Update app.py

app.py

@@ -1,4 +1,14 @@
-# app.py ── MedGenesis AI · dual-LLM · CPU-only
+#!/usr/bin/env python3
+"""MedGenesis AI — CPU-only, dual-LLM (OpenAI / Gemini)"""
+
+# ────────────── FIX: create a writable Streamlit data dir ──────────────
+import os, pathlib
+os.environ["STREAMLIT_DATA_DIR"]                = "/tmp/.streamlit"
+os.environ["XDG_STATE_HOME"]                    = "/tmp"
+os.environ["STREAMLIT_BROWSER_GATHERUSAGESTATS"] = "false"
+pathlib.Path("/tmp/.streamlit").mkdir(parents=True, exist_ok=True)
+# ───────────────────────────────────────────────────────────────────────
+
 import asyncio, re
 from pathlib import Path
 
@@ -14,158 +24,156 @@ from mcp.knowledge_graph import build_agraph
 from mcp.graph_metrics   import build_nx, get_top_hubs, get_density
 from mcp.alerts          import check_alerts
 
-ROOT  = Path(__file__).parent
-LOGO  = ROOT / "assets" / "logo.png"
+ROOT = Path(__file__).parent
+LOGO = ROOT / "assets" / "logo.png"
 
-# ─────────────────────────── helpers ────────────────────────────
+# ──────────────── small helpers ─────────────────
 def _pdf(papers):
     pdf = FPDF(); pdf.add_page(); pdf.set_font("Arial", size=11)
     pdf.cell(200, 8, "MedGenesis AI – Results", ln=True, align="C"); pdf.ln(3)
     for i, p in enumerate(papers, 1):
-        pdf.set_font("Arial", "B", 11); pdf.multi_cell(0, 7, f"{i}. {p['title']}")
+        pdf.set_font("Arial", "B", 11)
+        pdf.multi_cell(0, 7, f"{i}. {p['title']}")
         pdf.set_font("Arial", "", 9)
         pdf.multi_cell(0, 6, f"{p['authors']}\n{p['summary']}\n{p['link']}\n")
         pdf.ln(1)
     return pdf.output(dest="S").encode("latin-1")
 
-def _workspace_sidebar():
+def _sidebar_workspace():
     with st.sidebar:
         st.header("🗂️ Workspace")
-        for i, item in enumerate(get_workspace(), 1):
+        ws = get_workspace()
+        if not ws:
+            st.info("Run a search then press **Save** to populate this list.")
+            return
+        for i, item in enumerate(ws, 1):
             with st.expander(f"{i}. {item['query']}"):
                 st.write(item["result"]["ai_summary"])
-                df = pd.DataFrame(item["result"]["papers"])
-                st.download_button("CSV", df.to_csv(index=False),
-                                   f"ws_{i}.csv", "text/csv")
-        if not get_workspace():
-            st.info("Run a search and press **Save** to fill your workspace.")
 
-# ─────────────────────────── UI ────────────────────────────────
+# ──────────────── Streamlit UI ──────────────────
 def render_ui():
     st.set_page_config("MedGenesis AI", layout="wide")
-    _workspace_sidebar()
+    _sidebar_workspace()
 
-    # Logo & title
-    col1, col2 = st.columns([0.15, 0.85])
-    with col1:
+    # header
+    c1, c2 = st.columns([0.15, 0.85])
+    with c1:
         if LOGO.exists():
             st.image(str(LOGO), width=105)
-    with col2:
+    with c2:
         st.markdown("## 🧬 **MedGenesis AI**")
         st.caption("Multi-source biomedical assistant · OpenAI / Gemini")
 
-    llm = st.radio("LLM Engine", ["openai", "gemini"], horizontal=True)
-    query = st.text_input("Enter biomedical question …",
-                          placeholder="e.g. CRISPR for glioblastoma")
+    llm = st.radio("LLM engine", ["openai", "gemini"], horizontal=True)
+    query = st.text_input("Enter biomedical question",
+                          placeholder="e.g. CRISPR glioblastoma therapy")
 
-    # 🔔 alert check
+    # alert check
     if get_workspace():
         try:
             news = asyncio.run(check_alerts([w["query"] for w in get_workspace()]))
             if news:
-                with st.sidebar:
-                    st.subheader("🔔 New Papers")
-                    for q, links in news.items():
-                        st.write(f"**{q}** – {len(links)} new")
+                st.sidebar.subheader("🔔 New papers")
+                for q, lst in news.items():
+                    st.sidebar.write(f"**{q}** – {len(lst)} new")
         except Exception as e:
             st.sidebar.warning(f"Alert check failed: {e}")
 
-    # Run
     if st.button("Run Search 🚀") and query:
-        with st.spinner("Gathering literature & databases …"):
+        with st.spinner("Collecting literature & biomedical data …"):
             res = asyncio.run(orchestrate_search(query, llm=llm))
-        st.success(f"Finished with **{res['llm_used'].title()}**")
+        st.success(f"Completed with **{res['llm_used'].title()}**")
 
-        tabs = st.tabs(["Results", "Genes", "Trials", "Graph", "Metrics", "Visuals"])
+        tabs = st.tabs(["Results", "Genes", "Trials", "Graph",
+                        "Metrics", "Visuals"])
 
-        # ── Results
+        # Results -----------------------------------------------------
         with tabs[0]:
             for i, p in enumerate(res["papers"], 1):
                 st.markdown(f"**{i}. [{p['title']}]({p['link']})**  *{p['authors']}*")
-                st.markdown(f"<span style='color:gray'>{p['summary']}</span>",
-                            unsafe_allow_html=True)
+                st.write(p["summary"])
 
-            col_a, col_b = st.columns(2)
-            with col_a:
-                st.download_button("📥 CSV",
+            col1, col2 = st.columns(2)
+            with col1:
+                st.download_button("CSV",
                                    pd.DataFrame(res["papers"]).to_csv(index=False),
                                    "papers.csv", "text/csv")
-            with col_b:
-                st.download_button("📄 PDF", _pdf(res["papers"]),
+            with col2:
+                st.download_button("PDF", _pdf(res["papers"]),
                                    "papers.pdf", "application/pdf")
 
-            if st.button("💾 Save to Workspace"):
+            if st.button("💾 Save"):
                 save_query(query, res)
-                st.success("Saved!")
+                st.success("Saved to workspace")
 
-            st.subheader("🧠 UMLS Concepts")
+            st.subheader("UMLS concepts")
             for c in res["umls"]:
                 if c.get("cui"):
                     st.write(f"- **{c['name']}** ({c['cui']})")
 
-            st.subheader("💊 OpenFDA Safety")
+            st.subheader("OpenFDA safety")
             for d in res["drug_safety"]:
                 st.json(d)
 
-            st.subheader("🤖 AI Summary")
+            st.subheader("AI summary")
             st.info(res["ai_summary"])
 
-        # ── Genes
+        # Genes -------------------------------------------------------
         with tabs[1]:
-            st.header("Gene Signals")
+            st.header("Gene / Variant signals")
             for g in res["genes"]:
-                st.write(f"- **{g.get('name', g.get('geneid'))}** – "
+                st.write(f"- **{g.get('name', g.get('geneid'))}** "
                          f"{g.get('description', '')}")
             if res["gene_disease"]:
-                st.markdown("### DisGeNET Links")
+                st.markdown("### DisGeNET links")
                 st.json(res["gene_disease"][:15])
             if res["mesh_defs"]:
-                st.markdown("### MeSH Definitions")
+                st.markdown("### MeSH definitions")
                 for d in res["mesh_defs"]:
                     if d:
                         st.write("-", d)
 
-        # ── Trials
+        # Trials ------------------------------------------------------
         with tabs[2]:
-            st.header("Clinical Trials")
+            st.header("Clinical trials")
             if not res["clinical_trials"]:
                 st.info("No trials (rate-limited or none found).")
             for t in res["clinical_trials"]:
                 st.markdown(f"**{t['NCTId'][0]}** – {t['BriefTitle'][0]}")
-                st.write(f"Phase: {t.get('Phase', [''])[0]} | "
-                         f"Status: {t['OverallStatus'][0]}")
+                st.write(f"Phase {t.get('Phase', [''])[0]} | "
+                         f"Status {t['OverallStatus'][0]}")
 
-        # ── Graph
+        # Graph -------------------------------------------------------
         with tabs[3]:
             nodes, edges, cfg = build_agraph(res["papers"],
-                                             res["umls"], res["drug_safety"])
-            highlight = st.text_input("Highlight node name:")
-            if highlight:
-                pat = re.compile(re.escape(highlight), re.I)
+                                             res["umls"],
+                                             res["drug_safety"])
+            hl = st.text_input("Highlight node:", key="hl")
+            if hl:
+                pat = re.compile(re.escape(hl), re.I)
                 for n in nodes:
                     n.color = "#f1c40f" if pat.search(n.label) else "#d3d3d3"
-            agraph(nodes=nodes, edges=edges, config=cfg)
+            agraph(nodes, edges, cfg)
 
-        # ── Metrics
+        # Metrics -----------------------------------------------------
         with tabs[4]:
             G = build_nx([n.__dict__ for n in nodes],
                          [e.__dict__ for e in edges])
             st.metric("Density", f"{get_density(G):.3f}")
-            st.markdown("#### Top Hub Nodes")
+            st.markdown("**Top hubs**")
             for nid, sc in get_top_hubs(G):
                 lab = next((n.label for n in nodes if n.id == nid), nid)
-                st.write(f"- **{lab}** – {sc:.3f}")
+                st.write(f"- {lab}  {sc:.3f}")
 
-        # ── Visuals
+        # Visuals -----------------------------------------------------
         with tabs[5]:
             years = [p["published"] for p in res["papers"] if p.get("published")]
             if years:
                 st.plotly_chart(px.histogram(years, nbins=12,
                                              title="Publication Year"))
 
-        # Follow-up Q-A
         st.markdown("---")
-        follow = st.text_input("Ask follow-up question:")
+        follow = st.text_input("Ask follow-up:")
         if st.button("Ask AI"):
             ans = asyncio.run(answer_ai_question(follow,
                                                  context=query,
@@ -175,7 +183,6 @@ def render_ui():
     else:
         st.info("Enter a question and press **Run Search 🚀**")
 
-
-# ────────────────────────────────────────────────────────────────
+# entry-point
 if __name__ == "__main__":
     render_ui()