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.
- args_parse.py +593 -0
- candidate_corrector.py +161 -0
- candidate_scorer.py +359 -0
- conformend/__init__.py +36 -0
- conformend/refiner.py +25 -0
- dataset/__init__.py +1 -0
- dataset/drugdataset.py +644 -0
- dataset/manifold.py +237 -0
- dataset/sharded_drugdataset.py +124 -0
- dataset/smiles2graph.py +217 -0
- dualmapref/__init__.py +24 -0
- dualmapref/refiner.py +16 -0
- dualmapref-0.2.8.dist-info/LICENSE +21 -0
- dualmapref-0.2.8.dist-info/METADATA +167 -0
- dualmapref-0.2.8.dist-info/RECORD +186 -0
- dualmapref-0.2.8.dist-info/WHEEL +5 -0
- dualmapref-0.2.8.dist-info/entry_points.txt +10 -0
- dualmapref-0.2.8.dist-info/top_level.txt +29 -0
- exputils.py +289 -0
- infer.py +23 -0
- infer_base_conformers.py +5589 -0
- infer_mean_dispersion_torsion.py +1117 -0
- infer_torsion.py +752 -0
- infer_torsional_denoiser.py +1021 -0
- manimol/__init__.py +30 -0
- manimol/__main__.py +6 -0
- manimol/cli.py +36 -0
- manimol/full_cli.py +41 -0
- manimol/legacy_imports.py +43 -0
- manimol/manifest.py +56 -0
- manimol/postprocess.py +148 -0
- manimol/priors.py +60 -0
- manimol/protocols.py +119 -0
- manimol/refiner.py +645 -0
- manimol/runtime.py +194 -0
- manimol/selection.py +85 -0
- manimol/torsion.py +22 -0
- manimol/train_cli.py +14 -0
- mixture_flow/src/__init__.py +1 -0
- mixture_flow/src/_path.py +7 -0
- mixture_flow/src/infer28_mixture_torsion_flow.py +1093 -0
- mixture_flow/src/mixture_torsion_flow.py +291 -0
- mixture_flow/src/summarize_mixture_debug.py +80 -0
- mixture_flow/src/train28_mixture_torsion_flow.py +583 -0
- mixture_torsion_flow.py +7 -0
- models/ manifold_learning.py +86 -0
- models/__init__.py +8 -0
- models/dist.py +273 -0
- models/dist2coords.py +23 -0
- models/egnn.py +107 -0
- models/experimental_backbones.py +364 -0
- models/gnnconv.py +512 -0
- models/kernel_inversion.py +141 -0
- models/kernels.py +427 -0
- models/losses.py +154 -0
- models/mean_dispersion_bridge.py +119 -0
- models/mean_dispersion_torsion_context.py +155 -0
- models/model.py +73 -0
- models/model0.py +2375 -0
- models/vis.py +128 -0
- pgraph_controls.py +107 -0
- scripts/__init__.py +2 -0
- scripts/analyze_basin_alignment.py +63 -0
- scripts/analyze_hif2a_conformer_aggregation.py +267 -0
- scripts/analyze_hif2a_contact_pharmacophore.py +1111 -0
- scripts/analyze_hif2a_fixed_budget.py +202 -0
- scripts/analyze_hif2a_pharmacophore.py +405 -0
- scripts/analyze_hif2a_pharmacophore_match_metric.py +386 -0
- scripts/analyze_p_control_candidate_flow.py +154 -0
- scripts/analyze_scaffold_basin.py +83 -0
- scripts/audit_dispersion_proposals.py +208 -0
- scripts/audit_etflow_protocol.py +258 -0
- scripts/audit_external_overlap.py +150 -0
- scripts/audit_oldbest_fulltrainval_split.py +82 -0
- scripts/audit_pdbbind_contact_pharmacophores.py +146 -0
- scripts/audit_qm9_geomol_test_split.py +94 -0
- scripts/audit_stage1_stage2_cross.py +131 -0
- scripts/build_geom_drugs_lowref_diagnostic.py +84 -0
- scripts/build_qm9_backfill_manifest.py +99 -0
- scripts/check_etflow_runtime.py +56 -0
- scripts/compare_prior_sources.py +122 -0
- scripts/compose_binding_mode_figure.py +87 -0
- scripts/compose_hif2a_contact_pharmacophore_suppfig.py +255 -0
- scripts/compose_hif2a_functional_geometry_pipeline.py +266 -0
- scripts/compose_manimol_internal_architecture.py +291 -0
- scripts/diagnose_flow_basin_intervention.py +54 -0
- scripts/diagnose_hif2a_pharmacophore_budget.py +185 -0
- scripts/diagnose_route2_p_ranking.py +123 -0
- scripts/discover_binding_mode_inputs.py +30 -0
- scripts/evaluate_functional_prior_stage1.py +230 -0
- scripts/evaluate_geomanimol.py +74 -0
- scripts/evaluate_geomanimol_flow.py +23 -0
- scripts/evaluate_geomanimol_multiscaffold.py +46 -0
- scripts/evaluate_geomanimol_residual.py +45 -0
- scripts/evaluate_geomanimol_torsion.py +40 -0
- scripts/evaluate_hif2a_bioactive_enrichment.py +91 -0
- scripts/evaluate_hif2a_pms_suite.py +440 -0
- scripts/evaluate_pdbbind_contact_pms.py +155 -0
- scripts/evaluate_platinum_external.py +114 -0
- scripts/evaluate_platinum_pool.py +82 -0
- scripts/evaluate_route2_calibrated_p.py +104 -0
- scripts/evaluate_route2_library_components.py +596 -0
- scripts/evaluate_route2_p_basin_budget.py +288 -0
- scripts/evaluate_stage1_checkpoint_only.py +30 -0
- scripts/export_dispersion_bond_audit.py +136 -0
- scripts/export_top20_shards.py +207 -0
- scripts/external_validation_metrics.py +152 -0
- scripts/fit_topology_prior.py +117 -0
- scripts/frozen_dispersion_audit.py +281 -0
- scripts/geomanimol_debug.py +50 -0
- scripts/geomanimol_smoke.py +37 -0
- scripts/infer_etflow_matched.py +524 -0
- scripts/inspect_checkpoint.py +12 -0
- scripts/inspect_conformer_capacity.py +71 -0
- scripts/inspect_pool.py +12 -0
- scripts/make_figure3_selection_loss.py +474 -0
- scripts/make_figure3_selection_summary.py +275 -0
- scripts/make_geom_debug_subset.py +62 -0
- scripts/make_low_reference_test_subset.py +70 -0
- scripts/merge_stage1_into_stage2.py +82 -0
- scripts/place_hif2a_candidates_for_evaluation.py +66 -0
- scripts/plot_hif2a_low_budget_efficiency.py +100 -0
- scripts/plot_prior_validation.py +48 -0
- scripts/precompute_stage2_assignments.py +90 -0
- scripts/prepare_bace_activity.py +98 -0
- scripts/prepare_bace_etkdg_benchmark.py +90 -0
- scripts/prepare_figure5_4x4_cases.py +470 -0
- scripts/prepare_geom_drugs_geomol_top20.py +472 -0
- scripts/prepare_pdbbind_core_raw.py +90 -0
- scripts/prepare_platinum_raw.py +74 -0
- scripts/prepare_pubchem_etkdg.py +54 -0
- scripts/rebuild_hif2a_final_sdf_and_metrics.py +55 -0
- scripts/rebuild_hif2a_fixed_pool_sweep.py +175 -0
- scripts/rebuild_hif2a_strict.py +220 -0
- scripts/recompute_hif2a_bootstrap.py +63 -0
- scripts/reference_free_geometry.py +112 -0
- scripts/render_binding_modes.py +413 -0
- scripts/render_figure5_4x4.py +330 -0
- scripts/render_figure6_pharmacophore_pymol.py +162 -0
- scripts/render_hif2a_contact_pharmacophore_pymol.py +414 -0
- scripts/render_hif2a_figure11.py +397 -0
- scripts/run_bace_2d_baseline.py +73 -0
- scripts/run_drugs_validation_matrix.py +225 -0
- scripts/run_external_reference_free.py +53 -0
- scripts/run_manimol_finalk_sensitivity.py +106 -0
- scripts/run_manimol_oversampling_sensitivity.py +109 -0
- scripts/run_pdisp_matched_intervention.py +116 -0
- scripts/run_stage1_stage2_cross20.py +83 -0
- scripts/score_hif2a_candidates_with_pgraph.py +221 -0
- scripts/summarize_dispersion_intervention.py +88 -0
- scripts/test_mean_dispersion_bridge.py +50 -0
- scripts/train_dispersion_head_diagnostic.py +320 -0
- scripts/train_dispersion_head_streaming.py +519 -0
- scripts/train_geomanimol.py +100 -0
- scripts/train_geomanimol_flow.py +26 -0
- scripts/train_geomanimol_residual.py +70 -0
- scripts/train_geomanimol_torsion.py +50 -0
- scripts/train_quantile_representation_diagnostic.py +204 -0
- scripts/validate_mean_dispersion_prior.py +173 -0
- scripts/validate_packed_shard.py +41 -0
- scripts/validate_stage1_prior.py +221 -0
- scripts/validate_top20_shards.py +36 -0
- scripts/validation/__init__.py +1 -0
- scripts/validation/hif2a_downstream_baselines.py +105 -0
- scripts/validation/hif2a_pairwise_ranker.py +218 -0
- scripts/verify_binding_mode_figure.py +47 -0
- torsion_manifold.py +281 -0
- train.py +78 -0
- train_graph_encoder.py +206 -0
- train_local_torsion_corrector.py +511 -0
- train_mean_dispersion_torsion_prior.py +329 -0
- train_probability_basin.py +235 -0
- train_torsion_generator.py +1631 -0
- train_torsion_manifold_prior.py +258 -0
- train_torsional_denoiser.py +415 -0
- trainer.py +1038 -0
- utils/__init__.py +7 -0
- utils/checkpoint.py +40 -0
- utils/device.py +17 -0
- utils/helpers.py +98 -0
- utils/kabsch.py +29 -0
- utils/lookup_table.py +164 -0
- utils/metrics.py +50 -0
- utils/optuna.py +111 -0
- utils/save_mol.py +366 -0
- utils/util.py +36 -0
manimol/__init__.py
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
1
|
+
"""ConforMend utilities and the checkpoint-backed full inference runtime."""
|
|
2
|
+
|
|
3
|
+
from .legacy_imports import install_legacy_imports
|
|
4
|
+
|
|
5
|
+
install_legacy_imports()
|
|
6
|
+
|
|
7
|
+
from .priors import ensemble_pairwise_prior
|
|
8
|
+
from .runtime import ConforMend, ManiMol, run_full_inference
|
|
9
|
+
from .selection import density_centrality_select, pairwise_rmsd
|
|
10
|
+
from .torsion import circular_standard_deviation, wrap_angle
|
|
11
|
+
from .postprocess import fps_indices, mmff94s_window_fps, select_energy_window
|
|
12
|
+
|
|
13
|
+
# ``ManiMol`` remains a compatibility alias for existing checkpoints and
|
|
14
|
+
# downstream scripts released before the rename.
|
|
15
|
+
|
|
16
|
+
__all__ = [
|
|
17
|
+
"circular_standard_deviation",
|
|
18
|
+
"density_centrality_select",
|
|
19
|
+
"ensemble_pairwise_prior",
|
|
20
|
+
"ManiMol",
|
|
21
|
+
"ConforMend",
|
|
22
|
+
"pairwise_rmsd",
|
|
23
|
+
"fps_indices",
|
|
24
|
+
"select_energy_window",
|
|
25
|
+
"mmff94s_window_fps",
|
|
26
|
+
"run_full_inference",
|
|
27
|
+
"wrap_angle",
|
|
28
|
+
]
|
|
29
|
+
|
|
30
|
+
__version__ = "0.2.8"
|
manimol/__main__.py
ADDED
manimol/cli.py
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
1
|
+
"""Command-line entry point for reference-free representative selection."""
|
|
2
|
+
|
|
3
|
+
from __future__ import annotations
|
|
4
|
+
|
|
5
|
+
import argparse
|
|
6
|
+
from pathlib import Path
|
|
7
|
+
|
|
8
|
+
import numpy as np
|
|
9
|
+
|
|
10
|
+
from .selection import density_centrality_select
|
|
11
|
+
|
|
12
|
+
|
|
13
|
+
def main() -> None:
|
|
14
|
+
parser = argparse.ArgumentParser(
|
|
15
|
+
description="Select a compact, diverse conformer library from an .npy array."
|
|
16
|
+
)
|
|
17
|
+
parser.add_argument("input", type=Path, help=".npy file: (n_conformers, n_atoms, 3)")
|
|
18
|
+
parser.add_argument("-k", type=int, required=True, help="number of representatives")
|
|
19
|
+
parser.add_argument("-o", "--output", type=Path, required=True, help="output index .npy file")
|
|
20
|
+
parser.add_argument("--alpha", type=float, default=1.0)
|
|
21
|
+
parser.add_argument("--beta", type=float, default=0.45)
|
|
22
|
+
parser.add_argument("--duplicate-radius", type=float, default=0.04)
|
|
23
|
+
args = parser.parse_args()
|
|
24
|
+
|
|
25
|
+
conformers = np.load(args.input)
|
|
26
|
+
indices = density_centrality_select(
|
|
27
|
+
conformers,
|
|
28
|
+
args.k,
|
|
29
|
+
alpha=args.alpha,
|
|
30
|
+
beta=args.beta,
|
|
31
|
+
duplicate_radius=args.duplicate_radius,
|
|
32
|
+
)
|
|
33
|
+
args.output.parent.mkdir(parents=True, exist_ok=True)
|
|
34
|
+
np.save(args.output, indices)
|
|
35
|
+
print(f"selected {len(indices)} / {len(conformers)} conformers")
|
|
36
|
+
print(f"indices written to {args.output}")
|
manimol/full_cli.py
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
1
|
+
"""Console entry point for the full checkpoint-backed ConforMend pipeline."""
|
|
2
|
+
|
|
3
|
+
from __future__ import annotations
|
|
4
|
+
|
|
5
|
+
import sys
|
|
6
|
+
|
|
7
|
+
|
|
8
|
+
def _ensure_default_oversampling(argv):
|
|
9
|
+
"""Add the package default without overriding an explicit user value."""
|
|
10
|
+
argv = list(argv)
|
|
11
|
+
if not any(
|
|
12
|
+
item == "--oversample_factor" or item.startswith("--oversample_factor=")
|
|
13
|
+
for item in argv
|
|
14
|
+
):
|
|
15
|
+
argv.extend(["--oversample_factor", "15"])
|
|
16
|
+
return argv
|
|
17
|
+
|
|
18
|
+
|
|
19
|
+
def main() -> None:
|
|
20
|
+
if "--help" in sys.argv[1:] or "-h" in sys.argv[1:]:
|
|
21
|
+
print(
|
|
22
|
+
"DualMapRef checkpoint-backed inference\n\n"
|
|
23
|
+
"Usage: dualmapref-infer --protocol mean_dispersion_denoising "
|
|
24
|
+
"--base_checkpoint PATH --data_root DIR "
|
|
25
|
+
"[--denoiser_checkpoint PATH | --pbasin_only] "
|
|
26
|
+
"[inference options]\n\n"
|
|
27
|
+
"Install dualmapref[full] to run the complete PyTorch/RDKit pipeline. "
|
|
28
|
+
"The underlying inference parser exposes additional options in that environment."
|
|
29
|
+
)
|
|
30
|
+
return
|
|
31
|
+
from .runtime import run_full_inference
|
|
32
|
+
|
|
33
|
+
# The benchmark implementation has its own complete argparse surface.
|
|
34
|
+
# Keep this wrapper transparent and append the package default only when
|
|
35
|
+
# the caller did not choose a budget explicitly.
|
|
36
|
+
argv = _ensure_default_oversampling(sys.argv[1:])
|
|
37
|
+
run_full_inference(argv)
|
|
38
|
+
|
|
39
|
+
|
|
40
|
+
if __name__ == "__main__":
|
|
41
|
+
main()
|
|
@@ -0,0 +1,43 @@
|
|
|
1
|
+
"""Load historical module names after importing :mod:`manimol`.
|
|
2
|
+
|
|
3
|
+
Some older Python-serialized checkpoints contain module-qualified class names.
|
|
4
|
+
This adapter preserves those names without keeping numbered implementation files.
|
|
5
|
+
"""
|
|
6
|
+
from __future__ import annotations
|
|
7
|
+
|
|
8
|
+
import importlib
|
|
9
|
+
import importlib.abc
|
|
10
|
+
import importlib.util
|
|
11
|
+
import sys
|
|
12
|
+
|
|
13
|
+
LEGACY_MODULES = {
|
|
14
|
+
"manimol_stage1": "train_graph_encoder",
|
|
15
|
+
"train2": "train_torsion_generator",
|
|
16
|
+
"train5": "train_torsional_denoiser",
|
|
17
|
+
"train7": "train_local_torsion_corrector",
|
|
18
|
+
"train8": "train_probability_basin",
|
|
19
|
+
"infer1": "infer_base_conformers",
|
|
20
|
+
"infer_torsion5": "infer_torsional_denoiser",
|
|
21
|
+
}
|
|
22
|
+
|
|
23
|
+
class _AliasLoader(importlib.abc.Loader):
|
|
24
|
+
def __init__(self, target: str):
|
|
25
|
+
self.target = target
|
|
26
|
+
|
|
27
|
+
def create_module(self, spec):
|
|
28
|
+
return importlib.import_module(self.target)
|
|
29
|
+
|
|
30
|
+
def exec_module(self, module):
|
|
31
|
+
pass
|
|
32
|
+
|
|
33
|
+
class _LegacyFinder(importlib.abc.MetaPathFinder):
|
|
34
|
+
def find_spec(self, fullname, path, target=None):
|
|
35
|
+
replacement = LEGACY_MODULES.get(fullname)
|
|
36
|
+
if replacement is None:
|
|
37
|
+
return None
|
|
38
|
+
return importlib.util.spec_from_loader(fullname, _AliasLoader(replacement))
|
|
39
|
+
|
|
40
|
+
def install_legacy_imports():
|
|
41
|
+
"""Register old-to-new aliases for this process, without importing ML modules."""
|
|
42
|
+
if not any(isinstance(finder, _LegacyFinder) for finder in sys.meta_path):
|
|
43
|
+
sys.meta_path.insert(0, _LegacyFinder())
|
manimol/manifest.py
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
1
|
+
"""Run-manifest helpers for reproducible public inference."""
|
|
2
|
+
|
|
3
|
+
from __future__ import annotations
|
|
4
|
+
|
|
5
|
+
import hashlib
|
|
6
|
+
import json
|
|
7
|
+
import platform
|
|
8
|
+
import sys
|
|
9
|
+
from datetime import datetime, timezone
|
|
10
|
+
from pathlib import Path
|
|
11
|
+
from typing import Any, Mapping
|
|
12
|
+
|
|
13
|
+
|
|
14
|
+
def sha256_file(path: str | Path, chunk_size: int = 1024 * 1024) -> str:
|
|
15
|
+
digest = hashlib.sha256()
|
|
16
|
+
with Path(path).open("rb") as handle:
|
|
17
|
+
for chunk in iter(lambda: handle.read(chunk_size), b""):
|
|
18
|
+
digest.update(chunk)
|
|
19
|
+
return digest.hexdigest()
|
|
20
|
+
|
|
21
|
+
|
|
22
|
+
def write_run_manifest(
|
|
23
|
+
output_dir: str | Path,
|
|
24
|
+
*,
|
|
25
|
+
protocol: str,
|
|
26
|
+
argv: list[str],
|
|
27
|
+
checkpoint: str,
|
|
28
|
+
data_root: str,
|
|
29
|
+
status: str = "started",
|
|
30
|
+
defaults: Mapping[str, Any] | None = None,
|
|
31
|
+
) -> Path:
|
|
32
|
+
"""Write a stable JSON manifest without serializing private data."""
|
|
33
|
+
|
|
34
|
+
destination = Path(output_dir).expanduser()
|
|
35
|
+
destination.mkdir(parents=True, exist_ok=True)
|
|
36
|
+
checkpoint_path = Path(checkpoint).expanduser()
|
|
37
|
+
payload = {
|
|
38
|
+
"schema_version": 1,
|
|
39
|
+
"status": status,
|
|
40
|
+
"protocol": protocol,
|
|
41
|
+
"argv": list(argv),
|
|
42
|
+
"defaults": dict(defaults or {}),
|
|
43
|
+
"checkpoint": {
|
|
44
|
+
"path": str(checkpoint_path),
|
|
45
|
+
"sha256": sha256_file(checkpoint_path),
|
|
46
|
+
},
|
|
47
|
+
"data_root": str(Path(data_root).expanduser()),
|
|
48
|
+
"runtime": {
|
|
49
|
+
"python": sys.version,
|
|
50
|
+
"platform": platform.platform(),
|
|
51
|
+
},
|
|
52
|
+
"timestamp_utc": datetime.now(timezone.utc).isoformat(),
|
|
53
|
+
}
|
|
54
|
+
path = destination / "manifest.json"
|
|
55
|
+
path.write_text(json.dumps(payload, indent=2, sort_keys=True) + "\n", encoding="utf-8")
|
|
56
|
+
return path
|
manimol/postprocess.py
ADDED
|
@@ -0,0 +1,148 @@
|
|
|
1
|
+
"""Deterministic fixed-budget post-processing for generated conformer pools.
|
|
2
|
+
|
|
3
|
+
The public protocol mirrors the paper's selected inference preparation:
|
|
4
|
+
MMFF94s optimization, a relative 5 kcal/mol energy window, farthest-point
|
|
5
|
+
selection (FPS), and a final MMFF94s optimization. Model checkpoints and
|
|
6
|
+
dataset records remain external to the package.
|
|
7
|
+
"""
|
|
8
|
+
|
|
9
|
+
from __future__ import annotations
|
|
10
|
+
|
|
11
|
+
from typing import Sequence
|
|
12
|
+
|
|
13
|
+
import numpy as np
|
|
14
|
+
|
|
15
|
+
|
|
16
|
+
def _validate_coords(coords: np.ndarray) -> np.ndarray:
|
|
17
|
+
array = np.asarray(coords, dtype=float)
|
|
18
|
+
if array.ndim != 3 or array.shape[-1] != 3:
|
|
19
|
+
raise ValueError("coords must have shape (n_conformers, n_atoms, 3)")
|
|
20
|
+
if array.shape[0] == 0:
|
|
21
|
+
raise ValueError("coords must contain at least one conformer")
|
|
22
|
+
if not np.isfinite(array).all():
|
|
23
|
+
raise ValueError("coords must contain only finite values")
|
|
24
|
+
return array
|
|
25
|
+
|
|
26
|
+
|
|
27
|
+
def _centered_rmsd(left: np.ndarray, right: np.ndarray) -> float:
|
|
28
|
+
left_centered = left - left.mean(axis=0, keepdims=True)
|
|
29
|
+
right_centered = right - right.mean(axis=0, keepdims=True)
|
|
30
|
+
return float(np.sqrt(np.mean((left_centered - right_centered) ** 2)))
|
|
31
|
+
|
|
32
|
+
|
|
33
|
+
def fps_indices(coords: np.ndarray, target_count: int, *, start: int = 0) -> np.ndarray:
|
|
34
|
+
"""Select a deterministic farthest-point subset using centered RMSD.
|
|
35
|
+
|
|
36
|
+
Parameters
|
|
37
|
+
----------
|
|
38
|
+
coords:
|
|
39
|
+
Array with shape ``(n_conformers, n_atoms, 3)``.
|
|
40
|
+
target_count:
|
|
41
|
+
Number of conformers to retain. Values larger than the pool size are
|
|
42
|
+
clipped to the available pool.
|
|
43
|
+
start:
|
|
44
|
+
Initial conformer index; the default gives stable, order-independent
|
|
45
|
+
behavior for a fixed candidate pool.
|
|
46
|
+
"""
|
|
47
|
+
|
|
48
|
+
array = _validate_coords(coords)
|
|
49
|
+
if int(target_count) <= 0:
|
|
50
|
+
raise ValueError("target_count must be positive")
|
|
51
|
+
count = min(int(target_count), array.shape[0])
|
|
52
|
+
start_index = int(start)
|
|
53
|
+
if not 0 <= start_index < array.shape[0]:
|
|
54
|
+
raise ValueError("start must index an available conformer")
|
|
55
|
+
|
|
56
|
+
centered = array - array.mean(axis=1, keepdims=True)
|
|
57
|
+
distances = np.sqrt(
|
|
58
|
+
np.mean((centered[:, None, :, :] - centered[None, :, :, :]) ** 2, axis=(2, 3))
|
|
59
|
+
)
|
|
60
|
+
selected = [start_index]
|
|
61
|
+
nearest = distances[start_index].copy()
|
|
62
|
+
nearest[start_index] = -np.inf
|
|
63
|
+
while len(selected) < count:
|
|
64
|
+
candidate = int(np.argmax(nearest))
|
|
65
|
+
selected.append(candidate)
|
|
66
|
+
nearest = np.minimum(nearest, distances[candidate])
|
|
67
|
+
nearest[selected] = -np.inf
|
|
68
|
+
return np.asarray(selected, dtype=np.int64)
|
|
69
|
+
|
|
70
|
+
|
|
71
|
+
def select_energy_window(energies: Sequence[float], window_kcal: float = 5.0) -> np.ndarray:
|
|
72
|
+
"""Return indices within a relative energy window from the minimum."""
|
|
73
|
+
|
|
74
|
+
values = np.asarray(energies, dtype=float)
|
|
75
|
+
if values.ndim != 1 or values.size == 0:
|
|
76
|
+
raise ValueError("energies must be a non-empty one-dimensional array")
|
|
77
|
+
if window_kcal < 0:
|
|
78
|
+
raise ValueError("window_kcal must be non-negative")
|
|
79
|
+
finite = np.isfinite(values)
|
|
80
|
+
if not finite.any():
|
|
81
|
+
raise ValueError("energies contain no finite values")
|
|
82
|
+
minimum = float(values[finite].min())
|
|
83
|
+
return np.flatnonzero(finite & (values <= minimum + float(window_kcal)))
|
|
84
|
+
|
|
85
|
+
|
|
86
|
+
def mmff94s_window_fps(
|
|
87
|
+
conformers,
|
|
88
|
+
mol,
|
|
89
|
+
target_count: int,
|
|
90
|
+
*,
|
|
91
|
+
window_kcal: float = 5.0,
|
|
92
|
+
max_steps: int = 80,
|
|
93
|
+
final_mmff94s: bool = True,
|
|
94
|
+
):
|
|
95
|
+
"""Apply the selected fixed-budget MMFF94s/energy-window/FPS protocol.
|
|
96
|
+
|
|
97
|
+
``conformers`` is a Torch tensor or an array with shape ``(N, A, 3)`` and
|
|
98
|
+
``mol`` is an RDKit molecule containing matching atom coordinates. The
|
|
99
|
+
return value is a Torch tensor on CPU, matching the repository inference
|
|
100
|
+
artifact convention. Invalid MMFF candidates are excluded; if the
|
|
101
|
+
energy window contains fewer than the requested budget, the lowest finite
|
|
102
|
+
energy candidates refill the budget before FPS.
|
|
103
|
+
"""
|
|
104
|
+
|
|
105
|
+
try:
|
|
106
|
+
import torch
|
|
107
|
+
import infer_base_conformers
|
|
108
|
+
except ImportError as exc: # pragma: no cover - exercised in full extra
|
|
109
|
+
raise ImportError(
|
|
110
|
+
"mmff94s_window_fps requires the 'manimol[full]' dependencies"
|
|
111
|
+
) from exc
|
|
112
|
+
|
|
113
|
+
pool = conformers.detach().cpu() if hasattr(conformers, "detach") else torch.as_tensor(conformers)
|
|
114
|
+
if pool.ndim != 3 or pool.shape[-1] != 3 or pool.shape[0] == 0:
|
|
115
|
+
raise ValueError("conformers must have shape (n_conformers, n_atoms, 3)")
|
|
116
|
+
budget = min(int(target_count), int(pool.shape[0]))
|
|
117
|
+
if budget <= 0:
|
|
118
|
+
raise ValueError("target_count must be positive")
|
|
119
|
+
|
|
120
|
+
prepared, energies = [], []
|
|
121
|
+
for conformer in pool:
|
|
122
|
+
optimized, energy, valid = infer_base_conformers.optimize_with_mmff94s_and_energy(
|
|
123
|
+
conformer, mol, max_steps=int(max_steps)
|
|
124
|
+
)
|
|
125
|
+
prepared.append(optimized)
|
|
126
|
+
energies.append(float(energy) if valid else float("inf"))
|
|
127
|
+
prepared = torch.stack(prepared)
|
|
128
|
+
energies_np = np.asarray(energies, dtype=float)
|
|
129
|
+
window_idx = select_energy_window(energies_np, window_kcal=window_kcal)
|
|
130
|
+
if window_idx.size < budget:
|
|
131
|
+
finite_idx = np.flatnonzero(np.isfinite(energies_np))
|
|
132
|
+
refill = finite_idx[np.argsort(energies_np[finite_idx])[:budget]]
|
|
133
|
+
candidate_idx = np.asarray(refill, dtype=np.int64)
|
|
134
|
+
else:
|
|
135
|
+
candidate_idx = window_idx
|
|
136
|
+
chosen_idx = fps_indices(prepared[candidate_idx].numpy(), budget)
|
|
137
|
+
selected = prepared[candidate_idx[chosen_idx]]
|
|
138
|
+
if final_mmff94s:
|
|
139
|
+
selected = torch.stack(
|
|
140
|
+
[
|
|
141
|
+
infer_base_conformers.optimize_with_mmff94s_and_energy(conf, mol, max_steps=int(max_steps))[0]
|
|
142
|
+
for conf in selected
|
|
143
|
+
]
|
|
144
|
+
)
|
|
145
|
+
return selected.cpu()
|
|
146
|
+
|
|
147
|
+
|
|
148
|
+
__all__ = ["fps_indices", "select_energy_window", "mmff94s_window_fps"]
|
manimol/priors.py
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
1
|
+
"""Ensemble-level pairwise proximity and dispersion utilities.
|
|
2
|
+
|
|
3
|
+
These functions operate on already aligned Cartesian conformers. They do not
|
|
4
|
+
rank individual conformers and intentionally contain no model or dataset code.
|
|
5
|
+
"""
|
|
6
|
+
|
|
7
|
+
from __future__ import annotations
|
|
8
|
+
|
|
9
|
+
import numpy as np
|
|
10
|
+
|
|
11
|
+
from .selection import pairwise_rmsd
|
|
12
|
+
|
|
13
|
+
|
|
14
|
+
def ensemble_pairwise_prior(
|
|
15
|
+
conformers: np.ndarray,
|
|
16
|
+
*,
|
|
17
|
+
scale: float = 1.0,
|
|
18
|
+
) -> tuple[np.ndarray, np.ndarray]:
|
|
19
|
+
"""Return mean proximity and dispersion over an aligned conformer ensemble.
|
|
20
|
+
|
|
21
|
+
Parameters
|
|
22
|
+
----------
|
|
23
|
+
conformers:
|
|
24
|
+
Array with shape ``(n_conformers, n_atoms, 3)``.
|
|
25
|
+
scale:
|
|
26
|
+
Positive length scale for the proximity kernel in the same units as
|
|
27
|
+
the coordinates, commonly Angstrom.
|
|
28
|
+
|
|
29
|
+
Returns
|
|
30
|
+
-------
|
|
31
|
+
mean, dispersion:
|
|
32
|
+
Two ``(n_atoms, n_atoms)`` arrays. Proximity is
|
|
33
|
+
``exp(-RMSD_pair / scale)``; dispersion is its population variance
|
|
34
|
+
across the ensemble. Diagonal entries are zero.
|
|
35
|
+
"""
|
|
36
|
+
|
|
37
|
+
data = _validate_conformers(conformers)
|
|
38
|
+
if scale <= 0:
|
|
39
|
+
raise ValueError("scale must be positive")
|
|
40
|
+
# Pairwise atom distances are measured across conformers, not between
|
|
41
|
+
# whole conformers: each atom pair receives an ensemble-level signal.
|
|
42
|
+
deltas = data[:, :, None, :] - data[:, None, :, :]
|
|
43
|
+
distances = np.sqrt(np.sum(deltas * deltas, axis=-1))
|
|
44
|
+
proximity = np.exp(-distances / float(scale))
|
|
45
|
+
mean = proximity.mean(axis=0)
|
|
46
|
+
dispersion = proximity.var(axis=0)
|
|
47
|
+
np.fill_diagonal(mean, 0.0)
|
|
48
|
+
np.fill_diagonal(dispersion, 0.0)
|
|
49
|
+
return mean, dispersion
|
|
50
|
+
|
|
51
|
+
|
|
52
|
+
def _validate_conformers(conformers: np.ndarray) -> np.ndarray:
|
|
53
|
+
data = np.asarray(conformers, dtype=float)
|
|
54
|
+
if data.ndim != 3 or data.shape[-1] != 3:
|
|
55
|
+
raise ValueError("conformers must have shape (n_conformers, n_atoms, 3)")
|
|
56
|
+
if data.shape[0] == 0 or data.shape[1] == 0:
|
|
57
|
+
raise ValueError("conformers must contain at least one conformer and atom")
|
|
58
|
+
if not np.isfinite(data).all():
|
|
59
|
+
raise ValueError("conformers must contain only finite coordinates")
|
|
60
|
+
return data
|
manimol/protocols.py
ADDED
|
@@ -0,0 +1,119 @@
|
|
|
1
|
+
"""Validated public inference protocols.
|
|
2
|
+
|
|
3
|
+
The research entry point has a large argparse surface. This module keeps the
|
|
4
|
+
small public preset in one place so the CLI and Python API cannot silently
|
|
5
|
+
drift apart.
|
|
6
|
+
"""
|
|
7
|
+
|
|
8
|
+
from __future__ import annotations
|
|
9
|
+
|
|
10
|
+
import argparse
|
|
11
|
+
from pathlib import Path
|
|
12
|
+
from typing import Iterable, Mapping, Sequence
|
|
13
|
+
|
|
14
|
+
|
|
15
|
+
MEAN_DISPERSION_DENOISING = "mean_dispersion_denoising"
|
|
16
|
+
ROUTE2_PAPER = "route2_paper" # Legacy alias; kept for existing commands.
|
|
17
|
+
|
|
18
|
+
|
|
19
|
+
def mean_dispersion_denoising_defaults() -> dict[str, object]:
|
|
20
|
+
"""Return the validated, reference-free route-2 inference defaults."""
|
|
21
|
+
|
|
22
|
+
return {
|
|
23
|
+
"max_confs": 0, # infer checkpoint embedding size unless explicitly overridden
|
|
24
|
+
"oversample_factor": 15.0,
|
|
25
|
+
"select_candidates": "stable_fps_088",
|
|
26
|
+
"stable_displacement_quantile": 0.88,
|
|
27
|
+
"precision2r_density_k": 20,
|
|
28
|
+
"precision2r_prefilter_quantile": 0.45,
|
|
29
|
+
"precision2r_density_weight": 1.0,
|
|
30
|
+
"precision2r_centrality_weight": 0.45,
|
|
31
|
+
"precision2r_duplicate_radius": 0.04,
|
|
32
|
+
"use_dispersion_proposal": True,
|
|
33
|
+
"deterministic_modes": True,
|
|
34
|
+
"use_mmff": True,
|
|
35
|
+
"mmff_steps": 200,
|
|
36
|
+
"use_torsion_refine": True,
|
|
37
|
+
"use_etkdg": True,
|
|
38
|
+
"etkdg_candidate_pool": True,
|
|
39
|
+
"output_dedup_radius": 0.0,
|
|
40
|
+
}
|
|
41
|
+
|
|
42
|
+
|
|
43
|
+
def route2_paper_defaults() -> dict[str, object]:
|
|
44
|
+
"""Backward-compatible alias for historical callers."""
|
|
45
|
+
return mean_dispersion_denoising_defaults()
|
|
46
|
+
|
|
47
|
+
|
|
48
|
+
def validate_external_artifacts(
|
|
49
|
+
checkpoint: str,
|
|
50
|
+
data_root: str,
|
|
51
|
+
denoiser_checkpoint: str = "",
|
|
52
|
+
) -> None:
|
|
53
|
+
"""Fail early with actionable messages for external runtime artifacts."""
|
|
54
|
+
|
|
55
|
+
checkpoint_path = Path(checkpoint).expanduser()
|
|
56
|
+
data_path = Path(data_root).expanduser()
|
|
57
|
+
if not checkpoint_path.is_file():
|
|
58
|
+
raise FileNotFoundError(f"MANIMOL checkpoint does not exist: {checkpoint_path}")
|
|
59
|
+
if not data_path.is_dir():
|
|
60
|
+
raise FileNotFoundError(f"MANIMOL data_root does not exist or is not a directory: {data_path}")
|
|
61
|
+
if denoiser_checkpoint:
|
|
62
|
+
denoiser_path = Path(denoiser_checkpoint).expanduser()
|
|
63
|
+
if not denoiser_path.is_file():
|
|
64
|
+
raise FileNotFoundError(f"MANIMOL denoiser checkpoint does not exist: {denoiser_path}")
|
|
65
|
+
|
|
66
|
+
|
|
67
|
+
def _value_after(argv: Sequence[str], name: str, default: str = "") -> str:
|
|
68
|
+
for index, item in enumerate(argv):
|
|
69
|
+
if item == name and index + 1 < len(argv):
|
|
70
|
+
return str(argv[index + 1])
|
|
71
|
+
if item.startswith(name + "="):
|
|
72
|
+
return item.split("=", 1)[1]
|
|
73
|
+
return default
|
|
74
|
+
|
|
75
|
+
|
|
76
|
+
def _has_flag(argv: Sequence[str], name: str) -> bool:
|
|
77
|
+
return name in argv or any(item.startswith(name + "=") for item in argv)
|
|
78
|
+
|
|
79
|
+
|
|
80
|
+
def prepare_protocol_argv(argv: Iterable[str]) -> tuple[list[str], str, dict[str, object]]:
|
|
81
|
+
"""Apply a public protocol while preserving explicit CLI overrides."""
|
|
82
|
+
|
|
83
|
+
raw = list(argv)
|
|
84
|
+
parser = argparse.ArgumentParser(add_help=False)
|
|
85
|
+
parser.add_argument("--protocol", default=MEAN_DISPERSION_DENOISING)
|
|
86
|
+
protocol_args, remaining = parser.parse_known_args(raw)
|
|
87
|
+
protocol = str(protocol_args.protocol)
|
|
88
|
+
if protocol not in (MEAN_DISPERSION_DENOISING, ROUTE2_PAPER):
|
|
89
|
+
raise ValueError(f"Unknown MANIMOL protocol: {protocol!r}; expected {MEAN_DISPERSION_DENOISING!r}")
|
|
90
|
+
|
|
91
|
+
defaults = mean_dispersion_denoising_defaults()
|
|
92
|
+
prepared = list(remaining)
|
|
93
|
+
for key, value in defaults.items():
|
|
94
|
+
flag = "--" + key
|
|
95
|
+
if _has_flag(prepared, flag):
|
|
96
|
+
continue
|
|
97
|
+
if isinstance(value, bool):
|
|
98
|
+
if value:
|
|
99
|
+
prepared.append(flag)
|
|
100
|
+
else:
|
|
101
|
+
prepared.extend([flag, str(value)])
|
|
102
|
+
|
|
103
|
+
checkpoint = _value_after(prepared, "--base_checkpoint")
|
|
104
|
+
data_root = _value_after(prepared, "--data_root")
|
|
105
|
+
denoiser = _value_after(prepared, "--denoiser_checkpoint")
|
|
106
|
+
if not checkpoint:
|
|
107
|
+
raise ValueError("mean_dispersion_denoising requires --base_checkpoint")
|
|
108
|
+
if not data_root:
|
|
109
|
+
raise ValueError("mean_dispersion_denoising requires --data_root")
|
|
110
|
+
validate_external_artifacts(checkpoint, data_root, denoiser)
|
|
111
|
+
# The underlying parser requires the same base model as --checkpoint.
|
|
112
|
+
if not _has_flag(prepared, "--checkpoint"):
|
|
113
|
+
prepared.extend(["--checkpoint", checkpoint])
|
|
114
|
+
if not denoiser and not _has_flag(prepared, "--pbasin_only"):
|
|
115
|
+
raise ValueError(
|
|
116
|
+
"mean_dispersion_denoising requires --denoiser_checkpoint, or explicitly pass --pbasin_only "
|
|
117
|
+
"for Stage-II-only inference"
|
|
118
|
+
)
|
|
119
|
+
return prepared, protocol, defaults
|