Update app.py

app.py

@@ -25,7 +25,7 @@ from PIL import Image
 from functools import wraps
 
 # ─────────────────────────────────────────────
-# CACHE SYSTEM  (TTL = 24 h)
+# CACHE SYSTEM (TTL = 24 h)
 # ─────────────────────────────────────────────
 CACHE_DIR = "./cache"
 os.makedirs(CACHE_DIR, exist_ok=True)
@@ -55,7 +55,6 @@ def cache_set(endpoint: str, query: str, data):
 # RETRY DECORATOR
 # ─────────────────────────────────────────────
 def retry(max_attempts=3, delay=1):
-    """Decorator to retry a function on exception."""
     def decorator(func):
         @wraps(func)
         def wrapper(*args, **kwargs):
@@ -72,24 +71,23 @@ def retry(max_attempts=3, delay=1):
     return decorator
 
 # ─────────────────────────────────────────────
-# LAB JOURNAL
+# LAB JOURNAL (уніфікована система кодування S1)
 # ─────────────────────────────────────────────
 JOURNAL_FILE = "./lab_journal.csv"
-# Уніфікована система кодування (як у Learning Playground)
 JOURNAL_CATEGORIES = [
-    # Real Data Tools (S2-A)
-    "S2-A·R1a",  # Gray Zones Explorer
-    "S2-A·R1b",  # Understudied Target Finder
-    "S2-A·R1c",  # Real Variant Lookup
-    "S2-A·R1d",  # Literature Gap Finder
-    "S2-A·R1e",  # Druggable Orphans
-    "S2-A·R1f",  # Research Assistant (Chatbot)
-    # Learning Sandbox (S2-B)
-    "S2-B·R1a",  # miRNA Explorer
-    "S2-B·R1b",  # siRNA Targets
-    "S2-B·R1c",  # LNP Corona
-    "S2-B·R1d",  # Flow Corona
-    "S2-B·R1e",  # Variant Concepts
+    # Real Data Tools (S1-A)
+    "S1-A·R2a",  # Gray Zones Explorer
+    "S1-A·R2b",  # Understudied Target Finder
+    "S1-A·R1a",  # Real Variant Lookup
+    "S1-A·R2c",  # Literature Gap Finder
+    "S1-A·R2d",  # Druggable Orphans
+    "S1-A·R2e",  # Research Assistant (Chatbot)
+    # Learning Sandbox
+    "S1-B·R1a",  # miRNA Explorer
+    "S1-B·R2a",  # siRNA Targets
+    "S1-D·R1a",  # LNP Corona
+    "S1-D·R2a",  # Flow Corona
+    "S1-A·R1b",  # Variant Concepts
     "Manual"
 ]
 
@@ -176,12 +174,11 @@ CT_BASE      = "https://clinicaltrials.gov/api/v2"
 
 @retry(max_attempts=3, delay=1)
 def pubmed_count(query: str) -> int:
-    """Return paper count for a PubMed query (cached)."""
     cached = cache_get("pubmed_count", query)
     if cached is not None:
         return cached
     try:
-        time.sleep(0.34)  # Rate limit compliance
+        time.sleep(0.34)
         r = requests.get(
             f"{PUBMED_BASE}/esearch.fcgi",
             params={"db": "pubmed", "term": query, "rettype": "count", "retmode": "json"},
@@ -192,19 +189,11 @@ def pubmed_count(query: str) -> int:
         count = int(data.get("esearchresult", {}).get("count", 0))
         cache_set("pubmed_count", query, count)
         return count
-    except requests.exceptions.Timeout:
-        print(f"Timeout for query: {query}")
-        return -1
-    except requests.exceptions.RequestException as e:
-        print(f"Request error for {query}: {e}")
-        return -1
-    except (KeyError, ValueError) as e:
-        print(f"Parsing error for {query}: {e}")
+    except Exception:
         return -1
 
 @retry(max_attempts=3, delay=1)
 def pubmed_search(query: str, retmax: int = 10) -> list:
-    """Return list of PMIDs (cached)."""
     cached = cache_get("pubmed_search", f"{query}_{retmax}")
     if cached is not None:
         return cached
@@ -225,7 +214,6 @@ def pubmed_search(query: str, retmax: int = 10) -> list:
 
 @retry(max_attempts=3, delay=1)
 def pubmed_summary(pmids: list) -> list:
-    """Fetch summaries for a list of PMIDs."""
     if not pmids:
         return []
     cached = cache_get("pubmed_summary", ",".join(pmids))
@@ -248,7 +236,6 @@ def pubmed_summary(pmids: list) -> list:
 
 @retry(max_attempts=3, delay=1)
 def ot_query(gql: str, variables: dict = None) -> dict:
-    """Run an OpenTargets GraphQL query (cached)."""
     key = json.dumps({"q": gql, "v": variables}, sort_keys=True)
     cached = cache_get("ot_gql", key)
     if cached is not None:
@@ -262,16 +249,13 @@ def ot_query(gql: str, variables: dict = None) -> dict:
         r.raise_for_status()
         data = r.json()
         if "errors" in data:
-            print(f"GraphQL errors: {data['errors']}")
             return {"error": data["errors"]}
         cache_set("ot_gql", key, data)
         return data
     except Exception as e:
-        print(f"OT query error: {e}")
         return {"error": str(e)}
-
 # ─────────────────────────────────────────────
-# TAB A1 — GRAY ZONES EXPLORER
+# TAB A1 — GRAY ZONES EXPLORER (S1-A·R2a)
 # ─────────────────────────────────────────────
 
 def a1_run(cancer_type: str):
@@ -324,13 +308,13 @@ def a1_run(cancer_type: str):
         )
 
     gaps_md = "\n\n---\n\n".join(gap_cards) if gap_cards else "No data available."
-    journal_log("S2-A·R1a", f"cancer={cancer_type}", f"gaps={[p for p,_ in sorted_procs[:5]]}")
+    journal_log("S1-A·R2a", f"cancer={cancer_type}", f"gaps={[p for p,_ in sorted_procs[:5]]}")
     source_note = f"*Source: PubMed E-utilities | Date: {today}*"
     return img, gaps_md + "\n\n" + source_note
 
 
 # ─────────────────────────────────────────────
-# TAB A2 — UNDERSTUDIED TARGET FINDER
+# TAB A2 — UNDERSTUDIED TARGET FINDER (S1-A·R2b)
 # ─────────────────────────────────────────────
 
 DEPMAP_URL = "https://ndownloader.figshare.com/files/40448549"  # CRISPR_gene_effect.csv (public)
@@ -458,14 +442,14 @@ def a2_run(cancer_type: str):
         f"and replace `_load_depmap_sample()` in `app.py`."
     )
     if not result_df.empty:
-        journal_log("S2-A·R1b", f"cancer={cancer_type}", f"top_gap={result_df.iloc[0]['Gene']}")
+        journal_log("S1-A·R2b", f"cancer={cancer_type}", f"top_gap={result_df.iloc[0]['Gene']}")
     else:
-        journal_log("S2-A·R1b", f"cancer={cancer_type}", "no targets found")
+        journal_log("S1-A·R2b", f"cancer={cancer_type}", "no targets found")
     return result_df, note
 
 
 # ─────────────────────────────────────────────
-# TAB A3 — REAL VARIANT LOOKUP
+# TAB A3 — REAL VARIANT LOOKUP (S1-A·R1a)
 # ─────────────────────────────────────────────
 
 def a3_run(hgvs: str):
@@ -586,12 +570,12 @@ def a3_run(hgvs: str):
         )
 
     result_parts.append(f"\n*Source: ClinVar E-utilities + gnomAD GraphQL | Date: {today}*")
-    journal_log("S2-A·R1c", f"hgvs={hgvs}", result_parts[0][:100] if result_parts else "no results")
+    journal_log("S1-A·R1a", f"hgvs={hgvs}", result_parts[0][:100] if result_parts else "no results")
     return "\n\n".join(result_parts)
 
 
 # ─────────────────────────────────────────────
-# TAB A4 — LITERATURE GAP FINDER
+# TAB A4 — LITERATURE GAP FINDER (S1-A·R2c)
 # ─────────────────────────────────────────────
 
 def a4_run(cancer_type: str, keyword: str):
@@ -652,12 +636,12 @@ def a4_run(cancer_type: str, keyword: str):
 
     summary = "\n\n".join(gap_text)
     summary += f"\n\n*Source: PubMed E-utilities | Date: {today}*"
-    journal_log("S2-A·R1d", f"cancer={cancer_type}, kw={keyword}", summary[:100])
+    journal_log("S1-A·R2c", f"cancer={cancer_type}, kw={keyword}", summary[:100])
     return img, summary
 
 
 # ─────────────────────────────────────────────
-# TAB A5 — DRUGGABLE ORPHANS
+# TAB A5 — DRUGGABLE ORPHANS (S1-A·R2d)
 # ─────────────────────────────────────────────
 
 def a5_run(cancer_type: str):
@@ -749,7 +733,7 @@ def a5_run(cancer_type: str):
         f"*Source: OpenTargets GraphQL + ClinicalTrials.gov v2 | Date: {today}*\n\n"
         f"*Orphan = no approved drug (OpenTargets knownDrugs.count = 0)*"
     )
-    journal_log("S2-A·R1e", f"cancer={cancer_type}", f"orphans={len(df)}")
+    journal_log("S1-A·R2d", f"cancer={cancer_type}", f"orphans={len(df)}")
     return df, note
 
 
@@ -762,7 +746,7 @@ SIMULATED_BANNER = (
     "for educational purposes only. Results do NOT reflect real experimental outcomes."
 )
 
-# ── TAB B1 — miRNA Explorer ──────────────────
+# ── TAB B1 — miRNA Explorer (S1-B·R1a) ──────────────────
 
 MIRNA_DB = {
     "BRCA2": {
@@ -832,11 +816,11 @@ def b1_run(gene: str):
         "Expression log2FC": changes,
     })
     context = f"\n\n**Cancer Context:** {db['cancer_context']}"
-    journal_log("S2-B·R1a", f"gene={gene}", f"top_miRNA={mirnas[0]}")
+    journal_log("S1-B·R1a", f"gene={gene}", f"top_miRNA={mirnas[0]}")
     return img, df.to_markdown(index=False) + context
 
 
-# ── TAB B2 — siRNA Targets ───────────────────
+# ── TAB B2 — siRNA Targets (S1-B·R2a) ───────────────────
 
 SIRNA_DB = {
     "LUAD": {
@@ -894,11 +878,11 @@ def b2_run(cancer: str):
         "Off-target Risk": off_risk,
         "Delivery Challenge": delivery,
     })
-    journal_log("S2-B·R1b", f"cancer={cancer}", f"top={targets[0]}")
+    journal_log("S1-B·R2a", f"cancer={cancer}", f"top={targets[0]}")
     return img, df.to_markdown(index=False)
 
 
-# ── TAB B3 — LNP Corona Simulator ───────────────
+# ── TAB B3 — LNP Corona Simulator (S1-D·R1a) ───────────────
 
 def b3_run(peg_mol_pct: float, ionizable_pct: float, helper_pct: float,
            chol_pct: float, particle_size_nm: float, serum_pct: float):
@@ -950,11 +934,11 @@ def b3_run(peg_mol_pct: float, ionizable_pct: float, helper_pct: float,
         + ("High ApoE → enhanced brain/liver targeting via LDLR pathway." if apoe_pct > 25
            else "Low ApoE → reduced receptor-mediated uptake.")
     )
-    journal_log("S2-B·R1c", f"PEG={peg_mol_pct}%,size={particle_size_nm}nm", f"ApoE={apoe_pct:.1f}%")
+    journal_log("S1-D·R1a", f"PEG={peg_mol_pct}%,size={particle_size_nm}nm", f"ApoE={apoe_pct:.1f}%")
     return img, interpretation
 
 
-# ── TAB B4 — Flow Corona (Vroman Kinetics) ──────
+# ── TAB B4 — Flow Corona (Vroman Kinetics) (S1-D·R2a) ──────
 
 def b4_run(time_points: int, kon_albumin: float, kon_apoe: float,
            koff_albumin: float, koff_apoe: float):
@@ -994,11 +978,11 @@ def b4_run(time_points: int, kon_albumin: float, kon_apoe: float,
         "The Vroman effect describes sequential protein displacement: "
         "abundant proteins (albumin) adsorb first, then are displaced by higher-affinity proteins (ApoE, fibrinogen)."
     )
-    journal_log("S2-B·R1d", f"kon_alb={kon_albumin},kon_apoe={kon_apoe}", note[:80])
+    journal_log("S1-D·R2a", f"kon_alb={kon_albumin},kon_apoe={kon_apoe}", note[:80])
     return img, note
 
 
-# ── TAB B5 — Variant Concepts ───────────────────
+# ── TAB B5 — Variant Concepts (S1-A·R1b) ───────────────────
 
 VARIANT_RULES = {
     "Pathogenic": {
@@ -1048,7 +1032,7 @@ def b5_run(classification: str):
         f"> ⚠️ SIMULATED — This is a rule-based educational model only. "
         f"Real variant classification requires expert review and full ACMG/AMP criteria evaluation."
     )
-    journal_log("S2-B·R1e", f"class={classification}", output[:100])
+    journal_log("S1-A·R1b", f"class={classification}", output[:100])
     return output
 # ─────────────────────────────────────────────
 # GRADIO UI ASSEMBLY
@@ -1099,7 +1083,7 @@ def build_app():
                         with gr.Tabs():
 
                             # ── A1 ──
-                            with gr.Tab("🔍 Gray Zones Explorer"):
+                            with gr.Tab("S1-A·R2a · Gray Zones Explorer"):
                                 gr.Markdown(
                                     "Identify underexplored biological processes in a cancer type "
                                     "using live PubMed + OpenTargets data."
@@ -1120,7 +1104,7 @@ def build_app():
                                 a1_btn.click(a1_run, inputs=[a1_cancer], outputs=[a1_heatmap, a1_gaps])
 
                             # ── A2 ──
-                            with gr.Tab("🎯 Understudied Target Finder"):
+                            with gr.Tab("S1-A·R2b · Understudied Target Finder"):
                                 gr.Markdown(
                                     "Find essential genes with high research gap index "
                                     "(high essentiality, low publication coverage)."
@@ -1150,7 +1134,7 @@ def build_app():
                                 a2_btn.click(a2_run, inputs=[a2_cancer], outputs=[a2_table, a2_note])
 
                             # ── A3 ──
-                            with gr.Tab("🧬 Real Variant Lookup"):
+                            with gr.Tab("S1-A·R1a · Real Variant Lookup"):
                                 gr.Markdown(
                                     "Look up a variant in **ClinVar** and **gnomAD**. "
                                     "Results are fetched live — never hallucinated."
@@ -1177,7 +1161,7 @@ def build_app():
                                 a3_btn.click(a3_run, inputs=[a3_hgvs], outputs=[a3_result])
 
                             # ── A4 ──
-                            with gr.Tab("📰 Literature Gap Finder"):
+                            with gr.Tab("S1-A·R2c · Literature Gap Finder"):
                                 gr.Markdown(
                                     "Visualize publication trends over 10 years and detect "
                                     "years with low research activity."
@@ -1200,7 +1184,7 @@ def build_app():
                                 a4_btn.click(a4_run, inputs=[a4_cancer, a4_kw], outputs=[a4_chart, a4_gaps])
 
                             # ── A5 ──
-                            with gr.Tab("💊 Druggable Orphans"):
+                            with gr.Tab("S1-A·R2d · Druggable Orphans"):
                                 gr.Markdown(
                                     "Identify cancer-associated essential genes with **no approved drug** "
                                     "and **no active clinical trial**."
@@ -1221,8 +1205,8 @@ def build_app():
                                     )
                                 a5_btn.click(a5_run, inputs=[a5_cancer], outputs=[a5_table, a5_note])
 
-                            # ── A6 (RAG Chatbot — injected from chatbot.py) ──
-                            with gr.Tab("🤖 Research Assistant"):
+                            # ── A6 (RAG Chatbot) ──
+                            with gr.Tab("S1-A·R2e · Research Assistant"):
                                 gr.Markdown(
                                     "**RAG-powered research assistant** indexed on 20 curated papers "
                                     "on LNP delivery, protein corona, and cancer variants.\n\n"
@@ -1248,7 +1232,7 @@ def build_app():
                         with gr.Tabs():
 
                             # ── B1 ──
-                            with gr.Tab("🧬 miRNA Explorer"):
+                            with gr.Tab("S1-B·R1a · miRNA Explorer"):
                                 gr.Markdown(SIMULATED_BANNER)
                                 b1_gene = gr.Dropdown(["BRCA2", "BRCA1", "TP53"], label="Gene", value="TP53")
                                 b1_btn = gr.Button("🔬 Explore miRNA Interactions", variant="primary")
@@ -1267,7 +1251,7 @@ def build_app():
                                 b1_btn.click(b1_run, inputs=[b1_gene], outputs=[b1_plot, b1_table])
 
                             # ── B2 ──
-                            with gr.Tab("🎯 siRNA Targets"):
+                            with gr.Tab("S1-B·R2a · siRNA Targets"):
                                 gr.Markdown(SIMULATED_BANNER)
                                 b2_cancer = gr.Dropdown(["LUAD", "BRCA", "COAD"], label="Cancer Type", value="LUAD")
                                 b2_btn = gr.Button("🎯 Simulate siRNA Efficacy", variant="primary")
@@ -1285,7 +1269,7 @@ def build_app():
                                 b2_btn.click(b2_run, inputs=[b2_cancer], outputs=[b2_plot, b2_table])
 
                             # ── B3 ──
-                            with gr.Tab("🧪 LNP Corona"):
+                            with gr.Tab("S1-D·R1a · LNP Corona"):
                                 gr.Markdown(SIMULATED_BANNER)
                                 with gr.Row():
                                     b3_peg = gr.Slider(0.5, 5.0, value=1.5, step=0.1, label="PEG mol% (lipid)")
@@ -1316,7 +1300,7 @@ def build_app():
                                 )
 
                             # ── B4 ──
-                            with gr.Tab("🌊 Flow Corona"):
+                            with gr.Tab("S1-D·R2a · Flow Corona"):
                                 gr.Markdown(SIMULATED_BANNER)
                                 with gr.Row():
                                     b4_time = gr.Slider(10, 120, value=60, step=5, label="Time range (min)")
@@ -1348,7 +1332,7 @@ def build_app():
                                 )
 
                             # ── B5 ──
-                            with gr.Tab("🔬 Variant Concepts"):
+                            with gr.Tab("S1-A·R1b · Variant Concepts"):
                                 gr.Markdown(SIMULATED_BANNER)
                                 b5_class = gr.Dropdown(
                                     list(VARIANT_RULES.keys()),