herg-best-deployment / predict_herg.py
Delower's picture
Upload folder using huggingface_hub
45a72ab verified
Raw History Blame Contribute Delete
4.71 kB
"""Inference for Delower/herg-best-deployment (DEPLOYMENT REFIT).
Predicts hERG blocker probability (10 uM, classification winner) and pIC50
(regression winner) from SMILES. Feature stack: Morgan ECFP4 bits+counts,
RDKit 2D descriptors + QED + hERG-targeted physchem, ChemBERTa-77M pretrained
embeddings (mean-pooled; downloads seyonec/ChemBERTa-zinc-base-v1 on first use).
CDK/PaDEL descriptors are NOT used: a time-boxed PaDEL attempt stalled and the
CDK slot was substituted by the RDKit 2D descriptor block (see FEATURE_NOTES.md).
Requires: rdkit, numpy, scikit-learn, xgboost (if a tree is in a winner),
tensorflow (if the LTN is in a winner), transformers + torch (embeddings).
Usage: python predict_herg.py "CCOc1ccc..." ["SMILES2" ...]
"""
import sys, os, json, pickle
import numpy as np
HERE = os.path.dirname(os.path.abspath(__file__))
sys.path.insert(0, HERE)
import feature_extraction as FE
from feature_extraction import featurize_smiles
CFG = json.load(open(os.path.join(HERE, "config.json")))
BLOCKS = CFG["blocks"]
class ContPrep:
def __init__(self, s):
self.keep_ = np.array(s["keep"]); self.med_ = np.array(s["med"])
self.mu_ = np.array(s["mu"]); self.sd_ = np.array(s["sd"]); self.log1p = s["log1p"]
def transform(self, X):
X = np.where(np.isfinite(X), X, np.nan)
if self.log1p:
X = np.log1p(np.clip(X, 0, None))
X = X[:, self.keep_]
X = np.where(np.isnan(X), self.med_, X)
return ((X - self.mu_) / self.sd_).astype(np.float32)
_CB = {}
def chemberta_embed(smiles):
if "model" not in _CB:
import torch
from transformers import AutoModel, AutoTokenizer
_CB["tok"] = AutoTokenizer.from_pretrained("seyonec/ChemBERTa-zinc-base-v1")
_CB["model"] = AutoModel.from_pretrained("seyonec/ChemBERTa-zinc-base-v1")
_CB["model"].eval()
_CB["torch"] = torch
torch = _CB["torch"]
enc = _CB["tok"](smiles, padding=True, truncation=True, max_length=160, return_tensors="pt")
with torch.no_grad():
h = _CB["model"](**enc).last_hidden_state
mask = enc["attention_mask"].unsqueeze(-1).float()
return ((h * mask).sum(1) / mask.sum(1).clamp(min=1.0)).numpy().astype(np.float32)
def featurize(smiles_list):
raw = {b: [] for b in ["morgan", "morgan_counts", "desc", "physchem_extra", "herg"]}
for smi in smiles_list:
_, bl = featurize_smiles(smi)
assert bl is not None, f"unparseable SMILES: {smi}"
for b in raw:
raw[b].append(np.asarray(bl[b], dtype=np.float32))
raw = {b: np.vstack(v) for b, v in raw.items()}
raw["chemberta"] = chemberta_embed(smiles_list)
return raw
def assemble(raw, prep_states):
preps = {b: ContPrep(s) for b, s in prep_states.items()}
parts = []
for b in BLOCKS:
X = np.asarray(raw[b], dtype=np.float32)
if b in preps:
X = preps[b].transform(X)
parts.append(np.asarray(X, dtype=np.float32))
return np.hstack(parts)
def predict(smiles_list):
raw = featurize(smiles_list)
out = {}
for task in ("cls", "reg"):
entry = CFG["tasks"][task]
cand = entry["winner"]
preds = {}
if cand in ("tree", "ensemble"):
with open(os.path.join(HERE, f"tree_{task}.pkl"), "rb") as fh:
bundle = pickle.load(fh)
X = assemble(raw, bundle["prep_states"])
mdl = bundle["model"]
if task == "cls":
preds["tree"] = mdl.predict_proba(X)[:, 1]
elif mdl.__class__.__name__ == "Booster":
import xgboost as xgb
preds["tree"] = mdl.predict(xgb.DMatrix(X))
else:
preds["tree"] = mdl.predict(X)
if cand in ("ltn", "ensemble"):
import tensorflow as tf
meta = json.load(open(os.path.join(HERE, f"ltn_{task}_preps.json")))
X = assemble(raw, meta["prep_states"])
model = tf.keras.models.load_model(os.path.join(HERE, f"ltn_{task}.keras"))
if task == "cls":
preds["ltn"] = tf.nn.softmax(model(X, training=False), axis=1).numpy()[:, 1]
else:
preds["ltn"] = model(X, training=False).numpy()[:, 0] * meta["target_sd"] + meta["target_mu"]
if cand == "ensemble":
w = entry["ensemble_weight_on_tree"]
out[task] = w * preds["tree"] + (1 - w) * preds["ltn"]
else:
out[task] = preds[cand]
return out
if __name__ == "__main__":
smis = sys.argv[1:]
res = predict(smis)
for i, s in enumerate(smis):
print(f"{s}\tprob_blocker={res['cls'][i]:.4f}\tpred_pIC50={res['reg'][i]:.3f}")