update taxonomy to 2x5 (DesignApproach x MolecularSubject), fix diversity formula, real scores

app.py

@@ -28,42 +28,30 @@ ADMIN_PASSWORD = os.environ.get("BDB_ADMIN_PASSWORD", "")
 # ═══════════════════════════════════════════════════════════════════
 
 PAPER_URL = "#"
-GITHUB_URL = "https://github.com/biodesignbench/biodesignbench"
-HF_URL = "https://huggingface.co/spaces/biodesignbench/leaderboard"
+GITHUB_URL = "https://github.com/RomeroLab/BioDesignBench"
+HF_URL = "https://huggingface.co/spaces/RomeroLab-Duke/BioDesignBench-Leaderboard"
 
 
 # ═══════════════════════════════════════════════════════════════════
 #  Taxonomy & scoring constants
 # ═══════════════════════════════════════════════════════════════════
 
-TASK_TYPES = [
-    "de_novo_binder",
-    "sequence_optimization",
-    "de_novo_backbone",
-    "complex_engineering",
-    "conformational_design",
-]
-TASK_TYPE_LABELS = {
-    "de_novo_binder": "De Novo Binder",
-    "sequence_optimization": "Seq Optimization",
-    "de_novo_backbone": "De Novo Backbone",
-    "complex_engineering": "Complex Eng.",
-    "conformational_design": "Conformational",
+DESIGN_APPROACHES = ["de_novo", "redesign"]
+APPROACH_LABELS = {
+    "de_novo": "De Novo",
+    "redesign": "Redesign",
 }
-BIO_CONTEXTS = ["ab", "enz", "sig", "str", "flu"]
-BIO_CONTEXT_LABELS = {
-    "ab": "Antibody",
-    "enz": "Enzyme",
-    "sig": "Signaling",
-    "str": "Structural",
-    "flu": "Fluorescent",
+MOLECULAR_SUBJECTS = ["antibody", "enzyme", "binder", "scaffold", "fluorescent_protein"]
+SUBJECT_LABELS = {
+    "antibody": "Antibody",
+    "enzyme": "Enzyme",
+    "binder": "Binder",
+    "scaffold": "Scaffold",
+    "fluorescent_protein": "Fluorescent Protein",
 }
 VALID_CELLS = {
-    "de_novo_binder": {"ab", "enz", "sig"},
-    "sequence_optimization": {"ab", "enz", "sig", "str", "flu"},
-    "de_novo_backbone": {"str"},
-    "complex_engineering": {"enz", "sig", "str"},
-    "conformational_design": {"enz", "sig", "str", "flu"},
+    "de_novo": {"antibody", "enzyme", "binder", "scaffold", "fluorescent_protein"},
+    "redesign": {"antibody", "enzyme", "scaffold", "fluorescent_protein"},
 }
 COMPONENTS = [
     "approach",
@@ -415,7 +403,7 @@ def build_leaderboard_table(
 
 
 def build_heatmap(entry: dict) -> str:
-    """HTML heatmap table for one agent across 17 taxonomy cells."""
+    """HTML heatmap table for one agent across 2×5 taxonomy cells."""
     ts = entry.get("taxonomy_scores", {})
     TH = (
         "background:#0f172a;color:white;padding:0.6rem 0.8rem;"
@@ -427,15 +415,15 @@ def build_heatmap(entry: dict) -> str:
     )
 
     rows = []
-    for tt in TASK_TYPES:
+    for ap in DESIGN_APPROACHES:
         cells = [
             f'<td style="{TD};text-align:left;font-weight:600;'
-            f'background:#f8fafc">{TASK_TYPE_LABELS[tt]}</td>'
+            f'background:#f8fafc">{APPROACH_LABELS[ap]}</td>'
         ]
         vals = []
-        for bc in BIO_CONTEXTS:
-            if bc in VALID_CELLS[tt]:
-                val = ts.get(tt, {}).get(bc)
+        for subj in MOLECULAR_SUBJECTS:
+            if subj in VALID_CELLS[ap]:
+                val = ts.get(ap, {}).get(subj)
                 bg = _heat_color(val)
                 text = f"{val:.0f}" if val is not None else "\u2014"
                 cells.append(f'<td style="{TD};background:{bg}">{text}</td>')
@@ -454,9 +442,9 @@ def build_heatmap(entry: dict) -> str:
         )
         rows.append(f'<tr>{"".join(cells)}</tr>')
 
-    bc_headers = "".join(
-        f'<th style="{TH}">{BIO_CONTEXT_LABELS[bc]}</th>'
-        for bc in BIO_CONTEXTS
+    subj_headers = "".join(
+        f'<th style="{TH}">{SUBJECT_LABELS[s]}</th>'
+        for s in MOLECULAR_SUBJECTS
     )
 
     return f"""
@@ -464,8 +452,8 @@ def build_heatmap(entry: dict) -> str:
                   border-radius:10px;overflow:hidden;
                   box-shadow:0 1px 3px rgba(0,0,0,0.08)">
       <thead><tr>
-        <th style="{TH};text-align:left">Task Type</th>
-        {bc_headers}
+        <th style="{TH};text-align:left">Approach</th>
+        {subj_headers}
         <th style="{TH}">Avg</th>
       </tr></thead>
       <tbody>{''.join(rows)}</tbody>
@@ -586,8 +574,8 @@ def build_about() -> str:
           </div>
           <div {stat_box}>
             <div style="font-size:1.8rem;font-weight:800;color:#0f172a">
-              17</div>
-            <div style="font-size:0.78rem;color:#64748b">taxonomy cells</div>
+              2×5</div>
+            <div style="font-size:0.78rem;color:#64748b">taxonomy matrix</div>
           </div>
           <div {stat_box}>
             <div style="font-size:1.8rem;font-weight:800;color:#0f172a">
@@ -679,8 +667,8 @@ Response:
           <strong>Novelty (5 pts)</strong> &mdash; sequence identity to
           reference (lower identity = more novel = higher score)</p>
         <p {p}>
-          <strong>Diversity (10 pts)</strong> &mdash; number and pairwise
-          diversity of generated designs</p>
+          <strong>Diversity (10 pts)</strong> &mdash; 65% pairwise sequence
+          diversity + 35% positional entropy across designs</p>
       </div>
 
       <div {card}>
@@ -704,32 +692,36 @@ Response:
 
 
 def chart_taxonomy_bar(entry: dict) -> go.Figure:
-    """Bar chart of average score per task type for one agent."""
+    """Grouped bar chart of scores by approach × subject for one agent."""
     ts = entry.get("taxonomy_scores", {})
-    avgs = []
-    for tt in TASK_TYPES:
-        vals = [v for v in ts.get(tt, {}).values() if v is not None]
-        avgs.append(sum(vals) / len(vals) if vals else 0)
+    subjects = MOLECULAR_SUBJECTS
+    colors = {"de_novo": "rgba(49,130,206,0.7)", "redesign": "rgba(237,137,54,0.7)"}
 
-    fig = go.Figure(
-        go.Bar(
-            x=[TASK_TYPE_LABELS[t] for t in TASK_TYPES],
-            y=avgs,
-            marker_color="rgba(49,130,206,0.7)",
-            marker_line_width=0,
-            text=[f"{v:.1f}" for v in avgs],
+    fig = go.Figure()
+    for ap in DESIGN_APPROACHES:
+        vals = []
+        for s in subjects:
+            v = ts.get(ap, {}).get(s)
+            vals.append(v if v is not None else 0)
+        fig.add_trace(go.Bar(
+            name=APPROACH_LABELS[ap],
+            x=[SUBJECT_LABELS[s] for s in subjects],
+            y=vals,
+            marker_color=colors[ap],
+            text=[f"{v:.0f}" if v else "" for v in vals],
             textposition="auto",
-        )
-    )
+        ))
+
     mode = entry.get("mode") or "\u2014"
     fig.update_layout(
         **_base_layout(
             title=dict(
-                text=f"{entry['agent_name']} ({mode}) \u2014 Score by Task Type",
+                text=f"{entry['agent_name']} ({mode}) \u2014 Score by Approach \u00d7 Subject",
                 font_size=14,
             ),
             yaxis=dict(range=[0, 100], title="Average Score"),
             xaxis=dict(title=""),
+            barmode="group",
             height=300,
         )
     )

leaderboard_data.json

@@ -18,29 +18,18 @@
         "diversity": 10.0
       },
       "taxonomy_scores": {
-        "de_novo_binder": {
-          "ab": 74.0,
-          "bnd": 82.0,
-          "scf": 92.0
-        },
-        "conformational_design": {
-          "enz": 92.0,
-          "fp": 96.0,
-          "scf": 81.0
-        },
-        "complex_engineering": {
-          "enz": 75.0,
-          "bnd": 84.0,
-          "scf": 78.0
-        },
-        "de_novo_backbone": {
-          "scf": 98.0
-        },
-        "sequence_optimization": {
-          "enz": 99.0,
-          "fp": 97.0,
-          "ab": 98.0,
-          "scf": 98.0
+        "redesign": {
+          "antibody": 78,
+          "enzyme": 96,
+          "fluorescent_protein": 98,
+          "scaffold": 86
+        },
+        "de_novo": {
+          "binder": 83,
+          "enzyme": 80,
+          "fluorescent_protein": 85,
+          "scaffold": 87,
+          "antibody": 74
         }
       },
       "tasks_completed": 76,
@@ -66,29 +55,18 @@
         "diversity": 2.6
       },
       "taxonomy_scores": {
-        "de_novo_binder": {
-          "ab": 57.0,
-          "bnd": 71.0,
-          "scf": 70.0
-        },
-        "conformational_design": {
-          "enz": 68.0,
-          "fp": 59.0,
-          "scf": 50.0
-        },
-        "complex_engineering": {
-          "enz": 40.0,
-          "bnd": 76.0,
-          "scf": 67.0
-        },
-        "de_novo_backbone": {
-          "scf": 84.0
-        },
-        "sequence_optimization": {
-          "enz": 48.0,
-          "fp": 51.0,
-          "ab": 65.0,
-          "scf": 54.0
+        "redesign": {
+          "antibody": 52,
+          "enzyme": 50,
+          "fluorescent_protein": 53,
+          "scaffold": 52
+        },
+        "de_novo": {
+          "binder": 74,
+          "enzyme": 46,
+          "fluorescent_protein": 61,
+          "scaffold": 68,
+          "antibody": 65
         }
       },
       "tasks_completed": 76,
@@ -114,29 +92,18 @@
         "diversity": 3.4
       },
       "taxonomy_scores": {
-        "de_novo_binder": {
-          "ab": 55.0,
-          "bnd": 63.0,
-          "scf": 56.0
-        },
-        "conformational_design": {
-          "enz": 48.0,
-          "fp": 56.0,
-          "scf": 54.0
-        },
-        "complex_engineering": {
-          "enz": 56.0,
-          "bnd": 66.0,
-          "scf": 60.0
-        },
-        "de_novo_backbone": {
-          "scf": 37.0
-        },
-        "sequence_optimization": {
-          "enz": 61.0,
-          "fp": 66.0,
-          "ab": 83.0,
-          "scf": 62.0
+        "redesign": {
+          "antibody": 57,
+          "enzyme": 58,
+          "fluorescent_protein": 62,
+          "scaffold": 57
+        },
+        "de_novo": {
+          "binder": 64,
+          "enzyme": 56,
+          "fluorescent_protein": 61,
+          "scaffold": 51,
+          "antibody": 60
         }
       },
       "tasks_completed": 76,
@@ -162,29 +129,18 @@
         "diversity": 2.0
       },
       "taxonomy_scores": {
-        "de_novo_binder": {
-          "ab": 45.0,
-          "bnd": 56.0,
-          "scf": 67.0
-        },
-        "conformational_design": {
-          "enz": 38.0,
-          "fp": 27.0,
-          "scf": 35.0
-        },
-        "complex_engineering": {
-          "enz": 57.0,
-          "bnd": 64.0,
-          "scf": 64.0
-        },
-        "de_novo_backbone": {
-          "scf": 11.0
-        },
-        "sequence_optimization": {
-          "enz": 70.0,
-          "fp": 67.0,
-          "ab": 57.0,
-          "scf": 75.0
+        "redesign": {
+          "antibody": 41,
+          "enzyme": 69,
+          "fluorescent_protein": 52,
+          "scaffold": 66
+        },
+        "de_novo": {
+          "binder": 59,
+          "enzyme": 28,
+          "fluorescent_protein": 61,
+          "scaffold": 40,
+          "antibody": 52
         }
       },
       "tasks_completed": 76,
@@ -210,29 +166,18 @@
         "diversity": 3.0
       },
       "taxonomy_scores": {
-        "de_novo_binder": {
-          "ab": 46.0,
-          "bnd": 53.0,
-          "scf": 47.0
-        },
-        "conformational_design": {
-          "enz": 44.0,
-          "fp": 62.0,
-          "scf": 38.0
-        },
-        "complex_engineering": {
-          "enz": 33.0,
-          "bnd": 56.0,
-          "scf": 52.0
-        },
-        "de_novo_backbone": {
-          "scf": 54.0
-        },
-        "sequence_optimization": {
-          "enz": 55.0,
-          "fp": 41.0,
-          "ab": 69.0,
-          "scf": 72.0
+        "redesign": {
+          "antibody": 51,
+          "enzyme": 52,
+          "fluorescent_protein": 50,
+          "scaffold": 60
+        },
+        "de_novo": {
+          "binder": 54,
+          "enzyme": 40,
+          "fluorescent_protein": 40,
+          "scaffold": 48,
+          "antibody": 46
         }
       },
       "tasks_completed": 76,
@@ -258,29 +203,18 @@
         "diversity": 3.1
       },
       "taxonomy_scores": {
-        "de_novo_binder": {
-          "ab": 43.0,
-          "bnd": 55.0,
-          "scf": 54.0
-        },
-        "conformational_design": {
-          "enz": 32.0,
-          "fp": 40.0,
-          "scf": 39.0
-        },
-        "complex_engineering": {
-          "enz": 43.0,
-          "bnd": 57.0,
-          "scf": 53.0
-        },
-        "de_novo_backbone": {
-          "scf": 45.0
-        },
-        "sequence_optimization": {
-          "enz": 48.0,
-          "fp": 52.0,
-          "ab": 71.0,
-          "scf": 62.0
+        "redesign": {
+          "antibody": 42,
+          "enzyme": 46,
+          "fluorescent_protein": 46,
+          "scaffold": 56
+        },
+        "de_novo": {
+          "binder": 56,
+          "enzyme": 40,
+          "fluorescent_protein": 55,
+          "scaffold": 47,
+          "antibody": 52
         }
       },
       "tasks_completed": 76,
@@ -306,29 +240,18 @@
         "diversity": 2.2
       },
       "taxonomy_scores": {
-        "de_novo_binder": {
-          "ab": 42.0,
-          "bnd": 53.0,
-          "scf": 38.0
-        },
-        "conformational_design": {
-          "enz": 42.0,
-          "fp": 47.0,
-          "scf": 35.0
-        },
-        "complex_engineering": {
-          "enz": 48.0,
-          "bnd": 66.0,
-          "scf": 53.0
-        },
-        "de_novo_backbone": {
-          "scf": 33.0
-        },
-        "sequence_optimization": {
-          "enz": 48.0,
-          "fp": 60.0,
-          "ab": 67.0,
-          "scf": 18.0
+        "redesign": {
+          "antibody": 42,
+          "enzyme": 47,
+          "fluorescent_protein": 56,
+          "scaffold": 32
+        },
+        "de_novo": {
+          "binder": 59,
+          "enzyme": 48,
+          "fluorescent_protein": 45,
+          "scaffold": 39,
+          "antibody": 48
         }
       },
       "tasks_completed": 76,
@@ -354,29 +277,18 @@
         "diversity": 1.7
       },
       "taxonomy_scores": {
-        "de_novo_binder": {
-          "ab": 32.0,
-          "bnd": 44.0,
-          "scf": 36.0
-        },
-        "conformational_design": {
-          "enz": 17.0,
-          "fp": 56.0,
-          "scf": 41.0
-        },
-        "complex_engineering": {
-          "enz": 44.0,
-          "bnd": 55.0,
-          "scf": 37.0
-        },
-        "de_novo_backbone": {
-          "scf": 44.0
-        },
-        "sequence_optimization": {
-          "enz": 40.0,
-          "fp": 51.0,
-          "ab": 58.0,
-          "scf": 20.0
+        "redesign": {
+          "antibody": 36,
+          "enzyme": 37,
+          "fluorescent_protein": 54,
+          "scaffold": 23
+        },
+        "de_novo": {
+          "binder": 49,
+          "enzyme": 38,
+          "fluorescent_protein": 41,
+          "scaffold": 41,
+          "antibody": 33
         }
       },
       "tasks_completed": 76,
@@ -402,29 +314,18 @@
         "diversity": 0.9
       },
       "taxonomy_scores": {
-        "de_novo_binder": {
-          "ab": 32.0,
-          "bnd": 41.0,
-          "scf": 45.0
-        },
-        "conformational_design": {
-          "enz": 22.0,
-          "fp": 55.0,
-          "scf": 40.0
-        },
-        "complex_engineering": {
-          "enz": 3.0,
-          "bnd": 49.0,
-          "scf": 26.0
-        },
-        "de_novo_backbone": {
-          "scf": 45.0
-        },
-        "sequence_optimization": {
-          "enz": 44.0,
-          "fp": 52.0,
-          "ab": 52.0,
-          "scf": 49.0
+        "redesign": {
+          "antibody": 30,
+          "enzyme": 36,
+          "fluorescent_protein": 54,
+          "scaffold": 41
+        },
+        "de_novo": {
+          "binder": 44,
+          "enzyme": 22,
+          "fluorescent_protein": 44,
+          "scaffold": 39,
+          "antibody": 40
         }
       },
       "tasks_completed": 76,
@@ -450,29 +351,18 @@
         "diversity": 1.5
       },
       "taxonomy_scores": {
-        "de_novo_binder": {
-          "ab": 22.0,
-          "bnd": 36.0,
-          "scf": 28.0
-        },
-        "conformational_design": {
-          "enz": 8.0,
-          "fp": 9.0,
-          "scf": 10.0
-        },
-        "complex_engineering": {
-          "enz": 12.0,
-          "bnd": 35.0,
-          "scf": 22.0
-        },
-        "de_novo_backbone": {
-          "scf": 21.0
-        },
-        "sequence_optimization": {
-          "enz": 33.0,
-          "fp": 36.0,
-          "ab": 53.0,
-          "scf": 22.0
+        "redesign": {
+          "antibody": 22,
+          "enzyme": 29,
+          "fluorescent_protein": 29,
+          "scaffold": 21
+        },
+        "de_novo": {
+          "binder": 36,
+          "enzyme": 8,
+          "fluorescent_protein": 0,
+          "scaffold": 19,
+          "antibody": 31
         }
       },
       "tasks_completed": 76,
@@ -498,29 +388,18 @@
         "diversity": 1.6
       },
       "taxonomy_scores": {
-        "de_novo_binder": {
-          "ab": 28.0,
-          "bnd": 35.0,
-          "scf": 20.0
-        },
-        "conformational_design": {
-          "enz": 16.0,
-          "fp": 22.0,
-          "scf": 6.0
-        },
-        "complex_engineering": {
-          "enz": 0.0,
-          "bnd": 32.0,
-          "scf": 27.0
-        },
-        "de_novo_backbone": {
-          "scf": 21.0
-        },
-        "sequence_optimization": {
-          "enz": 30.0,
-          "fp": 33.0,
-          "ab": 52.0,
-          "scf": 15.0
+        "redesign": {
+          "antibody": 31,
+          "enzyme": 26,
+          "fluorescent_protein": 32,
+          "scaffold": 14
+        },
+        "de_novo": {
+          "binder": 34,
+          "enzyme": 8,
+          "fluorescent_protein": 0,
+          "scaffold": 18,
+          "antibody": 30
         }
       },
       "tasks_completed": 76,