Update app.py

app.py

@@ -1,262 +1,41 @@
-#!/usr/bin/env python3
-"""
-MedGenesis AI – Streamlit front-end (v3)
---------------------------------------
-Supports **OpenAI** and **Gemini** engines and the enriched backend
-payload introduced in orchestrator v3:
-    • papers, umls, drug_safety, genes, mesh_defs, gene_disease,
-      clinical_trials, variants, ai_summary
-Tabs:
-    Results | Genes | Trials | Variants | Graph | Metrics | Visuals
-"""
-
-import os
-import pathlib
-import asyncio
-from pathlib import Path
-
-import streamlit as st
-import pandas as pd
-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.knowledge_graph import build_agraph
-from mcp.graph_metrics import build_nx, get_top_hubs, get_density
-from mcp.alerts import check_alerts
-
-# Streamlit telemetry directory → /tmp
-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)
-
-ROOT = Path(__file__).parent
-LOGO = ROOT / "assets" / "logo.png"
-
-
-def _latin1_safe(txt: str) -> str:
-    """Coerce UTF-8 → Latin-1 with replacement (for FPDF)."""
-    return txt.encode("latin-1", "replace").decode("latin-1")
-
-
-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.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.get('title','')}"))
-        pdf.set_font("Helvetica", "", 9)
-        body = (
-            f"{p.get('authors','')}\n"
-            f"{p.get('summary','')}\n"
-            f"{p.get('link','')}\n"
-        )
-        pdf.multi_cell(0, 6, _latin1_safe(body))
-        pdf.ln(1)
-    return pdf.output(dest="S").encode("latin-1", "replace")
-
-
-def _workspace_sidebar():
-    with st.sidebar:
-        st.header("🗂️ Workspace")
-        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'])
-
-
-def render_ui():
-    st.set_page_config("MedGenesis AI", layout="wide")
-
-    # Session-state defaults
-    defaults = dict(
-        query_result=None,
-        followup_input="",
-        followup_response=None,
-        last_query="",
-        last_llm="openai",
-    )
-    for k, v in defaults.items():
-        st.session_state.setdefault(k, v)
-
-    _workspace_sidebar()
-
-    # Header
-    col1, col2 = st.columns([0.15, 0.85])
-    with col1:
-        if LOGO.exists():
-            st.image(str(LOGO), width=105)
-    with col2:
-        st.markdown("## 🧬 **MedGenesis AI**")
-        st.caption("Multi-source biomedical assistant · OpenAI / Gemini")
-
-    # Controls
-    engine = st.radio("LLM engine", ["openai", "gemini"], horizontal=True)
-    query = st.text_input("Enter biomedical question", placeholder="e.g. CRISPR glioblastoma therapy")
-
-    # Alerts
-    if get_workspace():
-        try:
-            alerts = asyncio.run(check_alerts([w["query"] for w in get_workspace()]))
-            if alerts:
-                with st.sidebar:
-                    st.subheader("🔔 New papers")
-                    for q, lnks in alerts.items():
-                        st.write(f"**{q}** – {len(lnks)} new")
-        except Exception:
-            pass
-
-    # Run Search
-    if st.button("Run Search 🚀") and query:
-        with st.spinner("Collecting literature & biomedical data …"):
-            res = asyncio.run(orchestrate_search(query, llm=engine))
-        st.session_state.update(
-            query_result=res,
-            last_query=query,
-            last_llm=engine,
-            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", "Variants", "Graph", "Metrics", "Visuals"])
-
-    # --- Results tab ---
+# app.py
+import asyncio, streamlit as st, pandas as pd
+from mcp.orchestrator import orchestrate_search
+
+st.set_page_config(layout="wide", page_title="MedGenesis AI")
+if "res" not in st.session_state: st.session_state.res = None
+
+st.title("🧬 MedGenesis AI")
+llm = st.radio("LLM engine", ["openai","gemini"], horizontal=True)
+q = st.text_input("Enter biomedical question")
+if st.button("Run Search") and q:
+    with st.spinner("Fetching data…"):
+        st.session_state.res = asyncio.run(orchestrate_search(q, llm=llm))
+
+res = st.session_state.res
+if res:
+    st.subheader("🔬 Papers")
+    for p in res["papers"]:
+        st.markdown(f"**[{p['title']}]({p['link']})**  –  {p['authors']}")
+        st.write(p["summary"])
+    st.subheader("💡 AI Summary")
+    st.info(res["ai_summary"])
+
+    tabs = st.tabs(["Graph","Variants","Trials"])
     with tabs[0]:
-        st.subheader("Literature")
-        for i, p in enumerate(res['papers'], 1):
-            st.markdown(f"**{i}. [{p.get('title','')}]({p.get('link','')})**  *{p.get('authors','')}*")
-            st.write(p.get('summary',''))
-        c1, c2 = st.columns(2)
-        with c1:
-            st.download_button("CSV", pd.DataFrame(res['papers']).to_csv(index=False), "papers.csv", "text/csv")
-        with c2:
-            st.download_button("PDF", _pdf(res['papers']), "papers.pdf", "application/pdf")
-        if st.button("💾 Save"):
-            save_query(st.session_state.last_query, res)
-            st.success("Saved to workspace")
-
-        st.subheader("UMLS concepts")
-        for c in res['umls']:
-            if c.get('cui'):
-                st.write(f"- **{c.get('name','')}** ({c.get('cui')})")
-
-        st.subheader("OpenFDA safety signals")
-        for d in res['drug_safety']:
-            st.json(d)
-
-        st.subheader("AI summary")
-        st.info(res['ai_summary'])
-
-    # --- Genes tab ---
+        from mcp.knowledge_graph import build_agraph
+        nodes, edges, cfg = build_agraph(res)
+        from streamlit_agraph import agraph
+        agraph(nodes, edges, cfg)
     with tabs[1]:
-        st.header("Gene / Variant signals")
-        valid_genes = [g for g in res['genes'] if isinstance(g, dict)]
-        if valid_genes:
-            for g in valid_genes:
-                sym = g.get('symbol') or g.get('name') or ''
-                st.write(f"- **{sym}**")
+        if res["variants"]:
+            st.json(res["variants"])
         else:
-            st.info("No gene signals returned.")
-
-        mesh_list = [d for d in res['mesh_defs'] if isinstance(d, str) and d]
-        if mesh_list:
-            st.markdown("### MeSH definitions")
-            for d in mesh_list:
-                st.write(f"- {d}")
-
-        gene_disease = [d for d in res['gene_disease'] if isinstance(d, dict)]
-        if gene_disease:
-            st.markdown("### DisGeNET links")
-            st.json(gene_disease[:15])
-
-    # --- Trials tab ---
+            st.warning("No variants found. Try TP53 or BRCA1.")
     with tabs[2]:
-        st.header("Clinical trials")
-        trials = res['clinical_trials']
-        if not trials:
-            st.info(
-                "No trials found. Try a disease name (e.g. ‘Breast Neoplasms’) "
-                "or specific drug (e.g. ‘Pembrolizumab’)."
-            )
+        if res["trials"]:
+            st.json(res["trials"])
         else:
-            for t in trials:
-                st.markdown(
-                    f"**{t.get('nctId','')}** – {t.get('briefTitle','')}  "
-                    f"Phase {t.get('phase','?')} | Status {t.get('status','?')}"
-                )
-
-    # --- Variants tab ---
-    with tabs[3]:
-        st.header("Cancer variants (cBioPortal)")
-        variants = res['variants']
-        if not variants:
-            st.info(
-                "No variants found. Try a well-known gene symbol like ‘TP53’ or ‘BRCA1’."
-            )
-        else:
-            st.json(variants[:30])
-
-    # --- Graph tab ---
-    with tabs[4]:
-        nodes, edges, cfg = build_agraph(res['papers'], res['umls'], res['drug_safety'])
-        agraph(nodes, edges, cfg)
-
-    # --- Metrics tab ---
-    with tabs[5]:
-        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 tab ---
-    with tabs[6]:
-        years = [p.get('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 QA (outside tabs)
-    st.markdown("---")
-    input_col, button_col = st.columns([4, 1])
-    with input_col:
-        followup = st.text_input("Ask follow-up question:", key="followup_input")
-    with button_col:
-        if st.button("Ask AI"):
-            if followup.strip():
-                with st.spinner("Querying LLM …"):
-                    ans = asyncio.run(
-                        answer_ai_question(
-                            question=followup,
-                            context=st.session_state.last_query,
-                            llm=st.session_state.last_llm,
-                        )
-                    )
-                    st.session_state.followup_response = ans.get('answer', '')
-            else:
-                st.warning("Please type a question first.")
-    if st.session_state.followup_response:
-        st.write(st.session_state.followup_response)
-
-
-if __name__ == "__main__":
-    render_ui()
+            st.warning("No trials. Try a disease e.g. ‘Breast Neoplasms’ or a drug.")
+else:
+    st.info("Enter a query and press Run Search.")