Back up for app.py

app2.py

@@ -0,0 +1,142 @@
+import gradio as gr
+import joblib
+from huggingface_hub import hf_hub_download
+import pandas as pd
+import numpy as np
+from collections import Counter
+
+# ➕ ADDED: placeholders (instead of loading at startup)
+model_dict = None
+feature_columns = None
+model_package = None
+
+# ❌ REMOVED: direct model loading at startup
+# repo_id = "Ym420/Peptide-Function"
+# model_filename = "xgb_multilabel_model_full.pkl"
+# model_path = hf_hub_download(repo_id=repo_id, filename=model_filename)
+# model_package = joblib.load(model_path)
+# model_dict = model_package['model']
+# feature_columns = model_package['feature_columns']
+
+# ➕ ADDED: lazy loader function
+def init_model():
+    global model_dict, feature_columns, model_package
+    
+    if model_dict is None:
+        repo_id = "Ym420/Peptide-Function"
+        model_filename = "xgb_multilabel_model_full.pkl"
+
+        model_path = hf_hub_download(repo_id=repo_id, filename=model_filename)
+        model_package = joblib.load(model_path)
+
+        model_dict = model_package['model']
+        feature_columns = model_package['feature_columns']
+
+        # 🔁 MOVED: metadata loading (was global before)
+        global aa_list, dipeptides, hydrophobicity_scale, eisenberg_scale
+        global aa_mass, aa_charge, aa_boman, aa_flexibility
+        global aa_polarizability, aa_aliphatic, aa_deltaG, aa_pucker
+
+        aa_list = model_package.get('aa_list', [])
+        dipeptides = model_package.get('dipeptides', [])
+        hydrophobicity_scale = model_package.get('hydrophobicity_scale', {})
+        eisenberg_scale = model_package.get('eisenberg_scale', {})
+        aa_mass = model_package.get('aa_mass', {})
+        aa_charge = model_package.get('aa_charge', {})
+        aa_boman = model_package.get('aa_boman', {})
+        aa_flexibility = model_package.get('aa_flexibility', {})
+        aa_polarizability = model_package.get('aa_polarizability', {})
+        aa_aliphatic = model_package.get('aa_aliphatic', {})
+        aa_deltaG = model_package.get('aa_deltaG', {})
+        aa_pucker = model_package.get('aa_pucker', {})
+
+# --- Target cells ---
+TARGET_CELLS = ["Gram+", "Fungus", "Mammalian Cell", "Cancer", "Gram-"]
+
+# --- Feature extraction ---
+def extract_features_app(seq: str) -> pd.DataFrame:
+    seq = seq.upper()
+    
+    count = Counter([seq[i:i+2] for i in range(len(seq)-1)])
+    total = max(len(seq)-1, 1)
+    dipep_features = [count.get(dp, 0) / total for dp in dipeptides]
+
+    def g(aa, table): return table.get(aa, 0)
+    def h(dp, table): return (g(dp[0], table) + g(dp[1], table)) / 2.0
+
+    dipeptides_seq = [seq[i:i+2] for i in range(len(seq)-1)]
+    
+    if len(seq) < 2:
+        physchem_features = [0]*13
+    else:
+        mw = np.mean([h(dp, aa_mass) for dp in dipeptides_seq])
+        charge = np.mean([h(dp, aa_charge) for dp in dipeptides_seq])
+        hydro = np.mean([h(dp, hydrophobicity_scale) for dp in dipeptides_seq])
+        aromatic = np.mean([(dp[0] in 'FWY') + (dp[1] in 'FWY') for dp in dipeptides_seq]) / 2.0
+        pI = np.mean([h(dp, {aa: 7 + (int(aa in 'KRH') - int(aa in 'DE')) for aa in aa_list}) for dp in dipeptides_seq])
+        instability = np.mean([((dp[0] in 'DEKR') + (dp[1] in 'DEKR')) / 2.0 for dp in dipeptides_seq])
+        hydro_moment = np.sqrt(np.mean([(h(dp, eisenberg_scale))**2 for dp in dipeptides_seq]))
+        aliphatic = np.mean([h(dp, aa_aliphatic) for dp in dipeptides_seq])
+        boman = np.mean([h(dp, aa_boman) for dp in dipeptides_seq])
+        flexibility = np.mean([h(dp, aa_flexibility) for dp in dipeptides_seq])
+        polarizability = np.mean([h(dp, aa_polarizability) for dp in dipeptides_seq])
+        deltag = np.mean([h(dp, aa_deltaG) for dp in dipeptides_seq])
+        pucker = np.mean([h(dp, aa_pucker) for dp in dipeptides_seq])
+
+        physchem_features = [mw, charge, hydro, aromatic, pI, instability,
+                             hydro_moment, aliphatic, boman, flexibility, polarizability, deltag, pucker]
+    
+    features = dipep_features + physchem_features
+    
+    df = pd.DataFrame([features], columns=feature_columns)
+    df = df.astype('float32')
+    return df
+
+# --- Prediction function ---
+def predict_peptide(sequence: str):
+    init_model()   # ➕ ADDED: ensures model loads only when needed
+
+    seq = "".join(sequence.split()).upper()
+    if not seq:
+        return []
+
+    X = extract_features_app(seq)
+    
+    table = []
+    for target in TARGET_CELLS:
+        clf = model_dict.get(target)
+        if clf is not None:
+            prob = clf.predict_proba(X)[0][1]
+            table.append([target, round(float(prob), 4)])
+        else:
+            table.append([target, None])
+
+    return table
+
+# --- Gradio Interface ---
+custom_css = """
+footer, .footer {display:none !important;}
+"""
+
+with gr.Blocks(css=custom_css, theme="default") as demo:
+    gr.Markdown("## AMP Spectrum")
+    
+    seq_input = gr.Textbox(label="Enter Peptide Sequence")
+    
+    with gr.Row():
+        predict_btn = gr.Button("Predict", variant="primary")
+        clear_btn = gr.Button("Clear")
+    
+    table_output = gr.Dataframe(
+        headers=["Target", "Confidence"],
+        datatype=["str","number"],
+        interactive=False
+    )
+    
+    predict_btn.click(fn=predict_peptide, inputs=seq_input, outputs=table_output)
+    clear_btn.click(fn=lambda: ("", []), outputs=[seq_input, table_output])
+    
+    gr.api(predict_peptide, api_name="predict_peptide")
+
+if __name__ == "__main__": 
+    demo.launch(show_error=True, ssr_mode=False)   # ✅ CHANGED: disable SSR