Update app.py

app.py

@@ -1,6 +1,18 @@
-# ──────────────────────────── app.py ─────────────────────────────────
-"""Streamlit UI – MedGenesis v2 with gene + variant + trial integration."""
-import os, pathlib, asyncio, re
+# app.py – Streamlit front‑end for MedGenesis
+
+"""CPU‑only demo that can run on HF Spaces.
+Requirements (environment variables / HF 🎙 secrets):
+
+OPENAI_API_KEY / GEMINI_KEY            – LLMs
+PUB_KEY / UMLS_KEY / DISGENET_KEY ... – data APIs (optional)
+MYGENE_KEY / OT_KEY / CBIO_KEY         – new APIs (optional)
+
+Run locally:
+  streamlit run app.py --server.headless true --server.address 0.0.0.0
+"""
+
+from __future__ import annotations
+import os, asyncio, re, pathlib
 from pathlib import Path
 
 import streamlit as st
@@ -9,45 +21,42 @@ import plotly.express as px
 from fpdf import FPDF
 from streamlit_agraph import agraph
 
-from mcp.orchestrator    import orchestrate_search, answer_ai_question
-from mcp.workspace       import get_workspace, save_query
+from mcp.orchestrator import orchestrate_search, answer_ai_question
+from mcp.workspace    import get_workspace, save_query
 from mcp.knowledge_graph import build_agraph
-from mcp.graph_utils      import build_nx, get_top_hubs, get_density
-from mcp.alerts          import check_alerts
+from mcp.graph_utils   import build_nx, get_top_hubs, get_density
+from mcp.alerts        import check_alerts
 
-# ---- Streamlit telemetry patch -------------------------------------
-os.environ.update({
-    "STREAMLIT_DATA_DIR": "/tmp/.streamlit",
-    "XDG_STATE_HOME":     "/tmp",
-    "STREAMLIT_BROWSER_GATHERUSAGESTATS": "false",
-})
-pathlib.Path("/tmp/.streamlit").mkdir(parents=True, exist_ok=True)
+# --- Streamlit telemetry dir fix ------------------------------------------
+os.environ.setdefault("STREAMLIT_DATA_DIR", "/tmp/.streamlit")
+os.environ.setdefault("XDG_STATE_HOME", "/tmp")
+os.environ["STREAMLIT_BROWSER_GATHERUSAGESTATS"] = "false"
+pathlib.Path(os.environ["STREAMLIT_DATA_DIR"]).mkdir(parents=True, exist_ok=True)
 
 ROOT = Path(__file__).parent
 LOGO = ROOT / "assets" / "logo.png"
 
-# ---------------- helpers -------------------------------------------
+# --- helpers --------------------------------------------------------------
+LATIN1 = str.maketrans({**{chr(i): "?" for i in range(256, 0x110000)}})
 
-def _latin1_safe(t: str) -> str:
-    return t.encode("latin-1", "replace").decode("latin-1")
-
-def _export_pdf(papers):
+def _pdf(papers: list[dict]) -> bytes:
     pdf = FPDF()
     pdf.set_auto_page_break(auto=True, margin=15)
     pdf.add_page()
     pdf.set_font("Helvetica", size=11)
-    pdf.cell(200, 8, _latin1_safe("MedGenesis AI – Results"), ln=True, align="C")
+    pdf.multi_cell(0, 8, "MedGenesis AI – Results", align="C")
     pdf.ln(3)
+
     for i, p in enumerate(papers, 1):
         pdf.set_font("Helvetica", "B", 11)
-        pdf.multi_cell(0, 7, _latin1_safe(f"{i}. {p['title']}"))
+        pdf.multi_cell(0, 7, f"{i}. {p['title']}".translate(LATIN1))
         pdf.set_font("Helvetica", size=9)
         body = f"{p['authors']}\n{p['summary']}\n{p['link']}\n"
-        pdf.multi_cell(0, 6, _latin1_safe(body))
+        pdf.multi_cell(0, 6, body.translate(LATIN1))
         pdf.ln(1)
     return pdf.output(dest="S").encode("latin-1", "replace")
 
-# ---------------- sidebar -------------------------------------------
+# --- sidebar --------------------------------------------------------------
 
 def _workspace_sidebar():
     with st.sidebar:
@@ -60,107 +69,159 @@ def _workspace_sidebar():
             with st.expander(f"{i}. {item['query']}"):
                 st.write(item["result"]["ai_summary"])
 
-# ---------------- main ----------------------------------------------
+# --- UI -------------------------------------------------------------------
 
 def render_ui():
     st.set_page_config("MedGenesis AI", layout="wide")
+
+    # Session state --------------------------------------------------------
+    for k, v in {"query_result": None, "followup_input": "", "followup_response": None,
+                 "last_query": "", "last_llm": "openai", "tab": 0}.items():
+        st.session_state.setdefault(k, v)
+
     _workspace_sidebar()
 
-    # header ---------------------------------------------------------
     c1, c2 = st.columns([0.15, 0.85])
-    if LOGO.exists():
-        with c1: st.image(str(LOGO), width=105)
+    with c1:
+        if LOGO.exists():
+            st.image(str(LOGO), width=105)
     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", "CRISPR glioblastoma therapy")
-
-    if st.button("Run Search 🚀") and query:
-        with st.spinner("Collecting literature & biomedical data …"):
-            res = asyncio.run(orchestrate_search(query, llm=llm))
-        st.success(f"Completed with **{res['llm_used'].title()}**")
-        st.session_state.result = res
-        st.session_state.last_query = query
-        st.session_state.last_llm   = llm
-
-    res = st.session_state.get("result")
+    llm = st.radio("LLM engine", ["openai", "gemini"], horizontal=True, index=(0 if st.session_state.last_llm=="openai" else 1))
+    query = st.text_input("Enter biomedical question", st.session_state.last_query or "e.g. CRISPR glioblastoma therapy")
+
+    # alerts ---------------------------------------------------------------
+    if work := get_workspace():
+        try:
+            news = asyncio.run(check_alerts([w["query"] for w in work]))
+            if news:
+                with st.sidebar:
+                    st.subheader("🔔 New papers")
+                    for q, lnks in news.items():
+                        st.write(f"**{q}** – {len(lnks)} new")
+        except Exception:
+            pass
+
+    # run search -----------------------------------------------------------
+    if st.button("Run Search 🚀"):
+        if not query.strip():
+            st.warning("Please enter a biomedical question first.")
+        else:
+            with st.spinner("Collecting literature & biomedical data …"):
+                res = asyncio.run(orchestrate_search(query, llm=llm))
+            st.session_state.update({
+                "query_result": res,
+                "last_query": query,
+                "last_llm": llm,
+                "followup_input": "",
+                "followup_response": None,
+            })
+            st.success(f"Completed with **{res['llm_used'].title()}**")
+
+    res = st.session_state.query_result
     if not res:
         st.info("Enter a question and press **Run Search 🚀**")
         return
 
+    # --- tabs -------------------------------------------------------------
     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.write(p["summary"])
-        c1, c2 = st.columns(2)
-        with c1:
-            st.download_button("CSV", pd.DataFrame(res["papers"]).to_csv(index=False), "papers.csv")
-        with c2:
-            st.download_button("PDF", _export_pdf(res["papers"]), "papers.pdf", mime="application/pdf")
+        col1, col2 = st.columns(2)
+        with col1:
+            st.download_button("CSV", pd.DataFrame(res["papers"]).to_csv(index=False), "papers.csv", "text/csv")
+        with col2:
+            st.download_button("PDF", _pdf(res["papers"]), "papers.pdf", "application/pdf")
         if st.button("💾 Save"):
-            save_query(query, res)
+            save_query(st.session_state.last_query, res)
             st.success("Saved to workspace")
+
+        st.subheader("UMLS concepts")
+        for c in res["umls"]:
+            if isinstance(c, dict) and c.get("cui"):
+                st.write(f"- **{c['name']}** ({c['cui']})")
+
+        st.subheader("OpenFDA safety")
+        for d in res["drug_safety"]:
+            st.json(d)
+
         st.subheader("AI summary")
         st.info(res["ai_summary"])
 
-    # gene tab -------------------------------------------------------
+    # Genes ----------------------------------------------------------------
     with tabs[1]:
-        if not res["genes"]:
+        st.header("Gene / Variant signals")
+        genes = res.get("genes") or []
+        if not genes:
             st.info("No gene hits (rate‑limited or none found).")
-        for g in res["genes"]:
-            st.json(g)
-        if res["variants"]:
-            st.markdown("### Tumour variants (cBioPortal)")
-            for k, v in res["variants"].items():
-                st.write(f"**{k}** – {len(v)} variants")
-
-    # trials tab -----------------------------------------------------
+        for g in genes:
+            sym  = g.get("symbol") or g.get("approvedSymbol") or g.get("name", "")
+            summ = g.get("summary") or g.get("description", "")
+            st.write(f"- **{sym}** {summ}")
+        if res["gene_disease"]:
+            st.markdown("### DisGeNET links")
+            st.json(res["gene_disease"][:15])
+        if res["mesh_defs"]:
+            st.markdown("### MeSH definitions")
+            for d in res["mesh_defs"]:
+                if d:
+                    st.write("-", d)
+
+    # Trials ---------------------------------------------------------------
     with tabs[2]:
         st.header("Clinical trials")
-        if not res["clinical_trials"]:
+        trials = res.get("clinical_trials") or []
+        if not trials:
             st.info("No trials (rate‑limited or none found).")
-        for t in res["clinical_trials"]:
+        for t in trials:
             st.markdown(f"**{t['nctId']}** – {t['briefTitle']}")
             st.write(f"Phase {t.get('phase')} | Status {t.get('status')}")
 
-    # graph tab ------------------------------------------------------
+    # Graph ---------------------------------------------------------------
     with tabs[3]:
         nodes, edges, cfg = build_agraph(res["papers"], res["umls"], res["drug_safety"])
-        hl = st.text_input("Highlight node:")
+        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, edges, cfg)
 
-    # metrics tab ----------------------------------------------------
+    # Metrics -------------------------------------------------------------
     with tabs[4]:
+        nodes, edges, _ = build_agraph(res["papers"], res["umls"], res["drug_safety"])
         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 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}")
 
-    # visuals --------------------------------------------------------
+    # Visuals -------------------------------------------------------------
     with tabs[5]:
-        years = [p.get("published", "")[:4] for p in res["papers"] if p.get("published")]
+        years = [int(p["published"][:4]) for p in res["papers"] if p.get("published", "").isdigit()]
         if years:
-            fig = px.histogram(years, nbins=12, title="Publication Year")
-            st.plotly_chart(fig)
+            st.plotly_chart(px.histogram(years, nbins=12, title="Publication Year"))
 
-    # follow‑up QA ---------------------------------------------------
+    # Follow‑up QA --------------------------------------------------------
     st.markdown("---")
-    q = st.text_input("Ask follow‑up question:")
+    st.text_input("Ask follow‑up question:", key="followup_input", placeholder="e.g. Any phase III trials recruiting now?")
     if st.button("Ask AI"):
-        with st.spinner("Querying LLM …"):
-            ans = asyncio.run(answer_ai_question(q, context=st.session_state.last_query, llm=st.session_state.last_llm))
-        st.write(ans["answer"])
-
+        q = st.session_state.followup_input.strip()
+        if not q:
+            st.warning("Please type a question first.")
+        else:
+            with st.spinner("Querying LLM …"):
+                ans = asyncio.run(answer_ai_question(q, context=st.session_state.last_query, llm=st.session_state.last_llm))
+            st.session_state.followup_response = ans["answer"]
+    if st.session_state.followup_response:
+        st.write(st.session_state.followup_response)
 
 if __name__ == "__main__":
-    render_ui()
+    render_ui()