Update app.py

app.py

@@ -11,12 +11,6 @@ model_filename = "xgb_multilabel_model_full_extendedFuture.pkl"
 
 model_path = hf_hub_download(repo_id=repo_id, filename=model_filename)
 model_package = joblib.load(model_path)
-
-# --- Debug: Check what we loaded ---
-print("Loaded model_package type:", type(model_package))
-print("model_package keys:", list(model_package.keys()))
-print("Type of model:", type(model_package['model']))
-
 model = model_package['model']
 feature_columns = model_package['feature_columns']
 
@@ -24,14 +18,12 @@ feature_columns = model_package['feature_columns']
 aa_list = model_package['aa_list']
 dipeptides = model_package['dipeptides']
 hydrophobicity_scale = model_package['hydrophobicity_scale']
-eisenberg_scale = model_package['eisenberg_scale']
 aa_mass = model_package['aa_mass']
 aa_charge = model_package['aa_charge']
 aa_boman = model_package['aa_boman']
 aa_flexibility = model_package['aa_flexibility']
 aa_polarizability = model_package['aa_polarizability']
 aa_aliphatic = model_package['aa_aliphatic']
-aa_deltaG = model_package['aa_deltaG']
 
 # --- Target cells ---
 TARGET_CELLS = ["Gram+", "Fungus", "Mammalian Cell", "Cancer", "Gram-"]
@@ -40,19 +32,19 @@ TARGET_CELLS = ["Gram+", "Fungus", "Mammalian Cell", "Cancer", "Gram-"]
 def extract_features_app(seq: str) -> pd.DataFrame:
     seq = seq.upper()
     
-    # 1. Dipeptide composition
+    # --- 1. Dipeptide composition ---
     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]
 
-    # 2. Physicochemical features
+    # --- 2. Physicochemical features ---
     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]*12
+        physchem_features = [0]*11
     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])
@@ -60,15 +52,14 @@ def extract_features_app(seq: str) -> pd.DataFrame:
         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]))
+        hydro_moment = np.sqrt(np.mean([(h(dp, hydrophobicity_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])
-        
+
         physchem_features = [mw, charge, hydro, aromatic, pI, instability,
-                             hydro_moment, aliphatic, boman, flexibility, polarizability, deltag]
+                             hydro_moment, aliphatic, boman, flexibility, polarizability]
     
     features = dipep_features + physchem_features
     
@@ -83,20 +74,18 @@ def predict_peptide(sequence: str):
         return []
 
     X = extract_features_app(seq)
-
-    # --- Handle model being a list of estimators ---
-    if isinstance(model, list):
-        probs_list = [est.predict_proba(X) for est in model]
-    else:
-        probs_list = [model.predict_proba(X)]  # single model
+    
+    #probs_list = model.predict_proba(X)  # list of arrays per target
+    # --- probs_list: list of arrays from each estimator ---
+    probs_list = [est.predict_proba(X) for est in model]  # model is a list
 
     table = []
     for i, target in enumerate(TARGET_CELLS):
         prob = float(probs_list[i][0][1])
         table.append([target, round(prob, 4)])
-    
     return table
 
+
 # --- Gradio Interface ---
 custom_css = """
 footer, .footer {display:none !important;}
@@ -120,11 +109,11 @@ with gr.Blocks(css=custom_css, theme="default") as demo:
     predict_btn.click(fn=predict_peptide, inputs=seq_input, outputs=table_output)
     clear_btn.click(fn=lambda: ("", []), outputs=[seq_input, table_output])
     
-    # Optional API endpoint for iOS app
-    # Note: use only if Gradio version supports `api`
-    # gr.api(predict_peptide, api_name="predict_peptide")
+    # API endpoint for iOS app
+    gr.api(predict_peptide, api_name="predict_peptide")
+
+#if __name__ == "__main__": 
+#    demo.launch()
 
 if __name__ == "__main__": 
     demo.launch(show_error=True)
-
-