dualmapref 0.2.8__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (186) hide show
  1. args_parse.py +593 -0
  2. candidate_corrector.py +161 -0
  3. candidate_scorer.py +359 -0
  4. conformend/__init__.py +36 -0
  5. conformend/refiner.py +25 -0
  6. dataset/__init__.py +1 -0
  7. dataset/drugdataset.py +644 -0
  8. dataset/manifold.py +237 -0
  9. dataset/sharded_drugdataset.py +124 -0
  10. dataset/smiles2graph.py +217 -0
  11. dualmapref/__init__.py +24 -0
  12. dualmapref/refiner.py +16 -0
  13. dualmapref-0.2.8.dist-info/LICENSE +21 -0
  14. dualmapref-0.2.8.dist-info/METADATA +167 -0
  15. dualmapref-0.2.8.dist-info/RECORD +186 -0
  16. dualmapref-0.2.8.dist-info/WHEEL +5 -0
  17. dualmapref-0.2.8.dist-info/entry_points.txt +10 -0
  18. dualmapref-0.2.8.dist-info/top_level.txt +29 -0
  19. exputils.py +289 -0
  20. infer.py +23 -0
  21. infer_base_conformers.py +5589 -0
  22. infer_mean_dispersion_torsion.py +1117 -0
  23. infer_torsion.py +752 -0
  24. infer_torsional_denoiser.py +1021 -0
  25. manimol/__init__.py +30 -0
  26. manimol/__main__.py +6 -0
  27. manimol/cli.py +36 -0
  28. manimol/full_cli.py +41 -0
  29. manimol/legacy_imports.py +43 -0
  30. manimol/manifest.py +56 -0
  31. manimol/postprocess.py +148 -0
  32. manimol/priors.py +60 -0
  33. manimol/protocols.py +119 -0
  34. manimol/refiner.py +645 -0
  35. manimol/runtime.py +194 -0
  36. manimol/selection.py +85 -0
  37. manimol/torsion.py +22 -0
  38. manimol/train_cli.py +14 -0
  39. mixture_flow/src/__init__.py +1 -0
  40. mixture_flow/src/_path.py +7 -0
  41. mixture_flow/src/infer28_mixture_torsion_flow.py +1093 -0
  42. mixture_flow/src/mixture_torsion_flow.py +291 -0
  43. mixture_flow/src/summarize_mixture_debug.py +80 -0
  44. mixture_flow/src/train28_mixture_torsion_flow.py +583 -0
  45. mixture_torsion_flow.py +7 -0
  46. models/ manifold_learning.py +86 -0
  47. models/__init__.py +8 -0
  48. models/dist.py +273 -0
  49. models/dist2coords.py +23 -0
  50. models/egnn.py +107 -0
  51. models/experimental_backbones.py +364 -0
  52. models/gnnconv.py +512 -0
  53. models/kernel_inversion.py +141 -0
  54. models/kernels.py +427 -0
  55. models/losses.py +154 -0
  56. models/mean_dispersion_bridge.py +119 -0
  57. models/mean_dispersion_torsion_context.py +155 -0
  58. models/model.py +73 -0
  59. models/model0.py +2375 -0
  60. models/vis.py +128 -0
  61. pgraph_controls.py +107 -0
  62. scripts/__init__.py +2 -0
  63. scripts/analyze_basin_alignment.py +63 -0
  64. scripts/analyze_hif2a_conformer_aggregation.py +267 -0
  65. scripts/analyze_hif2a_contact_pharmacophore.py +1111 -0
  66. scripts/analyze_hif2a_fixed_budget.py +202 -0
  67. scripts/analyze_hif2a_pharmacophore.py +405 -0
  68. scripts/analyze_hif2a_pharmacophore_match_metric.py +386 -0
  69. scripts/analyze_p_control_candidate_flow.py +154 -0
  70. scripts/analyze_scaffold_basin.py +83 -0
  71. scripts/audit_dispersion_proposals.py +208 -0
  72. scripts/audit_etflow_protocol.py +258 -0
  73. scripts/audit_external_overlap.py +150 -0
  74. scripts/audit_oldbest_fulltrainval_split.py +82 -0
  75. scripts/audit_pdbbind_contact_pharmacophores.py +146 -0
  76. scripts/audit_qm9_geomol_test_split.py +94 -0
  77. scripts/audit_stage1_stage2_cross.py +131 -0
  78. scripts/build_geom_drugs_lowref_diagnostic.py +84 -0
  79. scripts/build_qm9_backfill_manifest.py +99 -0
  80. scripts/check_etflow_runtime.py +56 -0
  81. scripts/compare_prior_sources.py +122 -0
  82. scripts/compose_binding_mode_figure.py +87 -0
  83. scripts/compose_hif2a_contact_pharmacophore_suppfig.py +255 -0
  84. scripts/compose_hif2a_functional_geometry_pipeline.py +266 -0
  85. scripts/compose_manimol_internal_architecture.py +291 -0
  86. scripts/diagnose_flow_basin_intervention.py +54 -0
  87. scripts/diagnose_hif2a_pharmacophore_budget.py +185 -0
  88. scripts/diagnose_route2_p_ranking.py +123 -0
  89. scripts/discover_binding_mode_inputs.py +30 -0
  90. scripts/evaluate_functional_prior_stage1.py +230 -0
  91. scripts/evaluate_geomanimol.py +74 -0
  92. scripts/evaluate_geomanimol_flow.py +23 -0
  93. scripts/evaluate_geomanimol_multiscaffold.py +46 -0
  94. scripts/evaluate_geomanimol_residual.py +45 -0
  95. scripts/evaluate_geomanimol_torsion.py +40 -0
  96. scripts/evaluate_hif2a_bioactive_enrichment.py +91 -0
  97. scripts/evaluate_hif2a_pms_suite.py +440 -0
  98. scripts/evaluate_pdbbind_contact_pms.py +155 -0
  99. scripts/evaluate_platinum_external.py +114 -0
  100. scripts/evaluate_platinum_pool.py +82 -0
  101. scripts/evaluate_route2_calibrated_p.py +104 -0
  102. scripts/evaluate_route2_library_components.py +596 -0
  103. scripts/evaluate_route2_p_basin_budget.py +288 -0
  104. scripts/evaluate_stage1_checkpoint_only.py +30 -0
  105. scripts/export_dispersion_bond_audit.py +136 -0
  106. scripts/export_top20_shards.py +207 -0
  107. scripts/external_validation_metrics.py +152 -0
  108. scripts/fit_topology_prior.py +117 -0
  109. scripts/frozen_dispersion_audit.py +281 -0
  110. scripts/geomanimol_debug.py +50 -0
  111. scripts/geomanimol_smoke.py +37 -0
  112. scripts/infer_etflow_matched.py +524 -0
  113. scripts/inspect_checkpoint.py +12 -0
  114. scripts/inspect_conformer_capacity.py +71 -0
  115. scripts/inspect_pool.py +12 -0
  116. scripts/make_figure3_selection_loss.py +474 -0
  117. scripts/make_figure3_selection_summary.py +275 -0
  118. scripts/make_geom_debug_subset.py +62 -0
  119. scripts/make_low_reference_test_subset.py +70 -0
  120. scripts/merge_stage1_into_stage2.py +82 -0
  121. scripts/place_hif2a_candidates_for_evaluation.py +66 -0
  122. scripts/plot_hif2a_low_budget_efficiency.py +100 -0
  123. scripts/plot_prior_validation.py +48 -0
  124. scripts/precompute_stage2_assignments.py +90 -0
  125. scripts/prepare_bace_activity.py +98 -0
  126. scripts/prepare_bace_etkdg_benchmark.py +90 -0
  127. scripts/prepare_figure5_4x4_cases.py +470 -0
  128. scripts/prepare_geom_drugs_geomol_top20.py +472 -0
  129. scripts/prepare_pdbbind_core_raw.py +90 -0
  130. scripts/prepare_platinum_raw.py +74 -0
  131. scripts/prepare_pubchem_etkdg.py +54 -0
  132. scripts/rebuild_hif2a_final_sdf_and_metrics.py +55 -0
  133. scripts/rebuild_hif2a_fixed_pool_sweep.py +175 -0
  134. scripts/rebuild_hif2a_strict.py +220 -0
  135. scripts/recompute_hif2a_bootstrap.py +63 -0
  136. scripts/reference_free_geometry.py +112 -0
  137. scripts/render_binding_modes.py +413 -0
  138. scripts/render_figure5_4x4.py +330 -0
  139. scripts/render_figure6_pharmacophore_pymol.py +162 -0
  140. scripts/render_hif2a_contact_pharmacophore_pymol.py +414 -0
  141. scripts/render_hif2a_figure11.py +397 -0
  142. scripts/run_bace_2d_baseline.py +73 -0
  143. scripts/run_drugs_validation_matrix.py +225 -0
  144. scripts/run_external_reference_free.py +53 -0
  145. scripts/run_manimol_finalk_sensitivity.py +106 -0
  146. scripts/run_manimol_oversampling_sensitivity.py +109 -0
  147. scripts/run_pdisp_matched_intervention.py +116 -0
  148. scripts/run_stage1_stage2_cross20.py +83 -0
  149. scripts/score_hif2a_candidates_with_pgraph.py +221 -0
  150. scripts/summarize_dispersion_intervention.py +88 -0
  151. scripts/test_mean_dispersion_bridge.py +50 -0
  152. scripts/train_dispersion_head_diagnostic.py +320 -0
  153. scripts/train_dispersion_head_streaming.py +519 -0
  154. scripts/train_geomanimol.py +100 -0
  155. scripts/train_geomanimol_flow.py +26 -0
  156. scripts/train_geomanimol_residual.py +70 -0
  157. scripts/train_geomanimol_torsion.py +50 -0
  158. scripts/train_quantile_representation_diagnostic.py +204 -0
  159. scripts/validate_mean_dispersion_prior.py +173 -0
  160. scripts/validate_packed_shard.py +41 -0
  161. scripts/validate_stage1_prior.py +221 -0
  162. scripts/validate_top20_shards.py +36 -0
  163. scripts/validation/__init__.py +1 -0
  164. scripts/validation/hif2a_downstream_baselines.py +105 -0
  165. scripts/validation/hif2a_pairwise_ranker.py +218 -0
  166. scripts/verify_binding_mode_figure.py +47 -0
  167. torsion_manifold.py +281 -0
  168. train.py +78 -0
  169. train_graph_encoder.py +206 -0
  170. train_local_torsion_corrector.py +511 -0
  171. train_mean_dispersion_torsion_prior.py +329 -0
  172. train_probability_basin.py +235 -0
  173. train_torsion_generator.py +1631 -0
  174. train_torsion_manifold_prior.py +258 -0
  175. train_torsional_denoiser.py +415 -0
  176. trainer.py +1038 -0
  177. utils/__init__.py +7 -0
  178. utils/checkpoint.py +40 -0
  179. utils/device.py +17 -0
  180. utils/helpers.py +98 -0
  181. utils/kabsch.py +29 -0
  182. utils/lookup_table.py +164 -0
  183. utils/metrics.py +50 -0
  184. utils/optuna.py +111 -0
  185. utils/save_mol.py +366 -0
  186. utils/util.py +36 -0
models/gnnconv.py ADDED
@@ -0,0 +1,512 @@
1
+ # models/gnnconv.py
2
+
3
+ import torch
4
+ from torch import nn
5
+ import torch.nn.functional as F
6
+ from torch_geometric.nn import MessagePassing, global_add_pool
7
+ from torch_geometric.utils import degree
8
+
9
+
10
+ # ============================================================
11
+ # basic mlp
12
+ # ============================================================
13
+
14
+ class MLP(nn.Module):
15
+ def __init__(
16
+ self,
17
+ num_layers,
18
+ input_dim,
19
+ hidden_dim,
20
+ output_dim,
21
+ ):
22
+ super().__init__()
23
+
24
+ self.num_layers = num_layers
25
+ self.linear_or_not = (num_layers == 1)
26
+
27
+ if num_layers < 1:
28
+ raise ValueError("num_layers must be >= 1")
29
+
30
+ if self.linear_or_not:
31
+ self.linear = nn.Linear(
32
+ input_dim,
33
+ output_dim,
34
+ )
35
+ else:
36
+ self.linears = nn.ModuleList()
37
+ self.batch_norms = nn.ModuleList()
38
+
39
+ self.linears.append(
40
+ nn.Linear(input_dim, hidden_dim)
41
+ )
42
+
43
+ for _ in range(num_layers - 2):
44
+ self.linears.append(
45
+ nn.Linear(hidden_dim, hidden_dim)
46
+ )
47
+
48
+ self.linears.append(
49
+ nn.Linear(hidden_dim, output_dim)
50
+ )
51
+
52
+ for _ in range(num_layers - 1):
53
+ self.batch_norms.append(
54
+ nn.BatchNorm1d(hidden_dim)
55
+ )
56
+
57
+ def forward(self, x):
58
+ if self.linear_or_not:
59
+ return self.linear(x)
60
+
61
+ h = x
62
+
63
+ for i in range(self.num_layers - 1):
64
+ h = self.linears[i](h)
65
+ h = self.batch_norms[i](h)
66
+ h = F.relu(h)
67
+
68
+ return self.linears[-1](h)
69
+
70
+
71
+ # ============================================================
72
+ # GIN conv
73
+ # ============================================================
74
+
75
+ class GINConv(MessagePassing):
76
+ def __init__(
77
+ self,
78
+ emb_dim,
79
+ edge_dim,
80
+ ):
81
+ super().__init__(aggr="add")
82
+
83
+ self.mlp = nn.Sequential(
84
+ nn.Linear(emb_dim, 2 * emb_dim),
85
+ nn.BatchNorm1d(2 * emb_dim),
86
+ nn.ReLU(),
87
+ nn.Linear(2 * emb_dim, emb_dim),
88
+ )
89
+
90
+ self.eps = nn.Parameter(
91
+ torch.zeros(1)
92
+ )
93
+
94
+ self.bond_encoder = MLP(
95
+ num_layers=1,
96
+ input_dim=edge_dim,
97
+ hidden_dim=emb_dim,
98
+ output_dim=emb_dim,
99
+ )
100
+
101
+ def forward(
102
+ self,
103
+ x,
104
+ edge_index,
105
+ edge_attr,
106
+ ):
107
+ edge_embedding = self.bond_encoder(
108
+ edge_attr.float()
109
+ )
110
+
111
+ out = self.propagate(
112
+ edge_index=edge_index,
113
+ x=x,
114
+ edge_attr=edge_embedding,
115
+ )
116
+
117
+ out = (1 + self.eps) * x + out
118
+ out = self.mlp(out)
119
+
120
+ return out
121
+
122
+ def message(
123
+ self,
124
+ x_j,
125
+ edge_attr,
126
+ ):
127
+ return F.relu(x_j + edge_attr)
128
+
129
+ def update(
130
+ self,
131
+ aggr_out,
132
+ ):
133
+ return aggr_out
134
+
135
+
136
+ # ============================================================
137
+ # GCN conv
138
+ # ============================================================
139
+
140
+ class GCNConv(MessagePassing):
141
+ def __init__(
142
+ self,
143
+ emb_dim,
144
+ edge_dim,
145
+ ):
146
+ super().__init__(aggr="add")
147
+
148
+ self.linear = nn.Linear(
149
+ emb_dim,
150
+ emb_dim,
151
+ )
152
+
153
+ self.root_emb = nn.Embedding(
154
+ 1,
155
+ emb_dim,
156
+ )
157
+
158
+ self.bond_encoder = MLP(
159
+ num_layers=1,
160
+ input_dim=edge_dim,
161
+ hidden_dim=emb_dim,
162
+ output_dim=emb_dim,
163
+ )
164
+
165
+ def forward(
166
+ self,
167
+ x,
168
+ edge_index,
169
+ edge_attr,
170
+ ):
171
+ x = self.linear(x)
172
+
173
+ edge_embedding = self.bond_encoder(
174
+ edge_attr.float()
175
+ )
176
+
177
+ row, col = edge_index
178
+
179
+ deg = degree(
180
+ row,
181
+ x.size(0),
182
+ dtype=x.dtype,
183
+ ) + 1.0
184
+
185
+ deg_inv_sqrt = deg.pow(-0.5)
186
+ deg_inv_sqrt[
187
+ deg_inv_sqrt == float("inf")
188
+ ] = 0
189
+
190
+ norm = deg_inv_sqrt[row] * deg_inv_sqrt[col]
191
+
192
+ out = self.propagate(
193
+ edge_index=edge_index,
194
+ x=x,
195
+ edge_attr=edge_embedding,
196
+ norm=norm,
197
+ )
198
+
199
+ root = self.root_emb.weight[0]
200
+
201
+ return out + F.relu(
202
+ x + root
203
+ ) / deg.view(-1, 1)
204
+
205
+ def message(
206
+ self,
207
+ x_j,
208
+ edge_attr,
209
+ norm,
210
+ ):
211
+ return norm.view(-1, 1) * F.relu(
212
+ x_j + edge_attr
213
+ )
214
+
215
+ def update(
216
+ self,
217
+ aggr_out,
218
+ ):
219
+ return aggr_out
220
+
221
+
222
+ # ============================================================
223
+ # node gnn
224
+ # ============================================================
225
+
226
+ class GNN_node(nn.Module):
227
+ def __init__(
228
+ self,
229
+ num_layer,
230
+ emb_dim,
231
+ edge_dim,
232
+ node_dim=39,
233
+ drop_ratio=0.5,
234
+ JK="last",
235
+ residual=False,
236
+ gnn_type="gin",
237
+ ):
238
+ super().__init__()
239
+
240
+ self.num_layer = num_layer
241
+ self.drop_ratio = drop_ratio
242
+ self.JK = JK
243
+ self.residual = residual
244
+
245
+ self.atom_encoder = MLP(
246
+ num_layers=2,
247
+ input_dim=node_dim,
248
+ hidden_dim=emb_dim,
249
+ output_dim=emb_dim,
250
+ )
251
+
252
+ self.convs = nn.ModuleList()
253
+ self.batch_norms = nn.ModuleList()
254
+
255
+ for _ in range(num_layer):
256
+ if gnn_type == "gin":
257
+ conv = GINConv(
258
+ emb_dim=emb_dim,
259
+ edge_dim=edge_dim,
260
+ )
261
+ elif gnn_type == "gcn":
262
+ conv = GCNConv(
263
+ emb_dim=emb_dim,
264
+ edge_dim=edge_dim,
265
+ )
266
+ else:
267
+ raise ValueError(
268
+ f"Unknown gnn_type={gnn_type}"
269
+ )
270
+
271
+ self.convs.append(conv)
272
+
273
+ self.batch_norms.append(
274
+ nn.BatchNorm1d(emb_dim)
275
+ )
276
+
277
+ def forward(self, *argv):
278
+ if len(argv) == 1:
279
+ batch = argv[0]
280
+
281
+ x = batch.x
282
+ edge_index = batch.edge_index
283
+ edge_attr = batch.edge_attr
284
+
285
+ elif len(argv) == 3:
286
+ x, edge_index, edge_attr = argv
287
+
288
+ else:
289
+ raise ValueError(
290
+ "GNN_node forward args mismatch"
291
+ )
292
+
293
+ h = self.atom_encoder(
294
+ x.float()
295
+ )
296
+
297
+ h_list = [h]
298
+
299
+ for layer in range(self.num_layer):
300
+ h_new = self.convs[layer](
301
+ h_list[layer],
302
+ edge_index,
303
+ edge_attr,
304
+ )
305
+
306
+ h_new = self.batch_norms[layer](
307
+ h_new
308
+ )
309
+
310
+ if layer == self.num_layer - 1:
311
+ h_new = F.dropout(
312
+ h_new,
313
+ p=self.drop_ratio,
314
+ training=self.training,
315
+ )
316
+ else:
317
+ h_new = F.dropout(
318
+ F.relu(h_new),
319
+ p=self.drop_ratio,
320
+ training=self.training,
321
+ )
322
+
323
+ if self.residual:
324
+ h_new = h_new + h_list[layer]
325
+
326
+ h_list.append(h_new)
327
+
328
+ if self.JK == "last":
329
+ return h_list[-1]
330
+
331
+ elif self.JK == "sum":
332
+ out = 0
333
+ for h in h_list:
334
+ out = out + h
335
+ return out
336
+
337
+ else:
338
+ raise ValueError(
339
+ f"Unknown JK={self.JK}"
340
+ )
341
+
342
+
343
+ # ============================================================
344
+ # virtual node gnn
345
+ # ============================================================
346
+
347
+ class GNN_node_Virtualnode(nn.Module):
348
+ def __init__(
349
+ self,
350
+ num_layer,
351
+ emb_dim,
352
+ edge_dim,
353
+ node_dim=39,
354
+ drop_ratio=0.5,
355
+ JK="last",
356
+ residual=False,
357
+ gnn_type="gin",
358
+ ):
359
+ super().__init__()
360
+
361
+ if num_layer < 2:
362
+ raise ValueError(
363
+ "num_layer must be >= 2"
364
+ )
365
+
366
+ self.num_layer = num_layer
367
+ self.drop_ratio = drop_ratio
368
+ self.JK = JK
369
+ self.residual = residual
370
+
371
+ self.atom_encoder = MLP(
372
+ num_layers=2,
373
+ input_dim=node_dim,
374
+ hidden_dim=emb_dim,
375
+ output_dim=emb_dim,
376
+ )
377
+
378
+ self.virtualnode_embedding = nn.Embedding(
379
+ 1,
380
+ emb_dim,
381
+ )
382
+
383
+ nn.init.constant_(
384
+ self.virtualnode_embedding.weight,
385
+ 0,
386
+ )
387
+
388
+ self.convs = nn.ModuleList()
389
+ self.batch_norms = nn.ModuleList()
390
+ self.virtual_mlps = nn.ModuleList()
391
+
392
+ for _ in range(num_layer):
393
+ if gnn_type == "gin":
394
+ conv = GINConv(
395
+ emb_dim=emb_dim,
396
+ edge_dim=edge_dim,
397
+ )
398
+ else:
399
+ conv = GCNConv(
400
+ emb_dim=emb_dim,
401
+ edge_dim=edge_dim,
402
+ )
403
+
404
+ self.convs.append(conv)
405
+
406
+ self.batch_norms.append(
407
+ nn.BatchNorm1d(emb_dim)
408
+ )
409
+
410
+ for _ in range(num_layer - 1):
411
+ self.virtual_mlps.append(
412
+ nn.Sequential(
413
+ nn.Linear(
414
+ emb_dim,
415
+ 2 * emb_dim,
416
+ ),
417
+ nn.BatchNorm1d(
418
+ 2 * emb_dim
419
+ ),
420
+ nn.ReLU(),
421
+ nn.Linear(
422
+ 2 * emb_dim,
423
+ emb_dim,
424
+ ),
425
+ )
426
+ )
427
+
428
+ def forward(self, batch):
429
+ x = batch.x
430
+ edge_index = batch.edge_index
431
+ edge_attr = batch.edge_attr
432
+ batch_idx = batch.batch
433
+
434
+ h = self.atom_encoder(
435
+ x.float()
436
+ )
437
+
438
+ h_list = [h]
439
+
440
+ virtualnode_embedding = self.virtualnode_embedding(
441
+ torch.zeros(
442
+ batch_idx[-1].item() + 1,
443
+ dtype=torch.long,
444
+ device=batch_idx.device,
445
+ )
446
+ )
447
+
448
+ for layer in range(self.num_layer):
449
+ h_list[layer] = (
450
+ h_list[layer]
451
+ + virtualnode_embedding[batch_idx]
452
+ )
453
+
454
+ h_new = self.convs[layer](
455
+ h_list[layer],
456
+ edge_index,
457
+ edge_attr,
458
+ )
459
+
460
+ h_new = self.batch_norms[layer](
461
+ h_new
462
+ )
463
+
464
+ if layer == self.num_layer - 1:
465
+ h_new = F.dropout(
466
+ h_new,
467
+ p=self.drop_ratio,
468
+ training=self.training,
469
+ )
470
+ else:
471
+ h_new = F.dropout(
472
+ F.relu(h_new),
473
+ p=self.drop_ratio,
474
+ training=self.training,
475
+ )
476
+
477
+ if self.residual:
478
+ h_new = h_new + h_list[layer]
479
+
480
+ h_list.append(h_new)
481
+
482
+ if layer < self.num_layer - 1:
483
+ pooled = global_add_pool(
484
+ h_new,
485
+ batch_idx,
486
+ )
487
+
488
+ update = self.virtual_mlps[layer](
489
+ pooled
490
+ )
491
+
492
+ if self.residual:
493
+ virtualnode_embedding = (
494
+ virtualnode_embedding
495
+ + update
496
+ )
497
+ else:
498
+ virtualnode_embedding = update
499
+
500
+ if self.JK == "last":
501
+ return h_list[-1]
502
+
503
+ elif self.JK == "sum":
504
+ out = 0
505
+ for h in h_list:
506
+ out = out + h
507
+ return out
508
+
509
+ else:
510
+ raise ValueError(
511
+ f"Unknown JK={self.JK}"
512
+ )
@@ -0,0 +1,141 @@
1
+ import torch
2
+ import torch.nn.functional as F
3
+ from typing import List, Optional, Union
4
+
5
+ def prob_low_dim(Y, a, b, eps=1e-12):
6
+ """
7
+ 可微的低维概率矩阵计算。
8
+ Y: torch.Tensor (N, 3)
9
+ a, b: float or torch.Tensor (标量)
10
+ 返回 Q: (N, N)
11
+ """
12
+ a = torch.as_tensor(a, dtype=Y.dtype, device=Y.device)
13
+ b = torch.as_tensor(b, dtype=Y.dtype, device=Y.device)
14
+ D = torch.cdist(Y, Y, p=2) # 欧氏距离
15
+ s = D.pow(2) + eps # d_ij^2
16
+ Q = 1.0 / (1.0 + a * torch.pow(s, b))
17
+ Q.fill_diagonal_(0.0) # 对角线置0
18
+ return Q
19
+
20
+ def cross_entropy_loss(P, Q, eps=1e-12):
21
+ """
22
+ 交叉熵损失,P, Q 均为 (N,N) 张量。
23
+ 返回标量损失,除以非对角线元素数量,使损失与原子数无关。
24
+ """
25
+ Q = torch.clamp(Q, min=eps, max=1-eps)
26
+ P = torch.clamp(P, min=eps, max=1-eps)
27
+ loss = - (P * torch.log(Q) + (1 - P) * torch.log(1 - Q))
28
+ n = P.shape[0]
29
+ loss = loss.sum() / (n * (n-1))
30
+ return loss
31
+
32
+ def kernel_inversion(P_target: Union[torch.Tensor, List[torch.Tensor]],
33
+ Y_init: torch.Tensor,
34
+ a: float,
35
+ b: float,
36
+ steps: int = 200,
37
+ lr: float = 0.1,
38
+ verbose: bool = False,
39
+ device: Optional[torch.device] = None) -> torch.Tensor:
40
+ """
41
+ 核反转函数:给定目标概率图 P_target,从初始坐标 Y_init 开始优化,
42
+ 最小化交叉熵损失 CE(P_target, Q(Y)),得到最终坐标 Y_opt。
43
+
44
+ Args:
45
+ P_target: 目标概率图,形状 (N, N),或批次列表长度 B,每个形状 (N_i, N_i)
46
+ Y_init: 初始坐标,形状 (N, 3) 或 (B, N_i, 3) 与 P_target 对应
47
+ a, b: 低维核参数(标量)
48
+ steps: 优化步数
49
+ lr: 学习率
50
+ verbose: 是否打印损失变化
51
+ device: 计算设备
52
+
53
+ Returns:
54
+ 优化后的坐标,形状与 Y_init 相同
55
+ """
56
+ # 统一处理批量输入
57
+ if isinstance(P_target, list) and len(P_target) > 1:
58
+ if not isinstance(Y_init, list):
59
+ raise ValueError("当 P_target 为列表时,Y_init 也应为列表,每个元素对应一个分子")
60
+ results = []
61
+ for p, y in zip(P_target, Y_init):
62
+ res = kernel_inversion(p, y, a, b, steps, lr, verbose, device)
63
+ results.append(res)
64
+ return results
65
+
66
+ # 单分子情况:若 P_target 是单元素列表,取出第一个元素
67
+ if isinstance(P_target, list) and len(P_target) == 1:
68
+ P_target = P_target[0]
69
+
70
+ if device is not None:
71
+ P_target = P_target.to(device)
72
+ Y_init = Y_init.to(device)
73
+ else:
74
+ P_target = P_target.cpu()
75
+ Y_init = Y_init.cpu()
76
+
77
+ Y = Y_init.clone().detach().requires_grad_(True)
78
+ optimizer = torch.optim.Adam([Y], lr=lr)
79
+
80
+ for step in range(steps):
81
+ optimizer.zero_grad()
82
+ Q = prob_low_dim(Y, a, b)
83
+ loss = cross_entropy_loss(P_target, Q)
84
+ loss.backward()
85
+ optimizer.step()
86
+ # 保持坐标中心为原点(刚性平移不变)
87
+ with torch.no_grad():
88
+ Y -= Y.mean(dim=0, keepdim=True)
89
+ if verbose and (step % 50 == 0 or step == steps-1):
90
+ print(f"Step {step:4d}, loss = {loss.item():.6f}")
91
+
92
+ return Y.detach()
93
+
94
+ def generate_conformer_ensemble(P_target: Union[torch.Tensor, List[torch.Tensor]],
95
+ a: float,
96
+ b: float,
97
+ n_confs: int = 10,
98
+ steps: int = 200,
99
+ lr: float = 0.1,
100
+ noise_scale: float = 0.1,
101
+ device: Optional[torch.device] = None) -> List[torch.Tensor]:
102
+ """
103
+ 从同一个概率图 P_target 生成多个构象(多初始化)。
104
+
105
+ Args:
106
+ P_target: 目标概率图,形状 (N, N)
107
+ a, b: 核参数
108
+ n_confs: 生成的构象数量
109
+ steps: 每个构象的优化步数
110
+ lr: 学习率
111
+ noise_scale: 初始坐标的随机噪声标准差(以平均键长 ~1.5 Å 为参考)
112
+ device: 计算设备
113
+
114
+ Returns:
115
+ 列表,每个元素为优化后的坐标张量 (N, 3)
116
+ """
117
+ if isinstance(P_target, list):
118
+ if len(P_target) == 0:
119
+ raise ValueError("P_target 列表为空")
120
+ # 若列表长度大于1,认为每个元素对应一个分子,递归调用本函数处理每个分子
121
+ if len(P_target) > 1:
122
+ results = []
123
+ for p in P_target:
124
+ res = generate_conformer_ensemble(p, a, b, n_confs, steps, lr, noise_scale, device)
125
+ results.extend(res) # 注意:展平
126
+ return results
127
+ # 长度为1,取出单独处理
128
+ P_target = P_target[0]
129
+
130
+ if device is not None:
131
+ P_target = P_target.to(device)
132
+ else:
133
+ P_target = P_target.cpu()
134
+
135
+ N = P_target.shape[0]
136
+ ensemble = []
137
+ for i in range(n_confs):
138
+ Y0 = torch.randn(N, 3, device=P_target.device) * noise_scale
139
+ Y_opt = kernel_inversion(P_target, Y0, a, b, steps, lr, verbose=False, device=device)
140
+ ensemble.append(Y_opt.cpu())
141
+ return ensemble