_list.append(tuple(sample_list)) |
||
| 72 | sample_list.append(tuple(sample_list)) |
||
| 73 | for sample_tuple in combinations(sample_list, r=5): |
||
| 74 | python_hash = hash(sample_tuple) |
||
| 75 | custom_hash = hash_fnv1a_python(sample_tuple) |
||
| 76 | assert python_hash == custom_hash |
||
| 77 | |||
| 78 | |||
| 79 | def test_sparse_densify(): |
||
| 80 | """FP densify""" |
||
| 81 | sparse_fp = [0, 33, 49, 53, 107, 156, 161, 203, 215, 230, 251, 269, 299, |
||
| 82 | 323, 331, 376, 389, 410, 427, 430, 450, 484, 538, 592, 593, |
||
| 83 | 636, 646, 658, 698, 699, 702, 741, 753, 807, 850, 861, 882, |
||
| 84 | 915, 915, 915, 969, 969, 1023] |
||
| 85 | |||
| 86 | # count vectors |
||
| 87 | dense = sparse_to_dense(sparse_fp, size=1024, count_bits=True) |
||
| 88 | csr = sparse_to_csr_matrix(sparse_fp, size=1024, count_bits=True) |
||
| 89 | assert_array_equal(dense.reshape(1, -1), csr.toarray()) |
||
| 90 | resparsed = dense_to_sparse(dense) |
||
| 91 | resparsed_csr = csr_matrix_to_sparse(csr) |
||
| 92 | assert_array_equal(sparse_fp, resparsed) |
||
| 93 | assert_array_equal(sparse_fp, resparsed_csr) |
||
| 94 | |||
| 95 | # bool vectors |
||
| 96 | dense = sparse_to_dense(sparse_fp, size=1024, count_bits=False) |
||
| 97 | csr = sparse_to_csr_matrix(sparse_fp, size=1024, count_bits=False) |
||
| 98 | assert_array_equal(dense.reshape(1, -1), csr.toarray()) |
||
| 99 | resparsed = dense_to_sparse(dense) |
||
| 100 | resparsed_csr = csr_matrix_to_sparse(csr) |
||
| 101 | assert_array_equal(np.unique(sparse_fp), resparsed) |
||
| 102 | assert_array_equal(np.unique(sparse_fp), resparsed_csr) |
||
| 103 | |||
| 104 | # test stacking |
||
| 105 | np.random.seed(0) |
||
| 106 | sparse_fps = np.random.randint(0, 1024, size=(20, 100)) |
||
| 107 | dense = np.vstack([sparse_to_dense(fp, size=1024) for fp in sparse_fps]) |
||
| 108 | csr = sparse_vstack(sparse_to_csr_matrix(fp, size=1024) for fp in sparse_fps) |
||
| 109 | assert_array_equal(dense, csr.toarray()) |
||
| 110 | |||
| 111 | # test exceptions |
||
| 112 | with pytest.raises(ValueError): |
||
| 113 | csr_matrix_to_sparse(np.array([1, 2, 3])) |
||
| 114 | |||
| 115 | |||
| 116 | def test_InteractionFingerprint(): |
||
| 117 | """Interaction Fingerprint test""" |
||
| 118 | if oddt.toolkit.backend == 'ob': |
||
| 119 | IFP = [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 6, 0, 0, 0, 0, 0, 0, |
||
| 120 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, |
||
| 121 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 2, 0, 0, 0, 0, 0, 0, 0, |
||
| 122 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, |
||
| 123 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, |
||
| 124 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, |
||
| 125 | 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, |
||
| 126 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, |
||
| 127 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, |
||
| 128 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, |
||
| 129 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, |
||
| 130 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, |
||
| 131 | 1, 0, 0, 0, 0, 0, 0, 2, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, |
||
| 132 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, |
||
| 133 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, |
||
| 134 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, |
||
| 135 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, |
||
| 136 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, |
||
| 137 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, |
||
| 138 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, |
||
| 139 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, |
||
| 140 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, |
||
| 141 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 2, 0, 0, |
||
| 142 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0] |
||
| 143 | else: |
||
| 144 | IFP = [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 6, 0, 0, 0, 0, 0, 0, |
||
| 145 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, |
||
| 146 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 2, 0, 0, 0, 0, 0, 0, 0, |
||
| 147 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, |
||
| 148 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, |
||
| 149 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, |
||
| 150 | 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, |
||
| 151 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, |
||
| 152 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, |
||
| 153 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, |
||
| 154 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, |
||
| 155 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, |
||
| 156 | 1, 0, 0, 0, 0, 0, 0, 2, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, |
||
| 157 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, |
||
| 158 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, |
||
| 159 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, |
||
| 160 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, |
||
| 161 | 0, 0, 0, 0, 0, 1, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, |
||
| 162 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, |
||
| 163 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, |
||
| 164 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, |
||
| 165 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, |
||
| 166 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, |
||
| 167 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0] |
||
| 168 | assert_array_equal(IFP, InteractionFingerprint(ligand, protein)) |
||
| 169 | |||
| 170 | |||
| 171 | def test_SimpleInteractionFingerprint(): |
||
| 172 | """Simple Interaction Fingerprint test """ |
||
| 173 | SIFP = [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 2, |
||
| 174 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 2, 0, 0, 0, 0, 0, |
||
| 175 | 0, 0, 0, 0, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, |
||
| 176 | 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, |
||
| 177 | 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, |
||
| 178 | 0, 0, 6, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, |
||
| 179 | 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, |
||
| 180 | 0, 0, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0] |
||
| 181 | assert_array_equal(SIFP, SimpleInteractionFingerprint(ligand, protein)) |
||
| 182 | |||
| 183 | |||
| 184 | def test_IFP_SIFP_Folding_cum_sum(): |
||
| 185 | """Checks, whether InteractionFingerprint and SimpleInteractionFingerprint outcomes matches""" |
||
| 186 | IFP = np.sum(InteractionFingerprint(ligand, protein), axis=0) |
||
| 187 | SIFP = np.sum(SimpleInteractionFingerprint(ligand, protein), axis=0) |
||
| 188 | assert_array_equal(IFP, SIFP) |
||
| 189 | |||
| 190 | |||
| 191 | def test_similarity(): |
||
| 192 | """FP similarity""" |
||
| 193 | mols = list(oddt.toolkit.readfile('sdf', os.path.join( |
||
| 194 | test_data_dir, 'data/dude/xiap/actives_docked.sdf'))) |
||
| 195 | mols = list(filter(lambda x: x.title == '312335', mols)) |
||
| 196 | list(map(lambda x: x.addh(only_polar=True), mols)) |
||
| 197 | receptor = next(oddt.toolkit.readfile('pdb', os.path.join( |
||
| 198 | test_data_dir, 'data/dude/xiap/receptor_rdkit.pdb'))) |
||
| 199 | receptor.protein = True |
||
| 200 | receptor.addh(only_polar=True) |
||
| 201 | ref = SimpleInteractionFingerprint(mols[0], receptor) |
||
| 202 | |||
| 203 | outcome = [dice(ref, SimpleInteractionFingerprint( |
||
| 204 | mol, receptor)) for mol in mols[1:]] |
||
| 205 | target_outcome = np.array([0.742857, 0.645161, 0.727273, 0.571429, |
||
| 206 | 0.727273, 0.588235, 0.75, 0.551724, |
||
| 207 | 0.551724, 0.6875, 0.514286, 0.6875, |
||
| 208 | 0.592593, 0.647059, 0.736842, 0.62069, |
||
| 209 | 0.545455, 0.533333, 0.606061]) |
||
| 210 | assert_array_almost_equal(outcome, target_outcome) |
||
| 211 | |||
| 212 | outcome = [tanimoto(ref, SimpleInteractionFingerprint( |
||
| 213 | mol, receptor)) for mol in mols[1:]] |
||
| 214 | target_outcome = np.array([0.636364, 0.5, 0.666667, 0.384615, 0.666667, |
||
| 215 | 0.545455, 0.666667, 0.5, 0.363636, 0.666667, |
||
| 216 | 0.555556, 0.555556, 0.625, 0.6, 0.727273, |
||
| 217 | 0.555556, 0.5, 0.4, 0.363636]) |
||
| 218 | assert_array_almost_equal(outcome, target_outcome) |
||
| 219 | |||
| 220 | |||
| 221 | def test_sparse_similarity(): |
||
| 222 | """Sparse similarity""" |
||
| 223 | mol1 = oddt.toolkit.readstring("smi", "CC1=C(C(=CC=C1)C)NC(=O)CN2CCN(CC2)CC(=O)N3CCC4=C(C3)C=CS4") |
||
| 224 | mol2 = oddt.toolkit.readstring("smi", "CC1=C(C(=CC=C1)O)NC(=O)CN2CCN(CC2)CC(=O)N3CCC4=C(C3)C=CS4") |
||
| 225 | |||
| 226 | mol1_fp_dense = ECFP(mol1, depth=8, size=4096, sparse=False) |
||
| 227 | mol2_fp_dense = ECFP(mol2, depth=8, size=4096, sparse=False) |
||
| 228 | |||
| 229 | mol1_fp_sparse = ECFP(mol1, depth=8, size=4096, sparse=True) |
||
| 230 | mol2_fp_sparse = ECFP(mol2, depth=8, size=4096, sparse=True) |
||
| 231 | |||
| 232 | assert_almost_equal(dice(mol1_fp_sparse, mol2_fp_sparse, sparse=True), |
||
| 233 | dice(mol1_fp_dense, mol2_fp_dense)) |
||
| 234 | assert dice([], [], sparse=True) == 0. |
||
| 235 | assert dice(np.zeros(10), np.zeros(10), sparse=False) == 0. |
||
| 236 | assert_almost_equal(tanimoto(mol1_fp_sparse, mol2_fp_sparse, sparse=True), |
||
| 237 | tanimoto(mol1_fp_dense, mol2_fp_dense)) |
||
| 238 | assert tanimoto([], [], sparse=True) == 0. |
||
| 239 | assert tanimoto(np.zeros(10), np.zeros(10), sparse=False) == 0. |
||
| 240 | |||
| 241 | |||
| 242 | def test_ecfp_repr(): |
||
| 243 | """Test exact ECFP representation to track down the changes""" |
||
| 244 | mol = oddt.toolkit.readstring("smi", "CC1=C(C(=CC=C1)C)NC(=O)CN2CCN(CC2)CC(=O)N3CCC4=C(C3)C=CS4") |
||
| 245 | |||
| 246 | res = [(6, 0, 1, 3, 0, 0, 0), (6, 0, 3, 0, 0, 1, 1), (6, 0, 3, 0, 0, 1, 1), (6, 0, 3, 0, 0, 1, 1), |
||
| 247 | (6, 0, 2, 1, 0, 1, 1), (6, 0, 2, 1, 0, 1, 1), (6, 0, 2, 1, 0, 1, 1), (6, 0, 1, 3, 0, 0, 0), |
||
| 248 | (7, 0, 2, 1, 0, 0, 0), (6, 0, 3, 0, 0, 0, 0), (8, 0, 1, 0, 0, 0, 0), (6, 0, 2, 2, 0, 0, 0), |
||
| 249 | (7, 0, 3, 0, 0, 1, 0), (6, 0, 2, 2, 0, 1, 0), (6, 0, 2, 2, 0, 1, 0), (7, 0, 3, 0, 0, 1, 0), |
||
| 250 | (6, 0, 2, 2, 0, 1, 0), (6, 0, 2, 2, 0, 1, 0), (6, 0, 2, 2, 0, 0, 0), (6, 0, 3, 0, 0, 0, 0), |
||
| 251 | (8, 0, 1, 0, 0, 0, 0), (7, 0, 3, 0, 0, 1, 0), (6, 0, 2, 2, 0, 1, 0), (6, 0, 2, 2, 0, 1, 0), |
||
| 252 | (6, 0, 3, 0, 0, 1, 1), (6, 0, 3, 0, 0, 1, 1), (6, 0, 2, 2, 0, 1, 0), (6, 0, 2, 1, 0, 1, 1), |
||
| 253 | (6, 0, 2, 1, 0, 1, 1), (16, 0, 2, 0, 0, 1, 1)] |
||
| 254 | |||
| 255 | assert_array_equal([_ECFP_atom_repr(mol, i) for i in range(len(mol.atoms))], res) |
||
| 256 | |||
| 257 | |||
| 258 | def test_ecfp(): |
||
| 259 | """ECFP fingerprints""" |
||
| 260 | mol1 = oddt.toolkit.readstring("smi", "CC1=C(C(=CC=C1)C)NC(=O)CN2CCN(CC2)CC(=O)N3CCC4=C(C3)C=CS4") |
||
| 261 | mol2 = oddt.toolkit.readstring("smi", "CC1=C(C(=CC=C1)O)NC(=O)CN2CCN(CC2)CC(=O)N3CCC4=C(C3)C=CS4") |
||
| 262 | |||
| 263 | mol1_fp = ECFP(mol1, depth=8, size=4096, sparse=False) |
||
| 264 | mol2_fp = ECFP(mol2, depth=8, size=4096, sparse=False) |
||
| 265 | |||
| 266 | ref1 = [2, 100, 176, 185, 200, 203, 359, 382, 447, 509, 518, 550, 572, 583, |
||
| 267 | 598, 606, 607, 684, 818, 821, 832, 861, 960, 992, 1006, 1019, 1042, |
||
| 268 | 1050, 1059, 1103, 1175, 1281, 1315, 1377, 1431, 1470, 1479, 1512, |
||
| 269 | 1577, 1588, 1598, 1620, 1633, 1647, 1663, 1723, 1749, 1751, 1775, |
||
| 270 | 1781, 1821, 1837, 1899, 1963, 1969, 1986, 2013, 2253, 2343, 2355, |
||
| 271 | 2368, 2435, 2547, 2654, 2657, 2702, 2722, 2725, 2803, 2816, 2853, |
||
| 272 | 2870, 2920, 2992, 3028, 3056, 3074, 3103, 3190, 3203, 3277, 3321, |
||
| 273 | 3362, 3377, 3383, 3401, 3512, 3546, 3552, 3585, 3593, 3617, 3674, |
||
| 274 | 3759, 3784, 3790, 3832, 3895, 3937, 3956, 3974, 4007, 4033] |
||
| 275 | |||
| 276 | ref2 = [43, 100, 176, 200, 203, 231, 382, 396, 447, 490, 518, 583, 606, |
||
| 277 | 607, 650, 818, 821, 832, 840, 861, 907, 950, 960, 992, 1006, 1013, |
||
| 278 | 1019, 1042, 1050, 1059, 1103, 1104, 1112, 1175, 1281, 1293, 1315, |
||
| 279 | 1377, 1431, 1470, 1512, 1543, 1577, 1588, 1598, 1633, 1647, 1663, |
||
| 280 | 1723, 1749, 1751, 1757, 1759, 1775, 1781, 1821, 1837, 1880, 1963, |
||
| 281 | 1969, 1986, 2253, 2355, 2368, 2435, 2544, 2547, 2654, 2702, 2722, |
||
| 282 | 2725, 2726, 2799, 2816, 2853, 2870, 2920, 2992, 3028, 3074, 3190, |
||
| 283 | 3203, 3277, 3290, 3333, 3362, 3383, 3401, 3512, 3546, 3552, 3585, |
||
| 284 | 3593, 3617, 3640, 3660, 3674, 3759, 3784, 3790, 3805, 3832, 3856, |
||
| 285 | 3895, 3924, 3956, 3974, 3992, 4007, 4033] |
||
| 286 | |||
| 287 | assert_array_equal(ref1, np.where(mol1_fp)[0]) |
||
| 288 | assert_array_equal(ref2, np.where(mol2_fp)[0]) |
||
| 289 | |||
| 290 | assert_almost_equal(dice(mol1_fp, mol2_fp), 0.69999999) |
||
| 291 | assert_almost_equal(tanimoto(mol1_fp, mol2_fp), 0.63846153) |
||
| 292 | |||
| 293 | # adding Hs should not change anything |
||
| 294 | mol1.addh() |
||
| 295 | mol2.addh() |
||
| 296 | |||
| 297 | mol1_fp = ECFP(mol1, depth=8, size=4096, sparse=False) |
||
| 298 | mol2_fp = ECFP(mol2, depth=8, size=4096, sparse=False) |
||
| 299 | |||
| 300 | assert_array_equal(ref1, np.where(mol1_fp)[0]) |
||
| 301 | assert_array_equal(ref2, np.where(mol2_fp)[0]) |
||
| 302 | |||
| 303 | assert_almost_equal(dice(mol1_fp, mol2_fp), 0.69999999) |
||
| 304 | assert_almost_equal(tanimoto(mol1_fp, mol2_fp), 0.63846153) |
||
| 305 | |||
| 306 | # removig Hs should not change anything |
||
| 307 | mol1.removeh() |
||
| 308 | mol2.removeh() |
||
| 309 | |||
| 310 | mol1_fp = ECFP(mol1, depth=8, size=4096, sparse=False) |
||
| 311 | mol2_fp = ECFP(mol2, depth=8, size=4096, sparse=False) |
||
| 312 | |||
| 313 | assert_array_equal(ref1, np.where(mol1_fp)[0]) |
||
| 314 | assert_array_equal(ref2, np.where(mol2_fp)[0]) |
||
| 315 | |||
| 316 | assert_almost_equal(dice(mol1_fp, mol2_fp), 0.69999999) |
||
| 317 | assert_almost_equal(tanimoto(mol1_fp, mol2_fp), 0.63846153) |
||
| 318 | |||
| 319 | |||
| 320 | def test_fcfp(): |
||
| 321 | """FCFP fingerprints""" |
||
| 322 | mol1 = oddt.toolkit.readstring("smi", "CC1=C(C(=CC=C1)C)NC(=O)CN2CCN(CC2)CC(=O)N3CCC4=C(C3)C=CS4") |
||
| 323 | mol2 = oddt.toolkit.readstring("smi", "CC1=C(C(=CC=C1)O)NC(=O)CN2CCN(CC2)CC(=O)N3CCC4=C(C3)C=CS4") |
||
| 324 | |||
| 325 | mol1_fp = ECFP(mol1, depth=8, size=4096, |
||
| 326 | sparse=False, use_pharm_features=True) |
||
| 327 | mol2_fp = ECFP(mol2, depth=8, size=4096, |
||
| 328 | sparse=False, use_pharm_features=True) |
||
| 329 | |||
| 330 | ref1 = [46, 111, 305, 310, 362, 384, 409, 451, 467, 548, 572, 595, 607, |
||
| 331 | 608, 620, 659, 691, 699, 724, 743, 752, 842, 926, 935, 974, 1037, |
||
| 332 | 1072, 1094, 1135, 1143, 1161, 1172, 1313, 1325, 1368, 1399, 1461, |
||
| 333 | 1486, 1488, 1492, 1603, 1619, 1648, 1665, 1666, 1838, 1887, 1900, |
||
| 334 | 1948, 1961, 1972, 1975, 1996, 2000, 2052, 2085, 2094, 2174, 2232, |
||
| 335 | 2236, 2368, 2382, 2383, 2402, 2483, 2492, 2527, 2593, 2616, 2706, |
||
| 336 | 2789, 2899, 2922, 2945, 2966, 3102, 3117, 3176, 3189, 3215, 3225, |
||
| 337 | 3297, 3326, 3349, 3373, 3513, 3525, 3535, 3601, 3619, 3780, 3820, |
||
| 338 | 3897, 3919, 3976, 3981, 4050, 4079, 4091] |
||
| 339 | |||
| 340 | ref2 = [46, 111, 143, 172, 259, 305, 362, 409, 451, 467, 507, 518, 548, |
||
| 341 | 583, 595, 607, 608, 620, 639, 691, 693, 724, 752, 784, 825, 842, |
||
| 342 | 926, 1037, 1087, 1094, 1098, 1135, 1143, 1161, 1172, 1286, 1325, |
||
| 343 | 1368, 1371, 1395, 1399, 1461, 1486, 1488, 1492, 1565, 1619, 1648, |
||
| 344 | 1655, 1665, 1887, 1890, 1900, 1948, 1961, 1968, 1972, 1975, 1976, |
||
| 345 | 1996, 2000, 2007, 2094, 2125, 2174, 2232, 2236, 2368, 2382, 2383, |
||
| 346 | 2483, 2492, 2571, 2593, 2606, 2638, 2706, 2789, 2922, 2945, 2966, |
||
| 347 | 2986, 3030, 3100, 3102, 3117, 3227, 3326, 3350, 3373, 3406, 3419, |
||
| 348 | 3535, 3577, 3619, 3697, 3742, 3820, 3839, 3919, 3981, 4043, 4050, |
||
| 349 | 4079, 4091] |
||
| 350 | |||
| 351 | assert_array_equal(ref1, np.where(mol1_fp)[0]) |
||
| 352 | assert_array_equal(ref2, np.where(mol2_fp)[0]) |
||
| 353 | |||
| 354 | assert_almost_equal(dice(mol1_fp, mol2_fp), 0.64074074) |
||
| 355 | assert_almost_equal(tanimoto(mol1_fp, mol2_fp), 0.5) |
||
| 356 | |||
| 357 | # adding Hs should not change anything |
||
| 358 | mol1.addh() |
||
| 359 | mol2.addh() |
||
| 360 | |||
| 361 | assert_array_equal(ref1, np.where(mol1_fp)[0]) |
||
| 362 | assert_array_equal(ref2, np.where(mol2_fp)[0]) |
||
| 363 | |||
| 364 | assert_almost_equal(dice(mol1_fp, mol2_fp), 0.64074074) |
||
| 365 | assert_almost_equal(tanimoto(mol1_fp, mol2_fp), 0.5) |
||
| 366 | |||
| 367 | |||
| 368 | def test_ecfp_invaraiants(): |
||
| 369 | """ECFP: test random reordering""" |
||
| 370 | sildenafil = oddt.toolkit.readstring("smi", "CCCc1nn(C)c2c(=O)[nH]c(-c3cc(S(=O)(=O)N4CCN(C)CC4)ccc3OCC)nc12") |
||
| 371 | |||
| 372 | params = {'depth': 4, 'size': 4096, 'sparse': True} |
||
| 373 | fp = ECFP(sildenafil, **params) |
||
| 374 | |||
| 375 | for n in range(10): |
||
| 376 | sildenafil = shuffle_mol(sildenafil) |
||
| 377 | assert_array_equal(fp, ECFP(sildenafil, **params)) |
||
| 378 | |||
| 379 | |||
| 380 | def test_splif(): |
||
| 381 | """SPLIF fingerprints""" |
||
| 382 | mols = list(oddt.toolkit.readfile('sdf', os.path.join( |
||
| 383 | test_data_dir, 'data/dude/xiap/actives_docked.sdf'))) |
||
| 384 | mols = list(filter(lambda x: x.title == '312335', mols)) |
||
| 385 | list(map(lambda x: x.addh(only_polar=True), mols)) |
||
| 386 | receptor = next(oddt.toolkit.readfile('pdb', os.path.join( |
||
| 387 | test_data_dir, 'data/dude/xiap/receptor_rdkit.pdb'))) |
||
| 388 | receptor.protein = True |
||
| 389 | receptor.addh(only_polar=True) |
||
| 390 | splif = SPLIF(mols[0], receptor) |
||
| 391 | reference = [6, 38, 49, 53, 53, 53, 70, 70, 81, 81, 81, 81, 165, 216, 219, |
||
| 392 | 249, 330, 330, 333, 377, 380, 396, 396, 396, 423, 423, 479, |
||
| 393 | 479, 498, 498, 498, 570, 592, 625, 638, 768, 768, 817, 818, |
||
| 394 | 818, 818, 818, 858, 884, 888, 907, 930, 934, 935, 971, 1023, |
||
| 395 | 1041, 1115, 1142, 1184, 1184, 1252, 1263, 1269, 1275, 1275, |
||
| 396 | 1275, 1315, 1315, 1315, 1337, 1337, 1344, 1351, 1396, 1435, |
||
| 397 | 1465, 1502, 1502, 1502, 1502, 1569, 1569, 1569, 1569, 1569, |
||
| 398 | 1569, 1569, 1569, 1640, 1645, 1660, 1660, 1697, 1697, 1716, |
||
| 399 | 1746, 1756, 1778, 1901, 1937, 1997, 2000, 2000, 2000, 2007, |
||
| 400 | 2007, 2020, 2070, 2195, 2274, 2294, 2319, 2415, 2417, 2509, |
||
| 401 | 2528, 2578, 2578, 2584, 2590, 2590, 2624, 2636, 2678, 2678, |
||
| 402 | 2678, 2678, 2678, 2776, 2776, 2789, 2862, 2862, 2894, 2894, |
||
| 403 | 2894, 2923, 2923, 3058, 3073, 3073, 3073, 3073, 3137, 3159, |
||
| 404 | 3159, 3159, 3186, 3218, 3218, 3279, 3279, 3281, 3338, 3358, |
||
| 405 | 3360, 3368, 3387, 3609, 3636, 3636, 3713, 3713, 3716, 3716, |
||
| 406 | 3748, 3767, 3769, 3854, 3871, 3912, 3968, 3986, 3994, 3994, |
||
| 407 | 4069] |
||
| 408 | |||
| 409 | assert splif['hash'].shape == (172,) |
||
| 410 | assert_array_equal(splif['ligand_coords'].shape, (172, 7, 3)) |
||
| 411 | assert_array_equal(splif['protein_coords'].shape, (172, 7, 3)) |
||
| 412 | assert_array_equal(reference, splif['hash']) |
||
| 413 | |||
| 414 | |||
| 415 | def test_splif_similarity(): |
||
| 416 | """SPLIF similarity""" |
||
| 417 | mols = list(oddt.toolkit.readfile('sdf', os.path.join( |
||
| 418 | test_data_dir, 'data/dude/xiap/actives_docked.sdf'))) |
||
| 419 | mols = list(filter(lambda x: x.title == '312335', mols)) |
||
| 420 | list(map(lambda x: x.addh(only_polar=True), mols)) |
||
| 421 | receptor = next(oddt.toolkit.readfile('pdb', os.path.join( |
||
| 422 | test_data_dir, 'data/dude/xiap/receptor_rdkit.pdb'))) |
||
| 423 | receptor.protein = True |
||
| 424 | receptor.addh(only_polar=True) |
||
| 425 | ref = SPLIF(mols[0], receptor) |
||
| 426 | splif_fps = [SPLIF(mol, receptor) for mol in mols] |
||
| 427 | outcome = [similarity_SPLIF(ref, fp) for fp in splif_fps] |
||
| 428 | target_outcome = np.array([1.000, 0.779, 0.660, 0.805, 0.630, |
||
| 429 | 0.802, 0.366, 0.817, 0.378, 0.553, |
||
| 430 | 0.732, 0.705, 0.856, 0.797, 0.502, |
||
| 431 | 0.418, 0.653, 0.436, 0.708, 0.688]) |
||
| 432 | |||
| 433 | assert_array_almost_equal(outcome, target_outcome, decimal=3) |
||
| 434 | |||
| 435 | # check if similarity is symmetric |
||
| 436 | for fp1, fp2 in combinations(splif_fps, 2): |
||
| 437 | assert similarity_SPLIF(fp1, fp2) == similarity_SPLIF(fp2, fp1) |
||
| 438 | |||
| 439 | |||
| 440 | def test_plec(): |
||
| 441 | """PLEC fingerprints""" |
||
| 442 | mols = list(oddt.toolkit.readfile('sdf', os.path.join( |
||
| 443 | test_data_dir, 'data/dude/xiap/actives_docked.sdf'))) |
||
| 444 | mols = list(filter(lambda x: x.title == '312335', mols)) |
||
| 445 | list(map(lambda x: x.removeh(), mols)) |
||
| 446 | receptor = next(oddt.toolkit.readfile('pdb', os.path.join( |
||
| 447 | test_data_dir, 'data/dude/xiap/receptor_rdkit.pdb'))) |
||
| 448 | receptor.protein = True |
||
| 449 | receptor.removeh() |
||
| 450 | plec = PLEC(mols[0], receptor) |
||
| 451 | reference = [80, 119, 120, 120, 120, 120, 137, 138, 155, 155, 155, 155, |
||
| 452 | 155, 155, 155, 161, 199, 214, 214, 214, 226, 226, 233, 266, |
||
| 453 | 282, 283, 283, 313, 313, 386, 386, 430, 431, 431, 432, 448, |
||
| 454 | 581, 581, 643, 662, 684, 690, 729, 737, 741, 778, 778, 795, |
||
| 455 | 799, 799, 812, 812, 876, 877, 894, 907, 924, 924, 925, 925, |
||
| 456 | 935, 935, 935, 935, 935, 964, 964, 964, 993, 993, 996, 996, |
||
| 457 | 1002, 1002, 1042, 1042, 1066, 1066, 1077, 1113, 1119, 1224, |
||
| 458 | 1266, 1266, 1290, 1322, 1322, 1334, 1334, 1403, 1411, 1411, |
||
| 459 | 1461, 1475, 1480, 1497, 1521, 1584, 1584, 1614, 1618, 1618, |
||
| 460 | 1618, 1618, 1691, 1694, 1694, 1755, 1755, 1755, 1755, 1786, |
||
| 461 | 1835, 1835, 1867, 1953, 1953, 1953, 1953, 1963, 1970, 1970, |
||
| 462 | 1990, 1992, 1992, 1992, 2024, 2024, 2060, 2252, 2373, 2383, |
||
| 463 | 2383, 2390, 2390, 2451, 2537, 2538, 2552, 2555, 2558, 2640, |
||
| 464 | 2720, 2752, 2791, 2821, 2821, 2931, 2950, 2957, 2957, 2959, |
||
| 465 | 2961, 2961, 2961, 2963, 2970, 2970, 2982, 3034, 3049, 3066, |
||
| 466 | 3084, 3084, 3084, 3104, 3126, 3227, 3248, 3293, 3293, 3293, |
||
| 467 | 3420, 3439, 3517, 3539, 3546, 3546, 3546, 3546, 3553, 3559, |
||
| 468 | 3596, 3630, 3643, 3643, 3674, 3707, 3708, 3716, 3738, 3742, |
||
| 469 | 3828, 3846, 3859, 3876, 3887, 3904, 3904, 3904, 3916, 3916, |
||
| 470 | 3939, 3941, 3981, 3981, 3991, 3993, 4010, 4097, 4127, 4127, |
||
| 471 | 4127, 4127, 4165, 4181, 4192, 4316, 4330, 4372, 4391, 4461, |
||
| 472 | 4462, 4463, 4542, 4542, 4542, 4549, 4549, 4549, 4549, 4614, |
||
| 473 | 4615, 4657, 4668, 4670, 4686, 4686, 4686, 4688, 4688, 4688, |
||
| 474 | 4688, 4695, 4729, 4740, 4741, 4744, 4744, 4744, 4744, 4756, |
||
| 475 | 4814, 4828, 4828, 4861, 4861, 4861, 4861, 4861, 4861, 4861, |
||
| 476 | 4861, 4861, 4861, 4861, 4861, 4861, 4861, 4861, 4861, 4916, |
||
| 477 | 4945, 4945, 5011, 5037, 5042, 5044, 5046, 5055, 5078, 5080, |
||
| 478 | 5101, 5101, 5126, 5139, 5146, 5189, 5193, 5232, 5271, 5314, |
||
| 479 | 5321, 5350, 5379, 5439, 5439, 5439, 5439, 5481, 5482, 5535, |
||
| 480 | 5563, 5565, 5565, 5585, 5601, 5601, 5626, 5626, 5631, 5631, |
||
| 481 | 5631, 5631, 5631, 5631, 5639, 5670, 5688, 5690, 5742, 5804, |
||
| 482 | 5804, 5864, 5871, 5885, 5983, 5992, 6010, 6010, 6010, 6059, |
||
| 483 | 6059, 6096, 6164, 6183, 6183, 6197, 6234, 6256, 6261, 6261, |
||
| 484 | 6277, 6277, 6277, 6277, 6299, 6333, 6333, 6388, 6388, 6404, |
||
| 485 | 6428, 6428, 6428, 6428, 6431, 6431, 6445, 6449, 6450, 6480, |
||
| 486 | 6496, 6519, 6519, 6540, 6582, 6642, 6654, 6654, 6671, 6717, |
||
| 487 | 6722, 6735, 6735, 6735, 6764, 6764, 6781, 6781, 6781, 6781, |
||
| 488 | 6788, 6788, 6803, 6808, 6833, 6838, 6838, 6950, 6979, 6979, |
||
| 489 | 6997, 7069, 7115, 7194, 7250, 7254, 7277, 7288, 7352, 7464, |
||
| 490 | 7493, 7506, 7506, 7520, 7530, 7530, 7530, 7542, 7546, 7561, |
||
| 491 | 7608, 7678, 7678, 7685, 7701, 7701, 7701, 7752, 7752, 7752, |
||
| 492 | 7790, 7847, 7957, 7957, 7957, 7959, 8003, 8003, 8003, 8010, |
||
| 493 | 8083, 8086, 8086, 8086, 8086, 8113, 8116, 8160, 8190, 8230, |
||
| 494 | 8230, 8262, 8262, 8282, 8284, 8284, 8292, 8297, 8327, 8327, |
||
| 495 | 8383, 8383, 8383, 8418, 8418, 8426, 8457, 8484, 8484, 8543, |
||
| 496 | 8543, 8580, 8629, 8651, 8655, 8697, 8726, 8781, 8784, 8796, |
||
| 497 | 8837, 8850, 8923, 9034, 9040, 9077, 9077, 9099, 9134, 9180, |
||
| 498 | 9206, 9257, 9281, 9304, 9304, 9333, 9341, 9358, 9393, 9394, |
||
| 499 | 9432, 9450, 9450, 9455, 9455, 9481, 9493, 9493, 9505, 9537, |
||
| 500 | 9547, 9572, 9585, 9610, 9610, 9661, 9689, 9690, 9690, 9700, |
||
| 501 | 9700, 9733, 9736, 9736, 9736, 9736, 9765, 9784, 9885, 9885, |
||
| 502 | 9885, 9934, 9938, 9968, 9968, 10037, 10080, 10080, 10103, |
||
| 503 | 10113, 10113, 10114, 10115, 10115, 10115, 10139, 10139, 10139, |
||
| 504 | 10139, 10139, 10181, 10181, 10181, 10181, 10185, 10286, 10295, |
||
| 505 | 10317, 10317, 10340, 10340, 10340, 10340, 10352, 10353, 10364, |
||
| 506 | 10364, 10385, 10490, 10490, 10504, 10535, 10539, 10539, 10589, |
||
| 507 | 10589, 10591, 10599, 10648, 10648, 10650, 10650, 10681, 10703, |
||
| 508 | 10714, 10714, 10714, 10739, 10739, 10793, 10806, 10806, 10806, |
||
| 509 | 10837, 10865, 10865, 10871, 10903, 10978, 10978, 11056, 11056, |
||
| 510 | 11141, 11159, 11207, 11213, 11257, 11272, 11360, 11362, 11377, |
||
| 511 | 11454, 11454, 11458, 11458, 11458, 11539, 11563, 11580, 11580, |
||
| 512 | 11580, 11605, 11605, 11610, 11610, 11613, 11624, 11664, 11664, |
||
| 513 | 11683, 11683, 11697, 11698, 11701, 11707, 11753, 11835, 11846, |
||
| 514 | 11852, 11858, 11876, 11879, 11890, 11957, 11957, 12009, 12115, |
||
| 515 | 12130, 12151, 12222, 12268, 12290, 12290, 12295, 12295, 12320, |
||
| 516 | 12431, 12448, 12475, 12475, 12475, 12481, 12485, 12487, 12587, |
||
| 517 | 12632, 12632, 12634, 12641, 12641, 12641, 12664, 12761, 12761, |
||
| 518 | 12778, 12832, 12878, 12878, 12884, 12958, 12982, 12982, 12982, |
||
| 519 | 12982, 12992, 13057, 13079, 13121, 13129, 13200, 13200, 13277, |
||
| 520 | 13277, 13317, 13317, 13320, 13320, 13336, 13388, 13434, 13443, |
||
| 521 | 13475, 13495, 13517, 13517, 13553, 13602, 13637, 13655, 13658, |
||
| 522 | 13658, 13688, 13688, 13774, 13774, 13784, 13784, 13784, 13786, |
||
| 523 | 13791, 13791, 13809, 13839, 13839, 13839, 13839, 13839, 13876, |
||
| 524 | 13905, 13906, 13906, 13906, 13906, 13920, 13920, 13920, 13920, |
||
| 525 | 13920, 13949, 13949, 14058, 14122, 14122, 14133, 14133, 14198, |
||
| 526 | 14259, 14259, 14317, 14332, 14368, 14386, 14423, 14423, 14423, |
||
| 527 | 14423, 14423, 14423, 14423, 14439, 14440, 14447, 14464, 14464, |
||
| 528 | 14469, 14505, 14510, 14510, 14513, 14516, 14516, 14529, 14529, |
||
| 529 | 14529, 14549, 14563, 14563, 14570, 14570, 14570, 14582, 14605, |
||
| 530 | 14605, 14611, 14748, 14748, 14750, 14757, 14772, 14798, 14802, |
||
| 531 | 14810, 14854, 14857, 14857, 14878, 14878, 14903, 14903, 14993, |
||
| 532 | 14993, 14996, 15008, 15012, 15018, 15044, 15044, 15074, 15092, |
||
| 533 | 15092, 15146, 15146, 15191, 15251, 15251, 15253, 15258, 15311, |
||
| 534 | 15311, 15317, 15429, 15429, 15441, 15444, 15498, 15518, 15520, |
||
| 535 | 15622, 15622, 15622, 15651, 15672, 15712, 15715, 15798, 15798, |
||
| 536 | 15811, 15950, 15982, 15982, 15987, 16023, 16023, 16042, 16049, |
||
| 537 | 16054, 16080, 16099, 16119, 16119, 16119, 16174, 16174, 16213, |
||
| 538 | 16225, 16229, 16234, 16234, 16234, 16252, 16252, 16252, 16252, |
||
| 539 | 16252, 16320, 16328, 16362, 16362] |
||
| 540 | |||
| 541 | assert_array_equal(reference, plec) |
||
| 542 | assert_array_equal(plec.shape, (860,)) |
||
| 543 | |||
| 544 | # Hydrogens should not impact the PLEC fingerprint |
||
| 545 | list(map(lambda x: x.addh(only_polar=True), mols)) |
||
| 546 | receptor.addh(only_polar=True) |
||
| 547 | plec = PLEC(mols[0], receptor) |
||
| 548 | assert_array_equal(reference, plec, "Polar Hs break PLEC") |
||
| 549 | |||
| 550 | list(map(lambda x: x.addh(), mols)) |
||
| 551 | receptor.addh() |
||
| 552 | plec = PLEC(mols[0], receptor) |
||
| 553 | assert_array_equal(reference, plec, "Non-polar Hs break PLEC") |
||
| 554 | |||
| 555 | |||
| 556 | def test_plec_binded_hoh(): |
||
| 557 | # if water coordinates metal in PDB and ligand is in contact with it, HOH |
||
| 558 | # will pop up in metals environment, thus we cannot ignore HOHs in repr_dict |
||
| 559 | |||
| 560 | if (oddt.toolkit.backend == 'ob' or |
||
| 561 | (oddt.toolkit.backend == 'rdk' and |
||
| 562 | oddt.toolkit.__version__ >= '2017.03')): |
||
| 563 | ligand = next(oddt.toolkit.readfile('sdf', os.path.join( |
||
| 564 | test_data_dir, 'data', 'pdb', '3kwa_ligand.sdf'))) |
||
| 565 | protein = next(oddt.toolkit.readfile('pdb', os.path.join( |
||
| 566 | test_data_dir, 'data', 'pdb', '3kwa_5Apocket.pdb'))) |
||
| 567 | protein.protein = True |
||
| 568 | |||
| 569 | assert len(PLEC(ligand, protein, ignore_hoh=True)) == 465 |
||
| 570 | assert len(PLEC(ligand, protein, ignore_hoh=False)) == 560 |
||
| 571 | |||
| 572 | |||
| 573 | def test_plec_similarity(): |
||
| 574 | """PLEC similarity""" |
||
| 575 | mols = list(oddt.toolkit.readfile('sdf', os.path.join( |
||
| 576 | test_data_dir, 'data/dude/xiap/actives_docked.sdf'))) |
||
| 577 | mols = list(filter(lambda x: x.title == '312335', mols)) |
||
| 578 | list(map(lambda x: x.addh(only_polar=True), mols)) |
||
| 579 | receptor = next(oddt.toolkit.readfile('pdb', os.path.join( |
||
| 580 | test_data_dir, 'data/dude/xiap/receptor_rdkit.pdb'))) |
||
| 581 | receptor.protein = True |
||
| 582 | receptor.addh(only_polar=True) |
||
| 583 | reference_sparse = PLEC(mols[0], receptor) |
||
| 584 | outcome_sparse = [dice(reference_sparse, PLEC(mol, receptor), |
||
| 585 | sparse=True) for mol in mols[1:]] |
||
| 586 | target_outcome = np.array([0.833, 0.729, 0.849, 0.785, 0.821, |
||
| 587 | 0.604, 0.868, 0.656, 0.712, 0.652, |
||
| 588 | 0.699, 0.785, 0.736, 0.745, 0.661, |
||
| 589 | 0.667, 0.555, 0.616, 0.714]) |
||
| 590 | reference_dense = PLEC(mols[0], receptor, sparse=False) |
||
| 591 | outcome_dense = [dice(reference_dense, PLEC(mol, receptor, sparse=False), |
||
| 592 | sparse=False) for mol in mols[1:]] |
||
| 593 | assert_array_almost_equal(outcome_sparse, target_outcome, decimal=2) |
||
| 594 | assert_array_almost_equal(outcome_dense, target_outcome, decimal=2) |
||
| 595 | |||
| 596 | |||
| 597 | def test_molecular_shingles(): |
||
| 598 | sildenafil = oddt.toolkit.readstring("smi", "CCCc1nn(C)c2c(=O)[nH]c(-c3cc(S(=O)(=O)N4CCN(C)CC4)ccc3OCC)nc12") |
||
| 599 | if oddt.toolkit.backend == 'ob': |
||
| 600 | target_shingles = [ |
||
| 601 | 'CCC', 'CCCc', 'CCCc(c)n', 'CCN(C)CC', 'CCN(CC)S(=O)(=O)c', 'CCO', 'CCOc', 'CCOc(c)c', 'CCc1nncc1n', 'CN(C)C', |
||
| 602 | 'CN(C)S(=O)(=O)c(c)c', 'CN(S)CCN', 'CN(S)CCN', 'COc(cc)c(c)c', 'Cc1ccn(n1)C', 'Cn(c)n', 'Cn1ncc(c1c(=O)[nH])n', |
||
| 603 | 'Cn1nccc1c', 'NCCN(C)C', 'NCCN(C)C', 'cS(=O)(=O)N', 'cS(=O)(=O)N', 'c[nH]c(=O)c(c)n', 'cc(=O)[nH]', |
||
| 604 | 'cc([nH])nc(c)c', 'cc(c)cc(S)c', 'cc(n)[nH]c(=O)c', 'ccc(c(O)c)c(n)[nH]', 'ccc(cc)S(=O)(=O)N', 'cccc(O)c', |
||
| 605 | 'cccc(S)c', 'cnc([nH]c)c(c)c', 'cnc1c(C)nnc1c'] |
||
| 606 | else: |
||
| 607 | |||
| 608 | target_shingles = [ |
||
| 609 | 'CCC', 'CCN(C)CC', 'CCO', 'CCc1nncc1n', 'CN(C)C', 'CN(C)CCN', 'CN(C)CCN', 'CN(S)CCN', 'CN(S)CCN', 'Cc1ccn(C)n1', |
||
| 610 | 'Cn1ncc(n)c1c([nH])=O', 'c-c([nH])nc(c)c', 'c-c(c)c(cc)OC', 'c-c(c)cc(c)S', 'c-c(n)[nH]c(c)=O', 'cCCC', 'cOCC', |
||
| 611 | 'cS(=O)(=O)N(CC)CC', 'cS(N)(=O)=O', 'cS(N)(=O)=O', 'c[nH]c(=O)c(c)n', 'cc([nH])=O', 'cc(c)OCC', |
||
| 612 | 'cc(c)S(=O)(=O)N(C)C', 'cc(n)CCC', 'cc1ccnn1C', 'ccc(-c(n)[nH])c(c)O', 'ccc(cc)S(N)(=O)=O', 'cccc(c)O', |
||
| 613 | 'cccc(c)S', 'cn(C)n', 'cnc([nH]c)-c(c)c', 'cnc1c(C)nnc1c'] |
||
| 614 | |||
| 615 | for n in range(10): |
||
| 616 | sildenafil = shuffle_mol(sildenafil) |
||
| 617 | shingles = sorted(get_molecular_shingles(sildenafil)) |
||
| 618 | assert_array_equal(shingles, target_shingles) |