Update app.py

app.py

@@ -1,6 +1,7 @@
-# ── app.py ─────────────────────────────────────────────────────────────
+# app.py
 import asyncio
 import re
+from pathlib import Path
 
 import streamlit as st
 import pandas as pd
@@ -13,8 +14,8 @@ from mcp.knowledge_graph import build_agraph
 from mcp.graph_metrics import build_nx, get_top_hubs, get_density
 from mcp.protocols import draft_protocol
 
-# ── Streamlit setup ────────────────────────────────────────────────────
-st.set_page_config(layout="wide", page_title="MedGenesis AI")
+# Streamlit config
+st.set_page_config(page_title="MedGenesis AI", layout="wide")
 if "res" not in st.session_state:
     st.session_state.res = None
 
@@ -22,8 +23,7 @@ st.title("🧬 MedGenesis AI")
 llm = st.radio("LLM engine", ["openai", "gemini"], horizontal=True)
 query = st.text_input("Enter biomedical question")
 
-# PDF helper
-
+# PDF generator
 def _make_pdf(papers):
     pdf = FPDF()
     pdf.add_page(); pdf.set_font("Helvetica", size=12)
@@ -39,7 +39,8 @@ def _make_pdf(papers):
     return pdf.output(dest="S").encode("latin-1", errors="replace")
 
 # Run search
-if st.button("Run Search 🚀") and query:
+enabled = st.button("Run Search 🚀") and query.strip()
+if enabled:
     with st.spinner("Gathering data…"):
         st.session_state.res = asyncio.run(orchestrate_search(query, llm))
 res = st.session_state.res
@@ -48,10 +49,15 @@ if not res:
     st.stop()
 
 # Tabs
-tabs = st.tabs(["Results", "Graph", "Clusters", "Variants", "Trials", "Metrics", "Visuals", "Protocols"])
+tabs = st.tabs([
+    "Results", "Graph", "Clusters", "Variants",
+    "Trials", "Metrics", "Visuals", "Protocols"
+])
+
+# Results
+title_tab, graph_tab, clust_tab, var_tab, trial_tab, met_tab, vis_tab, proto_tab = tabs
 
-# ── Results tab
-with tabs[0]:
+with title_tab:
     for i, p in enumerate(res["papers"], 1):
         st.markdown(f"**{i}. [{p['title']}]({p['link']})**")
         st.write(p["summary"])
@@ -62,8 +68,8 @@ with tabs[0]:
                        "papers.pdf", "application/pdf")
     st.subheader("AI summary"); st.info(res["ai_summary"])
 
-# ── Graph tab
-with tabs[1]:
+# Graph
+with graph_tab:
     nodes, edges, cfg = build_agraph(
         res["papers"], res["umls"], res["drug_safety"], res["umls_relations"]
     )
@@ -74,8 +80,8 @@ with tabs[1]:
             n.color = "#f1c40f" if pat.search(n.label) else n.color
     agraph(nodes, edges, cfg)
 
-# ── Clusters tab
-with tabs[2]:
+# Clusters
+with clust_tab:
     clusters = res.get("clusters", [])
     if clusters:
         df = pd.DataFrame({
@@ -85,77 +91,49 @@ with tabs[2]:
         st.write("### Paper Clusters")
         for c in sorted(set(clusters)):
             st.write(f"**Cluster {c}**")
-            for t in df[df['cluster'] == c]['title']:
+            for t in df[df['cluster']==c]['title']:
                 st.write(f"- {t}")
     else:
         st.info("No clusters to show.")
 
-# ── Variants tab
-with tabs[3]:
+# Variants
+with var_tab:
     if res.get("variants"):
         st.json(res["variants"])
     else:
         st.warning("No variants found. Try 'TP53' or 'BRCA1'.")
 
-# ── Trials tab
-with tabs[4]:
+# Trials
+with trial_tab:
     if res.get("clinical_trials"):
         st.json(res["clinical_trials"])
     else:
         st.warning("No trials found. Try a disease or drug.")
 
-# ── Metrics tab
-with tabs[5]:
-    nodes_dicts = [n.__dict__ for n in nodes]
-    edges_dicts = [e.__dict__ for e in edges]
-    G = build_nx(nodes_dicts, edges_dicts)
+# Metrics
+with met_tab:
+    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):
-        lbl = next((n.label for n in nodes if n.id == nid), nid)
-        st.write(f"- {lbl}: {sc:.3f}")
+    for nid, score in get_top_hubs(G):
+        lbl = next((n.label for n in nodes if n.id==nid), nid)
+        st.write(f"- {lbl}: {score:.3f}")
 
-# ── Visuals tab
-with tabs[6]:
+# Visuals
+with vis_tab:
     years = [p.get("published","")[:4] for p in res["papers"] if p.get("published")]
     if years:
         st.plotly_chart(px.histogram(years, nbins=10, title="Publication Year"))
 
-# ── Protocols tab
-with tabs[7]:
-    proto_q = st.text_input("Enter hypothesis for protocol:", key="proto_q")
-    if st.button("Draft Protocol") and proto_q.strip():
+# Protocols
+with proto_tab:
+    hyp = st.text_input("Enter hypothesis for protocol:", key="proto_q")
+    if st.button("Draft Protocol") and hyp.strip():
         with st.spinner("Generating protocol…"):
-            proto = asyncio.run(draft_protocol(
-                proto_q, context=res['ai_summary'], llm=llm
+            doc = asyncio.run(draft_protocol(
+                hyp, context=res["ai_summary"], llm=llm
             ))
         st.subheader("Experimental Protocol")
-        st.write(proto)
- ───────────────────────────────────────────────────
-# In import section:
-from mcp.embeddings import embed_texts, cluster_embeddings
-from mcp.protocols import draft_protocol
-
-# After creating tabs = st.tabs([...,'Clusters','Protocols']):
-with tabs[-2]:  # second last tab = Clusters
-    if res.get('clusters'):
-        df = pd.DataFrame({
-            'title': [p['title'] for p in res['papers']],
-            'cluster': res['clusters']
-        })
-        st.write("### Paper Clusters")
-        for c in sorted(set(res['clusters'])):
-            st.write(f"**Cluster {c}**")
-            for t in df[df['cluster']==c]['title']:
-                st.write(f"- {t}")
-    else:
-        st.info("No clusters to show.")
-
-with tabs[-1]:  # last tab = Protocols
-    proto_q = st.text_input("Enter hypothesis for protocol:", key="proto_q")
-    if st.button("Draft Protocol") and proto_q.strip():
-        with st.spinner("Generating protocol…"):
-            proto = asyncio.run(draft_protocol(
-                proto_q, context=res['ai_summary'], llm=llm))
-        st.subheader("Experimental Protocol")
-        st.write(proto)
+        st.write(doc)