kcat-km-v3 / predict.py
da24b032's picture
Upload folder using huggingface_hub
bfb9f0f verified
Raw History Blame Contribute Delete
1.24 kB
import argparse, os, joblib, numpy as np, pandas as pd, torch
from features import *
torch.set_num_threads(2)
here = os.path.dirname(os.path.abspath(__file__))
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["sequence"] = df["sequence"].fillna("").astype(str)
df["smiles"] = df["smiles"].fillna("").astype(str)
ref = pd.read_parquet(os.path.join(here, "ref.parquet"))
z = np.load(os.path.join(here, "ref_emb.npz"), allow_pickle=True)
emb = {s: v for s, v in zip(z["seqs"], z["vecs"])}
mu = z["mu"]
emb.update(embed_unique(df["sequence"], os.path.join(here, "esm_local")))
X = np.hstack([base_X(df, emb), label_feats(ref, df, emb, mu)])
models = joblib.load(os.path.join(here, "models.pkl"))
preds = [np.mean([m.predict(X) for m in models[t]], axis=0) for t in range(2)]
out = pd.DataFrame({"id": df["id"],
"log10_kcat": np.nan_to_num(np.clip(preds[0], -1e5, 1e5)),
"log10_km": np.nan_to_num(np.clip(preds[1], -1e5, 1e5))})
os.makedirs(os.path.dirname(os.path.abspath(args.output)) or ".", exist_ok=True)
out.to_csv(args.output, index=False)