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
@@ -0,0 +1,185 @@
1
+ #!/usr/bin/env python3
2
+ """Audit PMS ensemble ordering versus candidate-pool coverage.
3
+
4
+ This is a read-only diagnostic over candidate_pharmacophore_match_scores.csv.
5
+ It does not change the PMS definition or regenerate conformers.
6
+ """
7
+
8
+ from __future__ import annotations
9
+
10
+ import argparse
11
+ import json
12
+ from pathlib import Path
13
+
14
+ import numpy as np
15
+ import pandas as pd
16
+
17
+
18
+ def parse_map(value: str) -> dict[str, float]:
19
+ try:
20
+ result = json.loads(value)
21
+ except (TypeError, json.JSONDecodeError):
22
+ return {}
23
+ return {str(key): float(val) for key, val in result.items()}
24
+
25
+
26
+ def score(rows: list[dict], selected: list[int]) -> tuple[float, float, float]:
27
+ feature_keys = sorted({key for row in rows for key in row["features"]})
28
+ pair_keys = sorted({key for row in rows for key in row["pairs"]})
29
+ feature = [max((rows[i]["features"].get(key, 0.0) for i in selected), default=0.0) for key in feature_keys]
30
+ pairs = [max((rows[i]["pairs"].get(key, 0.0) for i in selected), default=0.0) for key in pair_keys]
31
+ region = float(np.mean(feature)) if feature else np.nan
32
+ topology = float(np.mean(pairs)) if pairs else np.nan
33
+ return region, topology, float(0.5 * region + 0.5 * topology)
34
+
35
+
36
+ def greedy_oracle(rows: list[dict], k: int) -> list[int]:
37
+ selected: list[int] = []
38
+ remaining = set(range(len(rows)))
39
+ for _ in range(min(k, len(rows))):
40
+ best_idx = max(
41
+ remaining,
42
+ key=lambda idx: score(rows, selected + [idx])[2],
43
+ )
44
+ selected.append(best_idx)
45
+ remaining.remove(best_idx)
46
+ return selected
47
+
48
+
49
+ def hybrid_select(rows: list[dict], k: int, quality_weight: float) -> list[int]:
50
+ """Select candidates by quality plus normalized marginal coverage gain."""
51
+ selected: list[int] = []
52
+ remaining = set(range(len(rows)))
53
+ for _ in range(min(k, len(rows))):
54
+ current = score(rows, selected)[2] if selected else 0.0
55
+ gains = {idx: score(rows, selected + [idx])[2] - current for idx in remaining}
56
+ max_gain = max(gains.values(), default=1.0)
57
+ max_gain = max(max_gain, 1e-8)
58
+ best_idx = max(
59
+ remaining,
60
+ key=lambda idx: quality_weight * score(rows, [idx])[2]
61
+ + (1.0 - quality_weight) * gains[idx] / max_gain,
62
+ )
63
+ selected.append(best_idx)
64
+ remaining.remove(best_idx)
65
+ return selected
66
+
67
+
68
+ def main() -> None:
69
+ parser = argparse.ArgumentParser()
70
+ parser.add_argument("--input", default="outputs/docking/hif2a_pharmacophore_match_metric/candidate_pharmacophore_match_scores.csv")
71
+ parser.add_argument("--output_dir", default="outputs/docking/hif2a_pharmacophore_budget_diagnostic")
72
+ parser.add_argument("--budgets", default="1,5,10,20")
73
+ parser.add_argument("--random_repeats", type=int, default=100)
74
+ parser.add_argument("--seed", type=int, default=20260822)
75
+ parser.add_argument("--hybrid_lambdas", default="0.25,0.5,0.75")
76
+ args = parser.parse_args()
77
+
78
+ data = pd.read_csv(args.input)
79
+ budgets = [int(value) for value in args.budgets.split(",") if value.strip()]
80
+ hybrid_lambdas = [float(value) for value in args.hybrid_lambdas.split(",") if value.strip()]
81
+ output_dir = Path(args.output_dir)
82
+ output_dir.mkdir(parents=True, exist_ok=True)
83
+ rng = np.random.default_rng(args.seed)
84
+ summary_rows = []
85
+ detail_rows = []
86
+ selected_rows = []
87
+ rmsd_rows = []
88
+
89
+ for (method, ligand_id), group in data.groupby(["method", "ligand_id"], sort=True):
90
+ group = group.sort_values("candidate_index").reset_index(drop=True)
91
+ rows = [
92
+ {"features": parse_map(value), "pairs": parse_map(pair)}
93
+ for value, pair in zip(group["feature_scores_json"], group["pair_scores_json"])
94
+ ]
95
+ for k in budgets:
96
+ original = score(rows, list(range(min(k, len(rows)))))
97
+ oracle_indices = greedy_oracle(rows, k)
98
+ oracle = score(rows, oracle_indices)
99
+ individual_indices = sorted(
100
+ range(len(rows)),
101
+ key=lambda idx: 0.5 * np.mean(list(rows[idx]["features"].values()))
102
+ + 0.5 * np.mean(list(rows[idx]["pairs"].values())),
103
+ reverse=True,
104
+ )[: min(k, len(rows))]
105
+ individual = score(rows, individual_indices)
106
+ random_scores = [score(rows, rng.permutation(len(rows))[: min(k, len(rows))].tolist()) for _ in range(args.random_repeats)]
107
+ random_arr = np.asarray(random_scores, dtype=float)
108
+ values = {
109
+ "original": original[2],
110
+ "individual_pms_topk": individual[2],
111
+ "random_mean": float(random_arr[:, 2].mean()),
112
+ "random_std": float(random_arr[:, 2].std(ddof=1)),
113
+ "oracle": oracle[2],
114
+ }
115
+ for label, value in values.items():
116
+ summary_rows.append({"method": method, "K": k, "metric": label, "value": value})
117
+ selections = {
118
+ "original_order": list(range(min(k, len(rows)))),
119
+ "pms_topk": individual_indices,
120
+ "coverage_greedy": oracle_indices,
121
+ }
122
+ for quality_weight in hybrid_lambdas:
123
+ selections[f"hybrid_lambda_{quality_weight:g}"] = hybrid_select(rows, k, quality_weight)
124
+ for selector_name, indices in selections.items():
125
+ region, topology, pms = score(rows, indices)
126
+ summary_rows.extend([
127
+ {"method": method, "K": k, "metric": f"{selector_name}_region", "value": region},
128
+ {"method": method, "K": k, "metric": f"{selector_name}_topology", "value": topology},
129
+ {"method": method, "K": k, "metric": f"{selector_name}_pms", "value": pms},
130
+ ])
131
+ for rank, idx in enumerate(indices):
132
+ selected_rows.append({
133
+ "method": method,
134
+ "ligand_id": ligand_id,
135
+ "K": k,
136
+ "selector": selector_name,
137
+ "rank": rank,
138
+ "candidate_index": int(group.iloc[idx]["candidate_index"]),
139
+ "candidate_file": group.iloc[idx]["candidate_file"],
140
+ })
141
+ rmsds = group.iloc[indices]["atom_rmsd"].astype(float).to_numpy()
142
+ hits = rmsds <= 0.75
143
+ rmsd_rows.append({
144
+ "method": method,
145
+ "ligand_id": ligand_id,
146
+ "K": k,
147
+ "selector": selector_name,
148
+ "cov_r": float(np.any(hits)),
149
+ "cov_p": float(np.mean(hits)),
150
+ "amr_r": float(np.min(rmsds)),
151
+ "amr_p": float(np.mean(rmsds)),
152
+ })
153
+ detail_rows.append({
154
+ "method": method,
155
+ "ligand_id": ligand_id,
156
+ "K": k,
157
+ "original_pms": original[2],
158
+ "original_region": original[0],
159
+ "original_topology": original[1],
160
+ "individual_pms_topk": individual[2],
161
+ "random_pms_mean": values["random_mean"],
162
+ "random_pms_std": values["random_std"],
163
+ "oracle_pms": oracle[2],
164
+ "oracle_indices": ";".join(map(str, oracle_indices)),
165
+ })
166
+
167
+ summary = pd.DataFrame(summary_rows)
168
+ detail = pd.DataFrame(detail_rows)
169
+ selected = pd.DataFrame(selected_rows)
170
+ rmsd = pd.DataFrame(rmsd_rows)
171
+ summary.to_csv(output_dir / "pharmacophore_budget_order_summary.csv", index=False)
172
+ detail.to_csv(output_dir / "pharmacophore_budget_order_per_ligand.csv", index=False)
173
+ selected.to_csv(output_dir / "pharmacophore_budget_selected_candidates.csv", index=False)
174
+ rmsd.to_csv(output_dir / "pharmacophore_budget_rmsd_per_ligand.csv", index=False)
175
+ rmsd_summary = rmsd.groupby(["method", "K", "selector"], as_index=False)[["cov_r", "cov_p", "amr_r", "amr_p"]].mean()
176
+ rmsd_summary.to_csv(output_dir / "pharmacophore_budget_rmsd_summary.csv", index=False)
177
+ config = vars(args)
178
+ (output_dir / "diagnostic_config.json").write_text(json.dumps(config, indent=2) + "\n", encoding="utf-8")
179
+ print(summary.pivot_table(index=["method", "K"], columns="metric", values="value").reset_index().to_string(index=False))
180
+ print(rmsd_summary.to_string(index=False))
181
+ print(f"Saved outputs under {output_dir}")
182
+
183
+
184
+ if __name__ == "__main__":
185
+ main()
@@ -0,0 +1,123 @@
1
+ #!/usr/bin/env python3
2
+ """Diagnose whether probability controls produce distinct candidate rankings."""
3
+
4
+ from __future__ import annotations
5
+
6
+ import argparse
7
+ import json
8
+ import sys
9
+ from argparse import Namespace
10
+ from pathlib import Path
11
+
12
+ import numpy as np
13
+ import torch
14
+ from tqdm import tqdm
15
+
16
+ sys.path.insert(0, str(Path(__file__).resolve().parents[1]))
17
+
18
+ import infer_base_conformers
19
+ from pgraph_controls import controlled_pglobal
20
+ from evaluate_route2_p_basin_budget import candidate_p_bce, farthest_point_basins
21
+
22
+
23
+ def rank(values: torch.Tensor) -> torch.Tensor:
24
+ order = torch.argsort(values)
25
+ ranks = torch.empty_like(order, dtype=torch.float32)
26
+ ranks[order] = torch.arange(order.numel(), dtype=torch.float32)
27
+ return ranks
28
+
29
+
30
+ def corr(a: torch.Tensor, b: torch.Tensor) -> float:
31
+ a = rank(a).double()
32
+ b = rank(b).double()
33
+ a = a - a.mean()
34
+ b = b - b.mean()
35
+ denom = torch.sqrt((a * a).sum() * (b * b).sum()).clamp_min(1e-12)
36
+ return float(((a * b).sum() / denom).item())
37
+
38
+
39
+ def density_quality(pool, mol, heavy_mask, density_k):
40
+ dist = infer_base_conformers._pairwise_torsion_signature_distance(
41
+ pool, mol, fallback_metric="kabsch", heavy_mask=heavy_mask
42
+ )
43
+ n = int(dist.size(0))
44
+ eye = torch.eye(n, dtype=dist.dtype)
45
+ k = max(1, min(int(density_k), max(1, n - 1)))
46
+ sorted_dist = torch.sort(dist + eye * 1e6, dim=1).values
47
+ local_radius = sorted_dist[:, :k].mean(dim=1)
48
+ centrality = dist.mean(dim=1)
49
+ return infer_base_conformers._normalize_01(local_radius) + 0.45 * infer_base_conformers._normalize_01(centrality), dist
50
+
51
+
52
+ def main():
53
+ parser = argparse.ArgumentParser()
54
+ parser.add_argument("--pool_pt", required=True)
55
+ parser.add_argument("--max_molecules", type=int, default=0)
56
+ parser.add_argument("--modes", type=int, default=3)
57
+ parser.add_argument("--budget_multiplier", type=float, default=2.0)
58
+ parser.add_argument("--controls", default="normal,shuffle,random")
59
+ parser.add_argument("--seed", type=int, default=20260825)
60
+ parser.add_argument("--density_k", type=int, default=20)
61
+ parser.add_argument("--output_prefix", required=True)
62
+ args = parser.parse_args()
63
+
64
+ payload = torch.load(args.pool_pt, map_location="cpu", weights_only=False)
65
+ records = list(payload["records"])
66
+ if args.max_molecules > 0:
67
+ records = records[: args.max_molecules]
68
+ controls = [x.strip() for x in args.controls.split(",") if x.strip()]
69
+ rows = []
70
+ for record in tqdm(records, desc="P ranking diagnostics", unit="molecule"):
71
+ pool = record["raw_pool"].float()
72
+ budget = min(int(pool.size(0)), max(1, int(round(
73
+ args.budget_multiplier * record["ref_confs"].size(0)
74
+ ))))
75
+ density, distance = density_quality(
76
+ pool, record.get("mol"), record.get("heavy_mask"), args.density_k
77
+ )
78
+ assignment = farthest_point_basins(distance, args.modes)
79
+ learned = record.get("pglobal")
80
+ kernel = record.get("pgraph_kernel")
81
+ if learned is None or kernel is None:
82
+ continue
83
+ scores = {}
84
+ for control in controls:
85
+ control_args = Namespace(
86
+ pglobal_control=control, pglobal_seed=args.seed,
87
+ disable_stage1_pglobal=False,
88
+ )
89
+ target = controlled_pglobal(learned.float(), control_args, mol=record.get("mol"))
90
+ scores[control] = candidate_p_bce(pool, target, kernel, record.get("mol"))
91
+ row = {"mol_id": record["mol_id"], "pool_size": int(pool.size(0)), "budget": budget}
92
+ for control in controls:
93
+ row[f"p_vs_density_spearman_{control}"] = corr(scores[control], density)
94
+ top = torch.argsort(scores[control])[:budget]
95
+ row[f"top_budget_mean_bce_{control}"] = float(scores[control][top].mean())
96
+ row[f"top_budget_density_{control}"] = float(density[top].mean())
97
+ for i, first in enumerate(controls):
98
+ for second in controls[i + 1:]:
99
+ row[f"rank_corr_{first}_vs_{second}"] = corr(scores[first], scores[second])
100
+ left = set(torch.argsort(scores[first])[:budget].tolist())
101
+ right = set(torch.argsort(scores[second])[:budget].tolist())
102
+ row[f"top_budget_jaccard_{first}_vs_{second}"] = len(left & right) / max(1, len(left | right))
103
+ rows.append(row)
104
+
105
+ keys = sorted({key for row in rows for key in row})
106
+ prefix = Path(args.output_prefix)
107
+ prefix.parent.mkdir(parents=True, exist_ok=True)
108
+ import csv
109
+ with prefix.with_name(prefix.name + "_per_molecule.csv").open("w", newline="") as handle:
110
+ writer = csv.DictWriter(handle, fieldnames=keys)
111
+ writer.writeheader(); writer.writerows(rows)
112
+ summary = {"molecules": len(rows), "controls": controls}
113
+ for key in keys:
114
+ if key in {"mol_id", "pool_size", "budget"}:
115
+ continue
116
+ vals = [float(row[key]) for row in rows if key in row]
117
+ summary[key] = {"mean": float(np.mean(vals)), "std": float(np.std(vals))}
118
+ prefix.with_name(prefix.name + "_summary.json").write_text(json.dumps(summary, indent=2) + "\n")
119
+ print(json.dumps(summary, indent=2))
120
+
121
+
122
+ if __name__ == "__main__":
123
+ main()
@@ -0,0 +1,30 @@
1
+ #!/usr/bin/env python3
2
+ """Inventory local receptor, ligand, pose, CSV, and PyMOL-session candidates."""
3
+
4
+ from __future__ import annotations
5
+
6
+ import json
7
+ import re
8
+ from pathlib import Path
9
+
10
+
11
+ ROOTS = (Path("data"), Path("outputs"))
12
+ PATTERN = re.compile(r"(receptor|protein|ligand|pose|dock|vina|pymol|\.pse$|\.pdb$|\.pdbqt$|\.sdf$|\.mol2$|\.csv$)", re.I)
13
+
14
+
15
+ def main() -> None:
16
+ records = []
17
+ for root in ROOTS:
18
+ if not root.exists():
19
+ continue
20
+ for path in root.rglob("*"):
21
+ if path.is_file() and PATTERN.search(str(path)):
22
+ records.append(str(path))
23
+ out = Path("outputs/binding_mode_figure/discovery_report.json")
24
+ out.parent.mkdir(parents=True, exist_ok=True)
25
+ out.write_text(json.dumps({"candidates": sorted(records)}, indent=2) + "\n")
26
+ print(f"Saved {len(records)} candidates to {out}")
27
+
28
+
29
+ if __name__ == "__main__":
30
+ main()
@@ -0,0 +1,230 @@
1
+ #!/usr/bin/env python3
2
+ """Evaluate optional functional-aware Stage-I probability teachers.
3
+
4
+ This diagnostic is intentionally protein-free. It compares predicted pairwise
5
+ probability maps with geometry and functional-aware ensemble teachers on the
6
+ same GEOM split, and exports a compact visual audit for one representative
7
+ molecule. It does not modify checkpoints or the main MANIMOL pipeline.
8
+ """
9
+
10
+ from __future__ import annotations
11
+
12
+ import argparse
13
+ from collections import OrderedDict
14
+ from pathlib import Path
15
+ import sys
16
+
17
+ import matplotlib.pyplot as plt
18
+ import numpy as np
19
+ import pandas as pd
20
+ import torch
21
+ from torch_geometric.data import Batch
22
+
23
+ ROOT = Path(__file__).resolve().parents[1]
24
+ if str(ROOT) not in sys.path:
25
+ sys.path.insert(0, str(ROOT))
26
+
27
+ from dataset import QM9Dataset
28
+ from models.model0 import (
29
+ _functional_atom_masks,
30
+ cross_entropy_loss,
31
+ functional_aware_teacher_graph,
32
+ prob_low_dim_kernel,
33
+ )
34
+ from train_torsional_denoiser import load_base_model
35
+
36
+
37
+ def parse_checkpoints(value: str) -> OrderedDict[str, str]:
38
+ result: OrderedDict[str, str] = OrderedDict()
39
+ for item in value.split(","):
40
+ item = item.strip()
41
+ if not item:
42
+ continue
43
+ if "=" not in item:
44
+ raise ValueError("--checkpoints expects Label=/path/to/checkpoint pairs.")
45
+ label, path = item.split("=", 1)
46
+ result[label.strip()] = path.strip()
47
+ if not result:
48
+ raise ValueError("At least one checkpoint is required.")
49
+ return result
50
+
51
+
52
+ def checkpoint_max_confs(path: str) -> int:
53
+ checkpoint = torch.load(path, map_location="cpu")
54
+ state = checkpoint.get("model_state_dict", checkpoint.get("state_dict", checkpoint)) if isinstance(checkpoint, dict) else checkpoint
55
+ for key, value in state.items():
56
+ if key.endswith("conf_embedding.weight"):
57
+ return int(value.shape[0])
58
+ raise KeyError(f"conf_embedding.weight is missing from checkpoint: {path}")
59
+
60
+
61
+ def grouped_split(dataset, indices, max_molecules: int):
62
+ groups: OrderedDict[int, list] = OrderedDict()
63
+ for index in indices:
64
+ item = dataset[int(index)]
65
+ mol_id = int(torch.as_tensor(item.mol_id).view(-1)[0].item())
66
+ groups.setdefault(mol_id, []).append(item)
67
+ if max_molecules > 0 and len(groups) >= max_molecules:
68
+ continue
69
+ groups = OrderedDict((key, value) for key, value in groups.items())
70
+ if max_molecules > 0:
71
+ groups = OrderedDict(list(groups.items())[:max_molecules])
72
+ return groups
73
+
74
+
75
+ def functional_pair_mask(mol, n_atoms: int, device):
76
+ masks = _functional_atom_masks(mol, n_atoms, device)
77
+ hbond = (masks["hbd"][:, None] & masks["hba"][None, :]) | (masks["hba"][:, None] & masks["hbd"][None, :])
78
+ aromatic = masks["aromatic"][:, None] & masks["aromatic"][None, :]
79
+ hydrophobic = masks["hydrophobic"][:, None] & masks["hydrophobic"][None, :]
80
+ mask = hbond | aromatic | hydrophobic
81
+ mask.fill_diagonal_(False)
82
+ return torch.triu(mask, diagonal=1)
83
+
84
+
85
+ @torch.no_grad()
86
+ def evaluate_one(model, conformers, device, kernel: str):
87
+ batch = Batch.from_data_list([conformers[0]]).to(device)
88
+ node_feat = model.gnn(batch)
89
+ graph_feat = model.pool(node_feat, batch.batch)
90
+ edge_i = model._get_local_edge_index(batch.edge_index, batch.batch == 0)
91
+ P, _ = model._predict_P_global(node_feat, edge_i)
92
+ P = P.detach()
93
+ q_geom_list, q_func_list = [], []
94
+ mol = conformers[0].rdmol
95
+ for conformer in conformers:
96
+ pos = conformer.pos.to(device=device, dtype=node_feat.dtype)
97
+ conf_id = int(torch.as_tensor(conformer.conf_id).view(-1)[0].item())
98
+ a, b = model.predict_ab(graph_feat[0], conf_id)
99
+ q_geom = prob_low_dim_kernel(pos, a, b, kernel=kernel)
100
+ q_geom_list.append(q_geom)
101
+ q_func_list.append(functional_aware_teacher_graph(q_geom, mol, model.args))
102
+ q_geom = torch.stack(q_geom_list).mean(dim=0)
103
+ q_func = torch.stack(q_func_list).mean(dim=0)
104
+ pair_mask = functional_pair_mask(mol, int(P.size(0)), device)
105
+ off_diag = torch.triu(torch.ones_like(P, dtype=torch.bool), diagonal=1)
106
+ other_mask = off_diag & ~pair_mask
107
+ functional_mean = P[pair_mask].mean() if pair_mask.any() else P.new_tensor(float("nan"))
108
+ other_mean = P[other_mask].mean() if other_mask.any() else P.new_tensor(float("nan"))
109
+ enrichment = functional_mean - other_mean if torch.isfinite(functional_mean) and torch.isfinite(other_mean) else P.new_tensor(float("nan"))
110
+ return {
111
+ "P": P.cpu(),
112
+ "Q_geom": q_geom.cpu(),
113
+ "Q_func": q_func.cpu(),
114
+ "bce_geometry": float(cross_entropy_loss(P, q_geom).item()),
115
+ "bce_functional": float(cross_entropy_loss(P, q_func).item()),
116
+ "functional_pair_probability": float(functional_mean.item()),
117
+ "other_pair_probability": float(other_mean.item()),
118
+ "functional_pair_enrichment": float(enrichment.item()),
119
+ "mol": mol,
120
+ }
121
+
122
+
123
+ def plot_audit(conformers, audit, output_prefix: Path, title: str):
124
+ fig, axes = plt.subplots(1, 4, figsize=(10.0, 2.65), dpi=300, gridspec_kw={"wspace": 0.34})
125
+ coords = np.stack([item.pos.detach().cpu().numpy() for item in conformers[: min(5, len(conformers))]])
126
+ for xyz in coords:
127
+ axes[0].plot(xyz[:, 0], xyz[:, 1], "o-", ms=2.8, lw=0.8, color="#8E6BBE", alpha=0.35)
128
+ axes[0].set_title("a Reference ensemble", loc="left", fontsize=8.4, weight="semibold")
129
+ axes[0].set_aspect("equal", adjustable="box")
130
+ axes[0].set_xticks([])
131
+ axes[0].set_yticks([])
132
+ for spine in axes[0].spines.values():
133
+ spine.set_visible(False)
134
+
135
+ maps = [("b $Q_{geom}$", audit["Q_geom"]), ("c $Q_{func}$", audit["Q_func"]), ("d $P_\\theta(G)$", audit["P"])]
136
+ for ax, (label, matrix) in zip(axes[1:], maps):
137
+ image = ax.imshow(matrix.numpy(), cmap="Purples", vmin=0.0, vmax=1.0, interpolation="nearest")
138
+ ax.set_title(label, loc="left", fontsize=8.4, weight="semibold")
139
+ ax.set_xticks([])
140
+ ax.set_yticks([])
141
+ for spine in ax.spines.values():
142
+ spine.set_color("#777777")
143
+ spine.set_linewidth(0.5)
144
+ cbar = fig.colorbar(image, ax=axes[1:], fraction=0.026, pad=0.02)
145
+ cbar.ax.tick_params(labelsize=6.3, width=0.5, length=2)
146
+ cbar.set_label("Pair probability", fontsize=6.8)
147
+ fig.suptitle(title, fontsize=9.0, y=1.01)
148
+ fig.savefig(output_prefix.with_suffix(".png"), bbox_inches="tight", pad_inches=0.03)
149
+ fig.savefig(output_prefix.with_suffix(".pdf"), bbox_inches="tight", pad_inches=0.03)
150
+ fig.savefig(output_prefix.with_suffix(".svg"), bbox_inches="tight", pad_inches=0.03)
151
+ plt.close(fig)
152
+
153
+
154
+ def main():
155
+ parser = argparse.ArgumentParser(description="Protein-free evaluation of functional-aware Stage-I teachers.")
156
+ parser.add_argument("--checkpoints", required=True, help="Comma-separated Label=/path pairs.")
157
+ parser.add_argument("--data_root", default="data")
158
+ parser.add_argument("--raw_prefix", default="geom_drugs")
159
+ parser.add_argument("--split", default="test", choices=["train", "val", "test"])
160
+ parser.add_argument("--max_confs", type=int, default=0,
161
+ help="Conformer cap; 0 reads the shared capacity from the supplied checkpoints.")
162
+ parser.add_argument("--max_molecules", type=int, default=50)
163
+ parser.add_argument("--device", default="auto")
164
+ parser.add_argument("--stage1_kernel", default="umap")
165
+ parser.add_argument("--output_prefix", default="outputs/functional_prior/stage1_teacher_alignment")
166
+ # The YAML runner appends common training flags (for example
167
+ # --fixed_dump_name) that are irrelevant to this standalone diagnostic.
168
+ args, _ = parser.parse_known_args()
169
+
170
+ device = torch.device("cuda" if args.device == "auto" and torch.cuda.is_available() else args.device if args.device != "auto" else "cpu")
171
+ checkpoints = parse_checkpoints(args.checkpoints)
172
+ capacities = {label: checkpoint_max_confs(path) for label, path in checkpoints.items()}
173
+ unique_capacities = set(capacities.values())
174
+ if int(args.max_confs) == 0:
175
+ if len(unique_capacities) != 1:
176
+ raise ValueError(
177
+ "Functional-prior comparison requires checkpoints trained with the same max_confs; "
178
+ f"received {capacities}."
179
+ )
180
+ args.max_confs = unique_capacities.pop()
181
+ print(f"Auto-resolved max_confs={args.max_confs} from checkpoints.")
182
+ elif any(capacity != int(args.max_confs) for capacity in capacities.values()):
183
+ raise ValueError(
184
+ f"--max_confs={args.max_confs} does not match checkpoint capacities: {capacities}."
185
+ )
186
+ dataset = QM9Dataset(name="Drugs", root=args.data_root, max_confs=args.max_confs, raw_prefix=args.raw_prefix)
187
+ split_indices = {"train": dataset.train_index, "val": dataset.valid_index, "test": dataset.test_index}[args.split]
188
+ groups = grouped_split(dataset, split_indices, args.max_molecules)
189
+ out_prefix = Path(args.output_prefix)
190
+ out_prefix.parent.mkdir(parents=True, exist_ok=True)
191
+
192
+ rows = []
193
+ visual_candidate = None
194
+ for label, checkpoint in checkpoints.items():
195
+ loader_args = type("Args", (), {"checkpoint": checkpoint, "max_confs": args.max_confs})()
196
+ model = load_base_model(loader_args, device)
197
+ for mol_id, conformers in groups.items():
198
+ audit = evaluate_one(model, conformers, device, args.stage1_kernel)
199
+ smiles = str(getattr(conformers[0], "smiles", ""))
200
+ rows.append({
201
+ "variant": label,
202
+ "mol_id": mol_id,
203
+ "smiles": smiles,
204
+ "n_conformers": len(conformers),
205
+ "bce_geometry": audit["bce_geometry"],
206
+ "bce_functional": audit["bce_functional"],
207
+ "functional_pair_probability": audit["functional_pair_probability"],
208
+ "other_pair_probability": audit["other_pair_probability"],
209
+ "functional_pair_enrichment": audit["functional_pair_enrichment"],
210
+ })
211
+ if visual_candidate is None and np.isfinite(audit["functional_pair_enrichment"]):
212
+ visual_candidate = (label, conformers, audit)
213
+
214
+ per_molecule = pd.DataFrame(rows)
215
+ summary = per_molecule.groupby("variant", sort=False).mean(numeric_only=True).reset_index()
216
+ per_path = out_prefix.with_name(out_prefix.name + "_per_molecule.csv")
217
+ summary_path = out_prefix.with_name(out_prefix.name + "_summary.csv")
218
+ per_molecule.to_csv(per_path, index=False)
219
+ summary.to_csv(summary_path, index=False)
220
+ if visual_candidate is not None:
221
+ label, conformers, audit = visual_candidate
222
+ plot_audit(conformers, audit, out_prefix.with_name(out_prefix.name + "_heatmap"), f"Functional-aware probability prior: {label}")
223
+ print(f"Saved: {per_path}")
224
+ print(f"Saved: {summary_path}")
225
+ print(f"Evaluated {len(groups)} molecules on {device}.")
226
+ print(summary.to_string(index=False, float_format=lambda value: f"{value:.4f}"))
227
+
228
+
229
+ if __name__ == "__main__":
230
+ main()
@@ -0,0 +1,74 @@
1
+ #!/usr/bin/env python
2
+ """COV/AMR evaluation for GeoManimol generated ensembles."""
3
+
4
+ from __future__ import annotations
5
+
6
+ import argparse
7
+ import sys
8
+ from pathlib import Path
9
+
10
+ import torch
11
+
12
+ sys.path.insert(0, str(Path(__file__).resolve().parents[1]))
13
+
14
+ from geomanimol.data import load_molecule_groups
15
+ from geomanimol.geometry import DynamicGeometryMemory
16
+ from geomanimol.model import GeoManimol
17
+
18
+
19
+ def kabsch_rmsd(a: torch.Tensor, b: torch.Tensor) -> float:
20
+ a = a - a.mean(dim=0, keepdim=True)
21
+ b = b - b.mean(dim=0, keepdim=True)
22
+ cov = b.t() @ a
23
+ u, _, vh = torch.linalg.svd(cov)
24
+ correction = torch.eye(3, dtype=a.dtype)
25
+ correction[-1, -1] = torch.sign(torch.linalg.det(vh.t() @ u.t()))
26
+ rot = vh.t() @ correction @ u.t()
27
+ return float(torch.sqrt(((b @ rot - a) ** 2).sum(dim=-1).mean().clamp_min(1e-12)))
28
+
29
+
30
+ def distances(reference, generated):
31
+ return torch.tensor([[kabsch_rmsd(r, g) for g in generated] for r in reference])
32
+
33
+
34
+ def main():
35
+ p = argparse.ArgumentParser()
36
+ p.add_argument("--test", default="data/geom_drugs_geomol_top20/geom_drugs_geomol_top20_debug_val.pt")
37
+ p.add_argument("--checkpoint", default="outputs/geomanimol/debug_p0_p1_checkpoint.pt")
38
+ p.add_argument("--molecules", type=int, default=2)
39
+ p.add_argument("--samples", type=int, default=8)
40
+ p.add_argument("--threshold", type=float, default=0.75)
41
+ p.add_argument("--steps", type=int, default=10)
42
+ args = p.parse_args()
43
+
44
+ molecules = load_molecule_groups(args.test, args.molecules)
45
+ checkpoint = torch.load(args.checkpoint, map_location="cpu", weights_only=False)
46
+ saved = checkpoint.get("args", {})
47
+ model = GeoManimol(saved.get("node_dim", 32), saved.get("n_basins", 3), saved.get("manifold_dim", 8), saved.get("diffusion_steps", 1000))
48
+ model.load_state_dict(checkpoint["model"])
49
+ model.eval()
50
+
51
+ recall_cov, precision_cov, recall_amr, precision_amr = [], [], [], []
52
+ for mol in molecules:
53
+ generated = model.generate(mol, args.samples, args.steps)
54
+ matrix = distances(mol["conformations"], generated)
55
+ recall_min = matrix.min(dim=1).values
56
+ precision_min = matrix.min(dim=0).values
57
+ recall_cov.append(float((recall_min <= args.threshold).float().mean()))
58
+ precision_cov.append(float((precision_min <= args.threshold).float().mean()))
59
+ recall_amr.append(float(recall_min.mean()))
60
+ precision_amr.append(float(precision_min.mean()))
61
+
62
+ print({
63
+ "molecules": len(molecules),
64
+ "samples": args.samples,
65
+ "threshold": args.threshold,
66
+ "COV-R": sum(recall_cov) / len(recall_cov),
67
+ "COV-P": sum(precision_cov) / len(precision_cov),
68
+ "AMR-R": sum(recall_amr) / len(recall_amr),
69
+ "AMR-P": sum(precision_amr) / len(precision_amr),
70
+ })
71
+
72
+
73
+ if __name__ == "__main__":
74
+ main()
@@ -0,0 +1,23 @@
1
+ #!/usr/bin/env python
2
+ """Evaluate the parallel torsion flow-matching route."""
3
+ from __future__ import annotations
4
+ import argparse,sys,json
5
+ from pathlib import Path
6
+ import torch
7
+ sys.path.insert(0,str(Path(__file__).resolve().parents[1]))
8
+ from geomanimol.data import load_molecule_groups
9
+ from geomanimol.residual import etkdg_scaffolds
10
+ from geomanimol.torsion_flow import TorsionFlowGeoManimol
11
+ from scripts.evaluate_geomanimol import distances
12
+ def main():
13
+ p=argparse.ArgumentParser(); p.add_argument('--test',default='data/geom_drugs_geomol_top20/geom_drugs_geomol_top20_debug_val.pt'); p.add_argument('--checkpoint',default='outputs/geomanimol/flow_debug_checkpoint.pt'); p.add_argument('--molecules',type=int,default=20); p.add_argument('--scaffolds',type=int,default=10); p.add_argument('--samples',type=int,default=20); p.add_argument('--steps',type=int,default=20); p.add_argument('--threshold',type=float,default=.75); p.add_argument('--condition-mode',choices=('full','no_z','shuffle_z'),default='full'); p.add_argument('--output',default=''); a=p.parse_args(); ms=load_molecule_groups(a.test,a.molecules); ck=torch.load(a.checkpoint,map_location='cpu',weights_only=False); c=ck['args']; model=TorsionFlowGeoManimol(c['node_dim'],c['n_basins'],c['manifold_dim'],c.get('assignment_weight',.5),c.get('basin_weight',.2)); model.load_state_dict(ck['model']); model.eval(); rr=[]; pp=[]; ar=[]; ap=[]
14
+ for m in ms:
15
+ gens=[]; ss=etkdg_scaffolds(m['mol'],a.scaffolds,30300+m['mol_id']*100)
16
+ for s in ss: gens.append(model.generate(m,s,max(1,a.samples//len(ss)),a.steps,a.condition_mode))
17
+ g=torch.cat(gens)[:a.samples]; d=distances(m['conformations'],g); r,q=d.min(1).values,d.min(0).values; rr.append(float((r<=a.threshold).float().mean())); pp.append(float((q<=a.threshold).float().mean())); ar.append(float(r.mean())); ap.append(float(q.mean()))
18
+ result={'molecules':len(ms),'scaffolds':a.scaffolds,'samples':a.samples,'steps':a.steps,'threshold':a.threshold,'condition_mode':a.condition_mode,'COV-R':sum(rr)/len(rr),'COV-P':sum(pp)/len(pp),'AMR-R':sum(ar)/len(ar),'AMR-P':sum(ap)/len(ap)}
19
+ print(result)
20
+ if a.output:
21
+ Path(a.output).parent.mkdir(parents=True,exist_ok=True)
22
+ Path(a.output).write_text(json.dumps(result,indent=2),encoding='utf-8')
23
+ if __name__=='__main__': main()