updates

app.py

@@ -1,29 +1,31 @@
 import gradio as gr
 import torch
-import torch.nn as nn
-from transformers import PreTrainedModel, PretrainedConfig
-from tape import ProteinBertForSequenceClassification, TAPETokenizer
+import json
 import re
+from huggingface_hub import hf_hub_download
+from tape import ProteinBertForSequenceClassification, TAPETokenizer
 
 WHITESPACE_RE = re.compile(r"\s+")
 
 def sanitize(s):
     return WHITESPACE_RE.sub("", str(s).upper())
 
-# Load model directly (avoids trust_remote_code complexity in Spaces)
-# ckpt = torch.load("kinbert_v2_long.pt", map_location="cpu")
-# OR load from your hub repo:
-from huggingface_hub import hf_hub_download
-ckpt_path = hf_hub_download("steveyu323/kinbert_v2_long", "checkpoints/best.pt")
-ckpt = torch.load(ckpt_path, map_location="cpu")
+# Load config
+config_path = hf_hub_download("steveyu323/kinbert_v2_long", "config.json")
+with open(config_path) as f:
+    config_dict = json.load(f)
+
+THRESHOLD = float(config_dict.get("threshold", 0.5))
+MAX_LEN = int(config_dict.get("max_len", 1024))
 
+# Load model
+model_path = hf_hub_download("steveyu323/kinbert_v2_long", "pytorch_model.bin")
 model = ProteinBertForSequenceClassification.from_pretrained("bert-base", num_labels=2)
-model.load_state_dict(ckpt["state_dict"])
+state_dict = torch.load(model_path, map_location="cpu")
+model.load_state_dict(state_dict)
 model.eval()
 
 tokenizer = TAPETokenizer(vocab="iupac")
-THRESHOLD = float(ckpt["threshold"])
-MAX_LEN = 1024
 
 def predict(kinase_seq, substrate_seq):
     kinase_seq = sanitize(kinase_seq)
@@ -60,9 +62,6 @@ demo = gr.Interface(
     ],
     title="KinBERT — Kinase–Substrate Interaction Classifier",
     description="Predicts whether a kinase will phosphorylate a given substrate sequence.",
-    examples=[
-        ["MGSSHHHHHHSSGENLYFQGH", "ARTKQTARKSTGGKAPRKQL"],
-    ],
 )
 
 demo.launch()