Upload app.py with huggingface_hub

app.py

@@ -0,0 +1,482 @@
+"""
+AntioxFP — GNN-Based Antioxidant Activity Predictor
+====================================================
+Predicts DPPH radical scavenging activity (pIC50) from SMILES strings
+using a 30-model AttentiveFP ensemble with GNNExplainer atom importance maps.
+
+Based on: "Graph Neural Network Models for Predicting the Antioxidant Activity
+of Chemical Compounds" (2025)
+"""
+
+import os
+import sys
+import warnings
+import io
+import math
+
+os.environ["KMP_DUPLICATE_LIB_OK"] = "TRUE"
+warnings.filterwarnings("ignore")
+
+import numpy as np
+import torch
+from torch_geometric.data import Data
+from torch_geometric.explain import Explainer, GNNExplainer
+from rdkit import Chem
+from rdkit.Chem import Descriptors
+from rdkit.Chem.Draw import rdMolDraw2D
+import matplotlib
+matplotlib.use("Agg")
+import matplotlib.pyplot as plt
+import matplotlib.cm as cm
+from matplotlib.colors import Normalize
+from PIL import Image
+import gradio as gr
+
+from models_arch import AttentiveFPModel
+
+# ── Constants ─────────────────────────────────────────────────────────────────
+MODEL_DIR = os.path.join(os.path.dirname(__file__), "models")
+DEVICE = torch.device("cpu")  # HF free CPU tier
+
+SEEDS = [42, 1, 100]
+N_FOLDS = 10
+HIDDEN = 200
+
+ATOM_TYPES  = ["C", "N", "O", "S", "F", "Cl", "Br", "I", "P", "other"]
+DEGREE_VALS = [0, 1, 2, 3, 4, 5]
+CHARGE_VALS = [-2, -1, 0, 1, 2]
+from rdkit.Chem import rdchem
+HYBRID_VALS = [
+    rdchem.HybridizationType.SP, rdchem.HybridizationType.SP2,
+    rdchem.HybridizationType.SP3, rdchem.HybridizationType.SP3D,
+    rdchem.HybridizationType.SP3D2,
+]
+BOND_TYPES = [
+    rdchem.BondType.SINGLE, rdchem.BondType.DOUBLE,
+    rdchem.BondType.TRIPLE, rdchem.BondType.AROMATIC,
+]
+
+EXAMPLE_SMILES = [
+    ["O=c1c(O)c(-c2ccc(O)c(O)c2)oc2cc(O)cc(O)c12", "Quercetin — high activity flavonol"],
+    ["OC(=O)/C=C/c1ccc(O)c(O)c1",                  "Caffeic acid — phenolic acid"],
+    ["Oc1ccc(/C=C/c2cc(O)cc(O)c2)cc1",             "Resveratrol — stilbene antioxidant"],
+    ["O=c1cc(-c2ccccc2)oc2cc(O)cc(O)c12",          "Chrysin — low activity (no B-ring OH)"],
+    ["O=c1c(O)c(-c2ccc(O)cc2)oc2cc(O)cc(O)c12",   "Kaempferol — moderate activity"],
+    ["CC(C)(C)c1cc(C(C)(C)C)cc(CC(=O)Nc2ccccc2)c1","BHA analogue — synthetic antioxidant"],
+]
+
+
+# ── Molecular graph builder ────────────────────────────────────────────────────
+def one_hot(val, choices):
+    vec = [0] * len(choices)
+    idx = choices.index(val) if val in choices else len(choices) - 1
+    vec[idx] = 1
+    return vec
+
+
+def atom_feat(atom):
+    sym = atom.GetSymbol()
+    return (
+        one_hot(sym if sym in ATOM_TYPES[:-1] else "other", ATOM_TYPES)
+        + one_hot(atom.GetDegree(), DEGREE_VALS)
+        + one_hot(atom.GetFormalCharge(), CHARGE_VALS)
+        + one_hot(atom.GetHybridization(), HYBRID_VALS)
+        + [int(atom.GetIsAromatic())]
+        + one_hot(atom.GetTotalNumHs(), [0, 1, 2, 3, 4])
+        + [int(atom.IsInRing())]
+        + one_hot(atom.GetTotalValence(), [0, 1, 2, 3, 4, 5, 6])
+    )
+
+
+def bond_feat(bond):
+    return (
+        one_hot(bond.GetBondType(), BOND_TYPES)
+        + [int(bond.GetIsConjugated()), int(bond.IsInRing())]
+    )
+
+
+def smiles_to_graph(smiles):
+    mol = Chem.MolFromSmiles(smiles)
+    if mol is None:
+        return None, None
+    x = torch.tensor([atom_feat(a) for a in mol.GetAtoms()], dtype=torch.float)
+    ei, ea = [], []
+    for bond in mol.GetBonds():
+        i, j = bond.GetBeginAtomIdx(), bond.GetEndAtomIdx()
+        f = bond_feat(bond)
+        ei += [[i, j], [j, i]]
+        ea += [f, f]
+    if not ei:
+        return None, None
+    graph = Data(
+        x=x,
+        edge_index=torch.tensor(ei, dtype=torch.long).t().contiguous(),
+        edge_attr=torch.tensor(ea, dtype=torch.float),
+        batch=torch.zeros(x.size(0), dtype=torch.long),
+    )
+    return graph, mol
+
+
+# ── Model loader ──────────────────────────────────────────────────────────────
+_MODELS = None  # lazy load
+
+
+def load_models():
+    global _MODELS
+    if _MODELS is not None:
+        return _MODELS
+
+    models = []
+    for seed in SEEDS:
+        seed_tag = "" if seed == 42 else f"_seed{seed}"
+        for fold in range(1, N_FOLDS + 1):
+            name = f"random_attentivefp{seed_tag}_fold{fold}.pt"
+            path = os.path.join(MODEL_DIR, name)
+            if not os.path.exists(path):
+                continue
+            m = AttentiveFPModel(hidden=HIDDEN, num_layers=2,
+                                 num_timesteps=2, dropout=0.2).to(DEVICE)
+            m.load_state_dict(torch.load(path, map_location=DEVICE, weights_only=False))
+            m.eval()
+            models.append(m)
+
+    if not models:
+        # fallback: single canonical model
+        path = os.path.join(MODEL_DIR, "random_attentivefp.pt")
+        m = AttentiveFPModel(hidden=HIDDEN).to(DEVICE)
+        m.load_state_dict(torch.load(path, map_location=DEVICE, weights_only=False))
+        m.eval()
+        models = [m]
+
+    _MODELS = models
+    return models
+
+
+# ── Rendering ─────────────────────────────────────────────────────────────────
+def render_atom_importance(mol, atom_weights, size=(600, 450)):
+    """Render molecule with per-atom importance heatmap via RDKit Cairo."""
+    w = np.array(atom_weights, dtype=float)
+    if w.max() > w.min():
+        w = (w - w.min()) / (w.max() - w.min())
+    else:
+        w = np.ones_like(w) * 0.5
+
+    cmap = cm.get_cmap("RdYlBu_r")
+    atom_colors = {i: cmap(float(w[i]))[:3] for i in range(mol.GetNumAtoms())}
+    atom_radii  = {i: 0.20 + 0.55 * float(w[i]) for i in range(mol.GetNumAtoms())}
+    highlight   = list(range(mol.GetNumAtoms()))
+
+    try:
+        drawer = rdMolDraw2D.MolDraw2DCairo(*size)
+        opts = drawer.drawOptions()
+        opts.addAtomIndices = False
+        opts.bondLineWidth = 2.0
+        rdMolDraw2D.PrepareAndDrawMolecule(
+            drawer, mol,
+            highlightAtoms=highlight,
+            highlightAtomColors=atom_colors,
+            highlightAtomRadii=atom_radii,
+            highlightBonds=[],
+            highlightBondColors={},
+        )
+        drawer.FinishDrawing()
+        img = Image.open(io.BytesIO(drawer.GetDrawingText()))
+
+        # Add colorbar
+        fig, ax = plt.subplots(figsize=(img.width / 100, img.height / 100 + 0.5))
+        ax.imshow(img)
+        ax.axis("off")
+        sm = plt.cm.ScalarMappable(cmap="RdYlBu_r", norm=Normalize(0, 1))
+        sm.set_array([])
+        cbar = fig.colorbar(sm, ax=ax, orientation="vertical",
+                            fraction=0.03, pad=0.02, aspect=20)
+        cbar.set_label("Atom Importance", fontsize=10)
+        cbar.set_ticks([0, 0.5, 1])
+        cbar.set_ticklabels(["Low", "Medium", "High"], fontsize=8)
+        plt.tight_layout(pad=0.3)
+        buf = io.BytesIO()
+        plt.savefig(buf, format="png", dpi=120, bbox_inches="tight")
+        plt.close()
+        buf.seek(0)
+        return Image.open(buf).copy()
+    except Exception as e:
+        print(f"Rendering error: {e}")
+        return None
+
+
+def make_importance_bargraph(mol, atom_weights, pred_pic50):
+    """Horizontal bar chart of top-15 atom importances."""
+    w = np.array(atom_weights)
+    atoms  = [mol.GetAtomWithIdx(i).GetSymbol() for i in range(mol.GetNumAtoms())]
+    labels = [f"{sym}{i}" for i, sym in enumerate(atoms)]
+
+    top_k = min(15, mol.GetNumAtoms())
+    sort_idx = np.argsort(w)[::-1][:top_k]
+    sw = w[sort_idx]
+    sl = [labels[i] for i in sort_idx]
+
+    cmap = cm.get_cmap("RdYlBu_r")
+    colors = [cmap(float(v)) for v in sw]
+
+    fig, ax = plt.subplots(figsize=(6, max(3, top_k * 0.4)))
+    ax.barh(range(top_k), sw[::-1], color=colors[::-1])
+    ax.set_yticks(range(top_k))
+    ax.set_yticklabels(sl[::-1], fontsize=9)
+    ax.set_xlabel("Atom Importance Score", fontsize=10)
+    ax.set_title(f"Top-{top_k} Atom Importances  (pred pIC₅₀ = {pred_pic50:.3f})",
+                 fontsize=11, fontweight="bold")
+    ax.set_xlim(0, 1.05)
+    ax.spines["top"].set_visible(False)
+    ax.spines["right"].set_visible(False)
+    plt.tight_layout()
+    buf = io.BytesIO()
+    plt.savefig(buf, format="png", dpi=110, bbox_inches="tight")
+    plt.close()
+    buf.seek(0)
+    return Image.open(buf).copy()
+
+
+# ── Activity interpretation ────────────────────────────────────────────────────
+def interpret_activity(pic50):
+    ic50_uM = 10 ** (-pic50) * 1e6
+    if pic50 >= 5.0:
+        level = "🟢 High"
+        desc  = "Strong DPPH radical scavenger (IC₅₀ ≤ 10 µM). Comparable to quercetin."
+    elif pic50 >= 4.5:
+        level = "🟡 Moderate–High"
+        desc  = "Moderate-to-high radical scavenging activity."
+    elif pic50 >= 4.0:
+        level = "🟠 Moderate"
+        desc  = "Moderate DPPH scavenging activity."
+    else:
+        level = "🔴 Low"
+        desc  = "Weak DPPH radical scavenger."
+    return level, ic50_uM, desc
+
+
+def pharmacophore_hint(mol, atom_weights):
+    """Generate a brief pharmacophore text based on atom weights."""
+    w = np.array(atom_weights)
+    top_idx = np.argsort(w)[::-1][:5]
+    top_atoms = [mol.GetAtomWithIdx(int(i)).GetSymbol() for i in top_idx]
+
+    # Simple heuristic annotations
+    hints = []
+    if top_atoms.count("O") >= 2:
+        hints.append("**Phenolic hydroxyl / catechol motif** — primary HAT pharmacophore detected")
+    if any(mol.GetAtomWithIdx(int(i)).GetIsAromatic() for i in top_idx):
+        hints.append("**Aromatic conjugation** — supports radical delocalization (HAT/SET)")
+    if any(mol.GetAtomWithIdx(int(i)).GetSymbol() == "C"
+           and not mol.GetAtomWithIdx(int(i)).GetIsAromatic() for i in top_idx):
+        hints.append("**sp² vinyl/carbonyl carbons** — extended π-system (SET pathway)")
+    if not hints:
+        hints.append("Importance distributed across scaffold — no single dominant pharmacophore")
+
+    return "\n".join(f"• {h}" for h in hints)
+
+
+# ── Core prediction function ───────────────────────────────────────────────────
+def predict(smiles_input, run_explainer):
+    smiles = smiles_input.strip()
+    if not smiles:
+        return (None, None, "⚠️ Please enter a SMILES string.", "", "")
+
+    graph, mol = smiles_to_graph(smiles)
+    if graph is None or mol is None:
+        return (None, None,
+                "❌ Invalid SMILES string. Please check the input.",
+                "", "")
+
+    models = load_models()
+    graph = graph.to(DEVICE)
+
+    # Ensemble prediction
+    preds = []
+    with torch.no_grad():
+        for m in models:
+            out = m(graph.x, graph.edge_index, graph.edge_attr, graph.batch)
+            preds.append(out.item())
+
+    pred_mean = float(np.mean(preds))
+    pred_std  = float(np.std(preds))
+    level, ic50_uM, desc = interpret_activity(pred_mean)
+
+    result_md = (
+        f"## Predicted pIC₅₀: **{pred_mean:.3f} ± {pred_std:.3f}**\n\n"
+        f"| Property | Value |\n|---|---|\n"
+        f"| Activity level | {level} |\n"
+        f"| Estimated IC₅₀ | **{ic50_uM:.1f} µM** |\n"
+        f"| Ensemble size | {len(models)} models |\n\n"
+        f"*{desc}*\n\n"
+        f"> **Note**: pIC₅₀ = −log₁₀(IC₅₀/M). Higher = more active."
+    )
+
+    # Atom importance map
+    atom_img = None
+    bar_img  = None
+    pharma_text = ""
+
+    if run_explainer:
+        try:
+            explainer = Explainer(
+                model=models[0],
+                algorithm=GNNExplainer(epochs=150),
+                explanation_type="model",
+                node_mask_type="attributes",
+                edge_mask_type="object",
+                model_config=dict(mode="regression", task_level="graph",
+                                  return_type="raw"),
+            )
+            exp = explainer(
+                x=graph.x,
+                edge_index=graph.edge_index,
+                edge_attr=graph.edge_attr,
+                batch=graph.batch,
+            )
+            raw_w = exp.node_mask.sum(dim=-1).cpu().numpy()
+            raw_w = np.abs(raw_w)
+            if raw_w.max() > 0:
+                raw_w /= raw_w.max()
+
+            atom_img = render_atom_importance(mol, raw_w)
+            bar_img  = make_importance_bargraph(mol, raw_w, pred_mean)
+            pharma_text = "### Pharmacophore Analysis\n\n" + pharmacophore_hint(mol, raw_w)
+        except Exception as e:
+            pharma_text = f"⚠️ Explainer error: {e}"
+    else:
+        pharma_text = (
+            "💡 *Enable 'Run GNNExplainer' to generate atom importance maps.*\n\n"
+            "The explainer adds ~10–20 s on CPU but reveals which atoms drive the prediction."
+        )
+
+    return atom_img, bar_img, result_md, pharma_text, ""
+
+
+# ── Gradio UI ─────────────────────────────────────────────────────────────────
+CSS = """
+.main-header {
+    background: linear-gradient(135deg, #1a1a2e 0%, #16213e 50%, #0f3460 100%);
+    padding: 24px;
+    border-radius: 12px;
+    margin-bottom: 16px;
+    text-align: center;
+    color: white;
+}
+.main-header h1 { font-size: 2.2em; margin: 0; font-weight: 800; }
+.main-header p  { font-size: 1.05em; opacity: 0.85; margin-top: 8px; }
+.result-box { border: 1px solid #e0e0e0; border-radius: 8px; padding: 16px; }
+.example-btn { font-size: 0.85em !important; }
+footer { display: none !important; }
+"""
+
+HEADER_HTML = """
+<div class="main-header">
+  <h1>🧪 AntioxFP</h1>
+  <p>GNN-Based Antioxidant Activity Predictor | AttentiveFP Ensemble × 30 Models</p>
+  <p style="font-size:0.85em; opacity:0.65;">
+    Predicts DPPH• radical scavenging pIC₅₀ from SMILES · Atom-level interpretability via GNNExplainer
+  </p>
+</div>
+"""
+
+ABOUT_MD = """
+### About This Tool
+
+**AntioxFP** uses a 30-model AttentiveFP ensemble to predict
+DPPH radical scavenging activity (pIC₅₀) for any small molecule
+provided as a SMILES string.
+
+**Key features:**
+- 30-model ensemble (3 random seeds × 10-fold CV) → prediction ± uncertainty
+- GNNExplainer atom importance maps → identify key pharmacophores
+- Exceeds descriptor-based benchmark (R² = 0.785 vs 0.78)
+- Applicable domain: ~98% of drug-like antioxidant space
+
+**Dataset**: 1,911 DPPH antioxidants (AODB, curated by Ghironi et al. 2025)
+
+**Reference**: *Graph Neural Network Models for Predicting the Antioxidant
+Activity of Chemical Compounds*, 2025.
+
+**Tips:**
+- pIC₅₀ > 5.0 → strong antioxidant (IC₅₀ ≤ 10 µM)
+- pIC₅₀ 4.0–5.0 → moderate activity
+- pIC₅₀ < 4.0 → weak scavenger
+- Enable GNNExplainer to see which atoms drive the prediction
+"""
+
+
+def predict_wrapper(smiles, run_explainer):
+    atom_img, bar_img, result_md, pharma_text, _ = predict(smiles, run_explainer)
+    return atom_img, bar_img, result_md, pharma_text
+
+
+with gr.Blocks(css=CSS, title="AntioxFP — Antioxidant Activity Predictor") as demo:
+    gr.HTML(HEADER_HTML)
+
+    with gr.Row():
+        # ── Left panel ────────────────────────────────────────────────────────
+        with gr.Column(scale=2):
+            smiles_input = gr.Textbox(
+                label="SMILES Input",
+                placeholder="Enter SMILES string, e.g. O=c1c(O)c(-c2ccc(O)c(O)c2)oc2cc(O)cc(O)c12",
+                lines=3,
+                max_lines=5,
+            )
+            with gr.Row():
+                run_btn      = gr.Button("🔬 Predict Activity", variant="primary", scale=3)
+                explainer_cb = gr.Checkbox(
+                    label="Run GNNExplainer (atom maps, +10–20s)",
+                    value=True, scale=2,
+                )
+            clear_btn = gr.Button("🗑️ Clear", variant="secondary")
+
+            gr.Markdown("**Quick Examples** — click to load:")
+            example_rows = []
+            for i in range(0, len(EXAMPLE_SMILES), 2):
+                with gr.Row():
+                    for smi, label in EXAMPLE_SMILES[i:i+2]:
+                        btn = gr.Button(label, elem_classes=["example-btn"])
+                        btn.click(fn=lambda s=smi: s, outputs=smiles_input)
+
+            gr.Markdown(ABOUT_MD)
+
+        # ── Right panel ───────────────────────────────────────────────────────
+        with gr.Column(scale=3):
+            result_md    = gr.Markdown("*Results will appear here after prediction.*",
+                                       elem_classes=["result-box"])
+            pharma_text  = gr.Markdown("")
+
+            with gr.Tabs():
+                with gr.TabItem("🗺️ Atom Importance Map"):
+                    atom_img = gr.Image(
+                        label="2D Atom-Level Importance (blue=low → red=high)",
+                        type="pil", height=420,
+                    )
+                with gr.TabItem("📊 Top-15 Atom Scores"):
+                    bar_img = gr.Image(
+                        label="Atom Importance Bar Chart",
+                        type="pil", height=420,
+                    )
+
+    run_btn.click(
+        fn=predict_wrapper,
+        inputs=[smiles_input, explainer_cb],
+        outputs=[atom_img, bar_img, result_md, pharma_text],
+        show_progress="full",
+    )
+
+    clear_btn.click(
+        fn=lambda: ("", None, None,
+                    "*Results will appear here after prediction.*", ""),
+        outputs=[smiles_input, atom_img, bar_img, result_md, pharma_text],
+    )
+
+    gr.HTML("""
+    <div style="text-align:center;margin-top:16px;opacity:0.5;font-size:0.82em;">
+      AntioxFP · AttentiveFP (PyTorch Geometric) · GNNExplainer ·
+      RDKit · Built with Gradio · 2025
+    </div>
+    """)
+
+if __name__ == "__main__":
+    demo.launch(share=False)