File size: 2,390 Bytes
b145940 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 | """Inference entry point: python /app/predict.py --input X.parquet --output Y.csv"""
import argparse
import json
import os
import time
import numpy as np
import pandas as pd
import features as F
HERE = os.path.dirname(os.path.abspath(__file__))
W = os.path.join(HERE, "weights")
N_THREADS = int(os.environ.get("NTHREADS", 2)) # the evaluator gives us 2 vCPUs
ESM_BUDGET_S = 480 # max 8 minutes for ESM, then fall back
def main():
t0 = time.time()
ap = argparse.ArgumentParser()
ap.add_argument("--input", required=True)
ap.add_argument("--output", required=True)
args = ap.parse_args()
df = pd.read_parquet(args.input).reset_index(drop=True)
df["smiles"] = df["smiles"].fillna("").astype(str)
df["sequence"] = df["sequence"].fillna("").astype(str)
meta = json.load(open(os.path.join(W, "meta.json")))
usmi = df["smiles"].unique().tolist()
useq = df["sequence"].unique().tolist()
smi_mat = F.smiles_features(usmi)
seq_mat = F.seq_features(useq)
print(f"[predict] features done {time.time() - t0:.0f}s", flush=True)
esm_mat = None
if meta["use_esm"]:
fb = np.load(os.path.join(W, "esm_mean.npy"))
esm_mat = F.esm_embed(useq, os.path.join(W, "esm"), fallback=fb,
budget_s=ESM_BUDGET_S, n_threads=N_THREADS)
print(f"[predict] esm done {time.time() - t0:.0f}s", flush=True)
stats = pd.read_parquet(os.path.join(W, "te_stats.parquet"))
te = F.te_apply(df["smiles"].values, stats)
X = F.assemble(df, usmi, smi_mat, useq, seq_mat, esm_mat, te)
import lightgbm as lgb
out = pd.DataFrame({"id": df["id"]})
for name, col, mean_key in [("kcat", "log10_kcat", "mean_kcat"), ("km", "log10_km", "mean_km")]:
preds = []
for s in range(meta["n_seeds"]):
b = lgb.Booster(model_file=os.path.join(W, f"{name}_{s}.txt"))
preds.append(b.predict(X, num_threads=N_THREADS))
p = np.mean(preds, axis=0)
p = np.nan_to_num(p, nan=meta[mean_key], posinf=meta[mean_key], neginf=meta[mean_key])
out[col] = np.clip(p, -50, 50)
os.makedirs(os.path.dirname(os.path.abspath(args.output)), exist_ok=True)
out.to_csv(args.output, index=False)
print(f"[predict] wrote {len(out)} rows in {time.time() - t0:.0f}s", flush=True)
if __name__ == "__main__":
main()
|