#!/usr/bin/env python3 """Run Morgan/protein-descriptor LightGBM controls on every split manifest.""" from __future__ import annotations import argparse import importlib.metadata import json import math import time from collections import Counter from pathlib import Path import lightgbm as lgb import numpy as np from rdkit import Chem from rdkit.Chem import Descriptors, Lipinski, rdFingerprintGenerator from mitointeract_recovery.metrics import regression_metrics AMINO_ACIDS = "ACDEFGHIKLMNPQRSTVWY" DIPEPTIDES = tuple(a + b for a in AMINO_ACIDS for b in AMINO_ACIDS) MORGAN_BITS = 2048 def read_jsonl(path: Path) -> list[dict]: with path.open() as handle: return [json.loads(line) for line in handle if line.strip()] def ligand_features(smiles: str, generator) -> np.ndarray: mol = Chem.MolFromSmiles(smiles) if mol is None: raise ValueError(f"invalid canonical SMILES: {smiles}") fingerprint = generator.GetFingerprintAsNumPy(mol).astype(np.float32) descriptors = np.asarray( [ Descriptors.MolWt(mol) / 1000, Descriptors.MolLogP(mol) / 10, Descriptors.TPSA(mol) / 200, Lipinski.NumHDonors(mol) / 10, Lipinski.NumHAcceptors(mol) / 20, Lipinski.NumRotatableBonds(mol) / 30, Lipinski.RingCount(mol) / 20, Lipinski.FractionCSP3(mol), ], dtype=np.float32, ) return np.concatenate([fingerprint, descriptors]) def protein_features(sequence: str) -> np.ndarray: sequence = sequence.upper() length = max(1, len(sequence)) counts = Counter(sequence) amino_acid_composition = np.asarray( [counts[amino_acid] / length for amino_acid in AMINO_ACIDS], dtype=np.float32, ) dipeptide_counts = Counter( sequence[index : index + 2] for index in range(length - 1) ) denominator = max(1, length - 1) dipeptide_composition = np.asarray( [dipeptide_counts[pair] / denominator for pair in DIPEPTIDES], dtype=np.float32, ) return np.concatenate( [ np.asarray([math.log1p(length) / 10], dtype=np.float32), amino_acid_composition, dipeptide_composition, ] ) def build_features( rows: list[dict], ) -> tuple[np.ndarray, np.ndarray, list[str], list[str]]: generator = rdFingerprintGenerator.GetMorganGenerator(radius=2, fpSize=MORGAN_BITS) ligand_cache = { row["ligand_id"]: ligand_features(row["smiles"], generator) for row in rows } protein_cache = { row["protein_id"]: protein_features(row["sequence"]) for row in rows } ligand = np.stack([ligand_cache[row["ligand_id"]] for row in rows]) protein = np.stack([protein_cache[row["protein_id"]] for row in rows]) ligand_names = [f"morgan_{index}" for index in range(MORGAN_BITS)] + [ "mol_weight", "mol_logp", "tpsa", "h_donors", "h_acceptors", "rotatable_bonds", "ring_count", "fraction_csp3", ] protein_names = ( ["log_protein_length"] + [f"aac_{amino_acid}" for amino_acid in AMINO_ACIDS] + [f"dipeptide_{pair}" for pair in DIPEPTIDES] ) return ligand, protein, ligand_names, protein_names def read_manifest(path: Path) -> dict[str, str]: return {row["pair_id"]: row["split"] for row in read_jsonl(path)} def fit_model( name: str, features: np.ndarray, feature_names: list[str], targets: np.ndarray, split_indices: dict[str, np.ndarray], seed: int, ) -> dict: started = time.monotonic() model = lgb.LGBMRegressor( objective="regression_l2", n_estimators=1000, learning_rate=0.03, num_leaves=31, min_child_samples=20, subsample=0.8, colsample_bytree=0.8, reg_lambda=1.0, random_state=seed, n_jobs=8, deterministic=True, force_col_wise=True, verbosity=-1, ) train = split_indices["train"] validation = split_indices["validation"] test = split_indices["test"] model.fit( features[train], targets[train], eval_X=features[validation], eval_y=targets[validation], eval_metric="rmse", callbacks=[lgb.early_stopping(50, verbose=False)], ) importances = sorted( zip(feature_names, model.feature_importances_, strict=True), key=lambda item: item[1], reverse=True, )[:20] return { "name": name, "best_iteration": int(model.best_iteration_), "validation": regression_metrics( targets[validation], model.predict(features[validation]) ), "test": regression_metrics(targets[test], model.predict(features[test])), "top_feature_importance": [ {"feature": feature, "gain_proxy": int(importance)} for feature, importance in importances ], "fit_and_eval_seconds": time.monotonic() - started, } def main() -> None: parser = argparse.ArgumentParser() parser.add_argument("--data-dir", type=Path, required=True) parser.add_argument("--target-key", required=True) parser.add_argument("--target-name", required=True) parser.add_argument("--seed", type=int, default=42) parser.add_argument("--output", type=Path, required=True) args = parser.parse_args() rows = read_jsonl(args.data_dir / "sample.jsonl") targets = np.asarray([row[args.target_key] for row in rows], dtype=np.float64) ligand, protein, ligand_names, protein_names = build_features(rows) combined = np.concatenate([protein, ligand], axis=1) feature_sets = { "ligand_morgan_descriptors_lightgbm": (ligand, ligand_names), "protein_aac_dipeptide_lightgbm": (protein, protein_names), "combined_morgan_protein_lightgbm": ( combined, protein_names + ligand_names, ), } report = { "sample_rows": len(rows), "target": args.target_name, "seed": args.seed, "packages": { package: importlib.metadata.version(package) for package in ("lightgbm", "numpy", "rdkit") }, "feature_dimensions": { "ligand": int(ligand.shape[1]), "protein": int(protein.shape[1]), "combined": int(combined.shape[1]), }, "splits": {}, } pair_ids = [row["pair_id"] for row in rows] for manifest_path in sorted(args.data_dir.glob("split-*.jsonl")): manifest = read_manifest(manifest_path) split_indices = { split: np.asarray( [ index for index, pair_id in enumerate(pair_ids) if manifest[pair_id] == split ] ) for split in ("train", "validation", "test") } mean = float(targets[split_indices["train"]].mean()) report["splits"][manifest_path.stem.removeprefix("split-")] = { "rows": { split: int(len(indices)) for split, indices in split_indices.items() }, "mean_baseline": { "prediction": mean, "validation": regression_metrics( targets[split_indices["validation"]], np.full(len(split_indices["validation"]), mean), ), "test": regression_metrics( targets[split_indices["test"]], np.full(len(split_indices["test"]), mean), ), }, "models": [ fit_model( name, features, feature_names, targets, split_indices, args.seed, ) for name, (features, feature_names) in feature_sets.items() ], } args.output.parent.mkdir(parents=True, exist_ok=True) args.output.write_text(json.dumps(report, indent=2) + "\n") print(json.dumps(report, indent=2)) if __name__ == "__main__": main()