#!/usr/bin/env python3 """Standalone inference for the hERG Phase-5 XGBoost models (Delower/herg-xgboost). Takes SMILES, builds the exact Phase-5 feature blocks with feature_extraction.py, applies the fitted preprocessing stored inside each model pickle (fold-fitted ContPrep states: column keep-mask, median imputation, standardisation; log1p for count blocks), and predicts with the XGBoost model stored in the same pickle. Usage: python predict_herg.py --model models/ "CCOc1ccc..." [...] python predict_herg.py --model models/ --csv compounds.csv (CSV must have a 'smiles' column; output adds pred_pIC50 / prob_blocker) Classification pickles output blocker probability at the locked 10 uM cutoff (call = prob >= 0.5). Regression pickles output predicted pIC50 (derived 10 uM call = pIC50 >= 5.0). Dependencies: see requirements.txt (rdkit, xgboost, scikit-learn, numpy). """ import argparse, csv, json, pickle, sys import numpy as np from feature_extraction import featurize_smiles BLOCK_KIND = {"morgan": "bits", "maccs": "bits", "desc": "cont", "physchem_extra": "cont", "morgan_counts": "counts", "ecfp6": "bits", "fcfp4": "bits", "herg": "cont", "pharm": "counts", "cdk": "bits", "morgan1024": "bits", "morgan1024_counts": "counts"} def apply_prep(raw, state): """Replicates p5_common.ContPrep.transform from its stored state dict.""" X = np.asarray(raw, dtype=float).reshape(1, -1) X = np.where(np.isfinite(X), X, np.nan) if state["log1p"]: X = np.log1p(np.clip(X, 0, None)) X = X[:, np.asarray(state["keep"], dtype=bool)] med = np.asarray(state["med"], dtype=float) X = np.where(np.isnan(X), med, X) mu = np.asarray(state["mu"], dtype=float) sd = np.asarray(state["sd"], dtype=float) return ((X - mu) / sd).astype(np.float32) def design_row(blocks, combo, preps): parts = [] for b in combo: raw = np.asarray(blocks[b], dtype=np.float32) if b in preps: parts.append(apply_prep(raw, preps[b])) else: parts.append(raw.reshape(1, -1).astype(np.float32)) return np.hstack(parts) def load_bundle(path): with open(path, "rb") as fh: return pickle.load(fh) def predict(bundle, smiles_list): out = [] for smi in smiles_list: _, blocks = featurize_smiles(smi) if blocks is None: out.append(None) continue X = design_row(blocks, bundle["blocks"], bundle["preps"]) model = bundle["model"] if bundle["task"] == "cls": out.append(float(model.predict_proba(X)[0, 1])) else: out.append(float(model.predict(X)[0])) return out def main(): ap = argparse.ArgumentParser() ap.add_argument("--model", required=True, help="path to a model pickle from models/") ap.add_argument("--csv", help="input CSV with a 'smiles' column") ap.add_argument("--out", help="output CSV (default: stdout summary)") ap.add_argument("smiles", nargs="*", help="SMILES strings") args = ap.parse_args() bundle = load_bundle(args.model) rows = [] if args.csv: with open(args.csv) as fh: for r in csv.DictReader(fh): rows.append(r) smiles = [r["smiles"] for r in rows] else: smiles = args.smiles rows = [{"smiles": s} for s in smiles] if not smiles: print("no SMILES given", file=sys.stderr) return 2 preds = predict(bundle, smiles) col = "prob_blocker" if bundle["task"] == "cls" else "pred_pIC50" for r, p in zip(rows, preds): r[col] = "" if p is None else f"{p:.4f}" if bundle["task"] == "cls": r["call_10uM"] = "" if p is None else int(p >= 0.5) else: r["derived_call_10uM"] = "" if p is None else int(p >= 5.0) if args.out: with open(args.out, "w", newline="") as fh: w = csv.DictWriter(fh, fieldnames=list(rows[0].keys())) w.writeheader() w.writerows(rows) print(f"wrote {args.out} ({len(rows)} rows, model task={bundle['task']}, " f"protocol={bundle['protocol']})") else: for r in rows: print(json.dumps(r)) return 0 if __name__ == "__main__": sys.exit(main())