Update app.py

app.py

@@ -238,7 +238,7 @@ def generate_and_screen(num_to_gen, app_mode, toggle_view, motifs=[], limit_aro=
                 "SA Score": f"{get_status_icon(sa, T_SA, False)} {sa:.2f}",
                 "Confidence": f"{conf_pct:.0f}%",
                 "Classification": status,
-                "_s": s, "_t": t, "_status": "Excellent" if "Excellent" in status else "Review" if "Review" in status else "Bad"
+                "_s": s, "_t": t, "Degradability_raw": d, "_status": "Excellent" if "Excellent" in status else "Review" if "Review" in status else "Bad"
             })
             
     if len(candidates) == 0:
@@ -270,7 +270,7 @@ def generate_and_screen(num_to_gen, app_mode, toggle_view, motifs=[], limit_aro=
 
     output_path = tempfile.NamedTemporaryFile(delete=False, suffix=".csv").name
     df.to_csv(output_path, index=False)
-    return df.drop(columns=["_s", "_t", "_status"]), output_path, fig
+    return df, output_path, fig
 
 def calculate_weighted_rank(df, app_mode, w_s, w_t, w_d, w_sa): # Added 4 weight arguments
     if df is None or df.empty: return None, None
@@ -465,7 +465,7 @@ def check_constraints(mol, motifs, limit_aromatic, max_mw):
         "Cyclic-Aliphatic": "C1CCCCC1"
     }
     
-    for m in motifs:
+    for m in active_motifs:
         if m in pattern_map:
             p = Chem.MolFromSmarts(pattern_map[m])
             if not mol.HasSubstructMatch(p):
@@ -480,6 +480,49 @@ def check_constraints(mol, motifs, limit_aromatic, max_mw):
             
     return True
 
+def run_sensitivity_analysis(raw_df, t_s, t_t, t_d):
+    if raw_df is None or raw_df.empty:
+        return None, "No data to analyze", []
+
+    processed_df = raw_df.copy()
+    
+    # Re-classification logic based on NEW thresholds
+    def reclassify(row):
+        s, t, d = row["_s"], row["_t"], row["Degradability_raw"]
+        failed = []
+        if s < t_s: failed.append("Strength")
+        if t < t_t: failed.append("Tg")
+        if d < t_d: failed.append("Degradability")
+        
+        if not failed: return "Excellent ✅"
+        if len(failed) <= 2: return f"Review (Failed {', '.join(failed)}) ⚠️"
+        return "Bad ❌"
+
+    processed_df["Classification"] = processed_df.apply(reclassify, axis=1)
+    
+    # Calculate Market Readiness
+    total = len(processed_df)
+    passed = len(processed_df[processed_df["Classification"] == "Excellent ✅"])
+    pass_pct = (passed / total) * 100 if total > 0 else 0
+    
+    # Update icons in the visible columns for the user
+    def update_icons(row):
+        row["Strength (GPa)"] = f"{'🟢' if row['_s'] >= t_s else '🔴'} {row['_s']:.3f}"
+        row["Tg (°C)"] = f"{'🟢' if row['_t'] >= t_t else '🔴'} {row['_t']:.1f}"
+        row["Degradability"] = f"{'🟢' if row['Degradability_raw'] >= t_d else '🔴'} {row['Degradability_raw']:.2f}"
+        return row
+    
+    display_df = processed_df.apply(update_icons, axis=1)
+    
+    status_msg = f"**{pass_pct:.1f}%** of candidates ({passed}/{total}) meet these industrial benchmarks."
+    # Color-coded badge for Gradio AnnotatedText
+    badge_color = "green" if pass_pct > 25 else "orange" if pass_pct > 5 else "red"
+    annotated_data = [(f"{pass_pct:.0f}% Pass Rate", badge_color)]
+
+    # Drop hidden columns before returning to the UI
+    final_cols = [c for c in display_df.columns if not c.startswith('_') and c != "Degradability_raw"]
+    return display_df[final_cols], status_msg, annotated_data
+    
 def generate_exports(df):
     if df is None or df.empty:
         return [None] * 4
@@ -530,6 +573,17 @@ def generate_exports(df):
         
     pdf.output(pdf_path)
     return csv_path, json_path, smiles_path, pdf_path
+
+def on_refine_wrapper(seed_with_icon, num, mode, view, motifs, limit_aro, max_mw):
+    # 1. Call existing refine logic (returns 6 items)
+    df, fig, dropdown, state, img, bar = on_refine_start(seed_with_icon, num, mode, view, motifs, limit_aro, max_mw)
+    
+    # 2. Prepare the 2 extra items
+    init_msg = "Move sliders above to re-analyze refined batch."
+    init_anno = [("0% Pass Rate", "Awaiting Analysis")]
+    
+    # 3. Return all 8 items
+    return df, fig, dropdown, state, img, bar, init_msg, init_anno
     
 # --- 6. GRADIO INTERFACE ---
 with gr.Blocks(title="PolymerDesignAI") as demo:
@@ -613,7 +667,18 @@ with gr.Blocks(title="PolymerDesignAI") as demo:
                     label="Sort Candidates By",
                     interactive=True
                 )
-        
+            # --- NEW: BENCHMARK SENSITIVITY ANALYSIS ---
+        with gr.Accordion("📊 Benchmark Sensitivity Analysis (Industrial What-if)", open=False):
+            gr.Markdown("Adjust thresholds to dynamically re-classify candidates and see market readiness.")
+            with gr.Row():
+                threshold_s = gr.Slider(0, 0.2, value=0.08, step=0.005, label="Min Strength (GPa)")
+                threshold_t = gr.Slider(0, 300, value=150, step=5, label="Min Tg (°C)")
+                threshold_d = gr.Slider(0, 1.0, value=0.10, step=0.05, label="Min Degradability")
+            
+            with gr.Row():
+                pass_metric = gr.AnnotatedText(label="Market Readiness")
+                stats_box = gr.Markdown("### 📈 Impact Summary")
+        # --------------------------------------------
         results_df = gr.DataFrame(label="Candidate Table (Click headers to sort)")
         full_results_state = gr.State()
         
@@ -735,8 +800,20 @@ with gr.Blocks(title="PolymerDesignAI") as demo:
         def clean_and_explain(choice, prop):
             smiles = choice.split(" ")[1] if choice and " " in choice else choice
             return explain_polymer(smiles, prop)    
+
+        def on_gen_complete_wrapper(num, mode, view, motifs, limit_aro, max_mw, progress=gr.Progress()):
+            # 1. This function MUST return 6 items based on your code: 
+            # (df, fig, dropdown, state_df, img, bar)
+            df, fig, dropdown, state, img, bar = on_gen_complete(num, mode, view, motifs, limit_aro, max_mw, progress)
+            
+            # 2. Add the 2 sensitivity items
+            init_msg = "### 📈 Impact Summary\nMove sliders above to see analysis."
+            init_anno = [("0% Pass Rate", "Awaiting Analysis")]
             
-        run.click(fn=on_gen_complete, inputs=[num, app_mode, toggle_view, must_have, exclude_aromatic, max_mol_wt], outputs=[results_df, pareto_plot, selection_dropdown, full_results_state, explain_img, explain_bar])
+            # 3. Return 8 items
+            return df, fig, dropdown, state, img, bar, init_msg, init_anno
+            
+        run.click(fn=on_gen_complete_wrapper, inputs=[num, app_mode, toggle_view, must_have, exclude_aromatic, max_mol_wt], outputs=[results_df, pareto_plot, selection_dropdown, full_results_state, explain_img, explain_bar, stats_box, pass_metric])
 
         filter_btn_all.click(lambda x: filter_table(x, "All"), full_results_state, results_df)
         filter_btn_exc.click(lambda x: filter_table(x, "Excellent"), full_results_state, results_df)
@@ -764,10 +841,20 @@ with gr.Blocks(title="PolymerDesignAI") as demo:
         sort_dropdown.change(sort_table, [results_df, sort_dropdown], results_df)
         rank_btn.click(calculate_weighted_rank, [results_df, app_mode, w_strength, w_tg, w_degrad, w_sa], [results_df, download_csv])
         refine_btn.click(
-            on_refine_start, 
-            [selection_dropdown, num, app_mode, toggle_view, must_have, exclude_aromatic, max_mol_wt], 
-            [results_df, pareto_plot, selection_dropdown, full_results_state, explain_img, explain_bar]
+            fn=on_refine_wrapper,  # Points to the new 8-output wrapper
+            inputs=[selection_dropdown, num, app_mode, toggle_view, must_have, exclude_aromatic, max_mol_wt], 
+            outputs=[results_df, pareto_plot, selection_dropdown, full_results_state, explain_img, explain_bar, stats_box, pass_metric]
         )
+        
+        # Sensitivity Triggers
+        slider_inputs = [full_results_state, threshold_s, threshold_t, threshold_d]
+        slider_outputs = [results_df, stats_box, pass_metric]
+
+        threshold_s.change(fn=run_sensitivity_analysis, inputs=slider_inputs, outputs=slider_outputs)
+        threshold_t.change(fn=run_sensitivity_analysis, inputs=slider_inputs, outputs=slider_outputs)
+        threshold_d.change(fn=run_sensitivity_analysis, inputs=slider_inputs, outputs=slider_outputs)
+        
+            
         # Automatically update all download links whenever the results table changes
         results_df.change(
             fn=update_exports,