Update app.py

app.py

@@ -1,14 +1,28 @@
+"""
+K R&D Lab — Learning Playground
+Author: Oksana Kolisnyk | kosatiks-group.pp.ua
+Repo:   github.com/TEZv/K-RnD-Lab-PHYLO-03_2026
+"""
+
 import gradio as gr
 import pandas as pd
 import numpy as np
-import json, re, csv
+import json
+import re
+import csv
+import os
+import time
+import math
+import hashlib
+import datetime
 import matplotlib
 matplotlib.use("Agg")
 import matplotlib.pyplot as plt
 from io import BytesIO
 from PIL import Image
-from datetime import datetime
 from pathlib import Path
+from datetime import datetime
+from functools import wraps
 import plotly.graph_objects as go
 import plotly.express as px
 import tabulate
@@ -28,49 +42,127 @@ RED  = "#ef4444"
 DIM  = "#8e9bae"
 BORDER = "#334155"
 
-# ========== Логування ==========
-LOG_PATH = Path("/tmp/lab_journal.csv")
-
-def log_entry(tab, inputs, result, note=""):
-    try:
-        write_header = not LOG_PATH.exists()
-        with open(LOG_PATH, "a", newline="", encoding="utf-8") as f:
-            w = csv.DictWriter(f, fieldnames=["timestamp","tab","inputs","result","note"])
-            if write_header: w.writeheader()
-            w.writerow({"timestamp": datetime.now().strftime("%Y-%m-%d %H:%M"),
-                        "tab": tab, "inputs": str(inputs),
-                        "result": str(result)[:200], "note": note})
-    except Exception as e:
-        print(f"Log error: {e}")
+# ─────────────────────────────────────────────
+# CACHE SYSTEM (TTL = 24 h)
+# ─────────────────────────────────────────────
+CACHE_DIR = "./cache"
+os.makedirs(CACHE_DIR, exist_ok=True)
+CACHE_TTL = 86400  # 24 hours in seconds
+
+def _cache_key(endpoint: str, query: str) -> str:
+    raw = f"{endpoint}_{query}"
+    return hashlib.md5(raw.encode()).hexdigest()
+
+def cache_get(endpoint: str, query: str):
+    key = _cache_key(endpoint, query)
+    path = os.path.join(CACHE_DIR, f"{endpoint}_{key}.json")
+    if os.path.exists(path):
+        mtime = os.path.getmtime(path)
+        if time.time() - mtime < CACHE_TTL:
+            with open(path) as f:
+                return json.load(f)
+    return None
+
+def cache_set(endpoint: str, query: str, data):
+    key = _cache_key(endpoint, query)
+    path = os.path.join(CACHE_DIR, f"{endpoint}_{key}.json")
+    with open(path, "w") as f:
+        json.dump(data, f)
+
+# ─────────────────────────────────────────────
+# RETRY DECORATOR
+# ─────────────────────────────────────────────
+def retry(max_attempts=3, delay=1):
+    def decorator(func):
+        @wraps(func)
+        def wrapper(*args, **kwargs):
+            for attempt in range(max_attempts):
+                try:
+                    return func(*args, **kwargs)
+                except Exception as e:
+                    print(f"Attempt {attempt+1} failed for {func.__name__}: {e}")
+                    if attempt == max_attempts - 1:
+                        raise
+                    time.sleep(delay * (attempt + 1))
+            return None
+        return wrapper
+    return decorator
+
+# ─────────────────────────────────────────────
+# LAB JOURNAL (уніфікована система кодування S1)
+# ─────────────────────────────────────────────
+JOURNAL_FILE = "./lab_journal.csv"
+JOURNAL_CATEGORIES = [
+    # S1-A Genomics
+    "S1-A·R1a",  # OpenVariant
+    "S1-A·R1b",  # Somatic Classifier (future)
+    # S1-B RNA
+    "S1-B·R1a",  # BRCA2 miRNA
+    "S1-B·R2a",  # TP53 siRNA
+    "S1-B·R3a",  # lncRNA-TREM2
+    "S1-B·R3b",  # ASO Designer
+    # S1-C Drug
+    "S1-C·R1a",  # FGFR3 RNA Drug
+    "S1-C·R1b",  # SL Drug Mapping (future)
+    "S1-C·R2a",  # Frontier (future)
+    # S1-D LNP
+    "S1-D·R1a",  # LNP Corona
+    "S1-D·R2a",  # Flow Corona
+    "S1-D·R3a",  # LNP Brain
+    "S1-D·R4a",  # AutoCorona NLP
+    "S1-D·R5a",  # CSF/Vitreous/BM (future)
+    "S1-D·R6a",  # Corona Database (NEW)
+    # S1-E Biomarkers
+    "S1-E·R1a",  # Liquid Biopsy
+    "S1-E·R1b",  # Protein Validator (future)
+    "S1-E·R2a",  # Multi-protein Biomarkers (NEW)
+    # S1-F Rare
+    "S1-F·R1a",  # DIPG Toolkit
+    "S1-F·R2a",  # UVM Toolkit
+    "S1-F·R3a",  # pAML Toolkit
+    # S1-G 3D
+    "S1-G·General",  # 3D Models
+    "Manual"
+]
 
-def load_journal(category=None):
-    """Load journal entries, optionally filtered by category. Returns markdown string."""
+def journal_log(category: str, action: str, result: str, note: str = ""):
+    """Log an entry with category."""
+    ts = datetime.now().isoformat()
+    row = [ts, category, action, result[:200], note]
+    write_header = not os.path.exists(JOURNAL_FILE)
+    with open(JOURNAL_FILE, "a", newline="", encoding="utf-8") as f:
+        w = csv.writer(f)
+        if write_header:
+            w.writerow(["timestamp", "category", "action", "result_summary", "note"])
+        w.writerow(row)
+    return ts
+
+def journal_read(category: str = "All") -> str:
+    """Read journal entries, optionally filtered by category. Returns markdown."""
+    if not os.path.exists(JOURNAL_FILE):
+        return "No entries yet."
     try:
-        if not LOG_PATH.exists() or LOG_PATH.stat().st_size == 0:
-            return "No entries yet."
-        df = pd.read_csv(LOG_PATH)
+        df = pd.read_csv(JOURNAL_FILE)
         if df.empty:
             return "No entries yet."
-        if category and category != "All":
-            df = df[df["tab"] == category]
+        if category != "All":
+            df = df[df["category"] == category]
         if df.empty:
-            return "No entries for this category."
-        return df.tail(50).to_markdown(index=False)
+            return f"No entries for category: {category}"
+        df_display = df[["timestamp", "category", "action", "result_summary", "note"]].tail(50)
+        df_display.columns = ["Timestamp", "Category", "Action", "Result", "Observation"]
+        return df_display.to_markdown(index=False)
     except Exception as e:
-        print(f"Journal load error: {e}")
-        return "Error loading journal."
-
-def save_note(note, category):
-    if note.strip():
-        log_entry(category, "manual note", note, note)
-    return "Note saved."
+        print(f"Journal read error: {e}")
+        return "Error reading journal."
 
 def clear_journal():
     try:
-        if LOG_PATH.exists():
-            LOG_PATH.unlink()
+        if os.path.exists(JOURNAL_FILE):
+            os.remove(JOURNAL_FILE)
         return "Journal cleared."
-    except Exception:
+    except Exception as e:
+        print(f"Clear journal error: {e}")
         return "Error clearing journal."
 
 # ========== БАЗИ ДАНИХ ==========
@@ -227,9 +319,7 @@ PAML_BM_LNP = [
     {"Formulation":"DLin-MC3-DPPC","BM_protein":"Vitronectin-rich","Size_nm":91,"Zeta_mV":-2.9,"Marrow_uptake_pct":19,"Priority":"MEDIUM"},
     {"Formulation":"Cationic-DOTAP-Chol","BM_protein":"Opsonin-heavy","Size_nm":132,"Zeta_mV":+8.1,"Marrow_uptake_pct":8,"Priority":"LOW"},
 ]
-
-# ========== ФУНКЦІЇ ПРЕДИКЦІЇ (з обробкою помилок) ==========
-
+# ========== ДОПОМІЖНІ ФУНКЦІЇ ==========
 def safe_img_from_fig(fig):
     """Convert matplotlib figure to PIL Image safely."""
     try:
@@ -243,22 +333,23 @@ def safe_img_from_fig(fig):
         plt.close(fig)
         return Image.new('RGB', (100, 100), color=CARD)
 
+# ========== ФУНКЦІЇ ПРЕДИКЦІЇ ==========
 def predict_mirna(gene):
     df = pd.DataFrame(MIRNA_DB.get(gene, []))
-    log_entry("S1-B·R1a", gene, f"{len(df)} miRNAs")
+    journal_log("S1-B·R1a", gene, f"{len(df)} miRNAs")
     return df
 
 def predict_sirna(cancer):
     df = pd.DataFrame(SIRNA_DB.get(cancer, []))
-    log_entry("S1-B·R2a", cancer, f"{len(df)} targets")
+    journal_log("S1-B·R2a", cancer, f"{len(df)} targets")
     return df
 
 def get_lncrna():
-    log_entry("S1-B·R3a", "load", "ceRNA")
+    journal_log("S1-B·R3a", "load", "ceRNA")
     return pd.DataFrame(CERNA)
 
 def get_aso():
-    log_entry("S1-B·R3b", "load", "ASO")
+    journal_log("S1-B·R3b", "load", "ASO")
     return pd.DataFrame(ASO)
 
 def predict_drug(pocket):
@@ -275,10 +366,10 @@ def predict_drug(pocket):
         ax.set_title(f"Top compounds — {pocket}", color=TXT, fontsize=10)
         plt.tight_layout()
         img = safe_img_from_fig(fig)
-        log_entry("S1-C·R1a", pocket, f"Top: {df.iloc[0]['Compound'] if len(df) else 'none'}")
+        journal_log("S1-C·R1a", pocket, f"Top: {df.iloc[0]['Compound'] if len(df) else 'none'}")
         return df, img
     except Exception as e:
-        log_entry("S1-C·R1a", pocket, f"Error: {str(e)}")
+        journal_log("S1-C·R1a", pocket, f"Error: {str(e)}")
         return pd.DataFrame(), None
 
 def predict_variant(hgvs, sift, polyphen, gnomad):
@@ -295,7 +386,7 @@ def predict_variant(hgvs, sift, polyphen, gnomad):
         conf = "High" if (sift < 0.01 or sift > 0.9) else "Moderate"
     colour = RED if "Pathogenic" in cls else GRN
     icon   = "⚠️ WARNING" if "Pathogenic" in cls else "✅ OK"
-    log_entry("S1-A·R1a", hgvs or f"SIFT={sift}", f"{cls} score={score}")
+    journal_log("S1-A·R1a", hgvs or f"SIFT={sift}", f"{cls} score={score}")
     return (
         f"<div style=\'background:{CARD};padding:16px;border-radius:8px;font-family:sans-serif;color:{TXT}\'>"
         f"<p style=\'font-size:11px;color:{DIM};margin:0 0 8px\'>S1-A·R1a · OpenVariant</p>"
@@ -317,7 +408,7 @@ def predict_corona(size, zeta, peg, lipid):
         if size < 100:     score += 1
         dominant = ["ApoE","Albumin","Fibrinogen","Vitronectin","ApoA-I"][min(score, 4)]
         efficacy = "High" if score >= 4 else "Medium" if score >= 2 else "Low"
-        log_entry("S1-D·R1a", f"size={size},peg={peg}", f"dominant={dominant}")
+        journal_log("S1-D·R1a", f"size={size},peg={peg},lipid={lipid}", f"dominant={dominant}")
         return f"**Dominant corona protein:** {dominant}\n\n**Predicted efficacy:** {efficacy}\n\n**Score:** {score}/6"
     except Exception as e:
         return f"Error: {str(e)}"
@@ -341,7 +432,7 @@ def predict_cancer(c1,c2,c3,c4,c5,c6,c7,c8,c9,c10):
         ax.set_title("Protein contributions", color=TXT, fontsize=10)
         plt.tight_layout()
         img = safe_img_from_fig(fig)
-        log_entry("S1-E·R1a", f"CTHRC1={c1},FHL2={c2}", f"{label} {prob:.2f}")
+        journal_log("S1-E·R1a", f"CTHRC1={c1},FHL2={c2}", f"{label} {prob:.2f}")
         html_out = (
             f"<div style=\'background:{CARD};padding:14px;border-radius:8px;font-family:sans-serif;\'>"
             f"<p style=\'font-size:11px;color:{DIM};margin:0 0 6px\'>S1-E·R1a · Liquid Biopsy</p>"
@@ -370,7 +461,7 @@ def predict_flow(size, zeta, peg, charge, flow_rate):
         ax.set_title("Vroman Effect — flow vs static", color=TXT, fontsize=9)
         plt.tight_layout()
         img = safe_img_from_fig(fig)
-        log_entry("S1-D·R2a", f"flow={flow_rate}", f"CSI={csi}")
+        journal_log("S1-D·R2a", f"flow={flow_rate}", f"CSI={csi}")
         return f"**Corona Shift Index: {csi}** — {stability}", img
     except Exception as e:
         return f"Error: {str(e)}", None
@@ -392,7 +483,7 @@ def predict_bbb(smiles, pka, zeta):
         ax.tick_params(colors=TXT)
         plt.tight_layout()
         img = safe_img_from_fig(fig)
-        log_entry("S1-D·R3a", f"pka={pka},zeta={zeta}", f"ApoE={apoe_pct:.1f}%")
+        journal_log("S1-D·R3a", f"pka={pka},zeta={zeta}", f"ApoE={apoe_pct:.1f}%")
         return f"**Predicted ApoE:** {apoe_pct:.1f}% — {tier}\n\n**BBB Probability:** {bbb_prob:.2f}", img
     except Exception as e:
         return f"Error: {str(e)}", None
@@ -418,15 +509,16 @@ def extract_corona(text):
         if not out["zeta_mv"]:         flags.append("zeta_mv not found")
         if not out["corona_proteins"]: flags.append("no proteins detected")
         summary = "All key fields extracted" if not flags else " | ".join(flags)
-        log_entry("S1-D·R4a", text[:80], f"proteins={len(out['corona_proteins'])}")
+        journal_log("S1-D·R4a", text[:80], f"proteins={len(out['corona_proteins'])}")
         return json.dumps(out, indent=2), summary
     except Exception as e:
         return json.dumps({"error": str(e)}), "Extraction error"
 
+# ========== ФУНКЦІЇ ДЛЯ РІДКІСНИХ РАКІВ ==========
 def dipg_variants(sort_by):
     df = pd.DataFrame(DIPG_VARIANTS).sort_values(
         "Freq_pct" if sort_by == "Frequency" else "Drug_status", ascending=False)
-    log_entry("S1-F·R1a", sort_by, f"{len(df)} variants")
+    journal_log("S1-F·R1a", sort_by, f"{len(df)} variants")
     return df
 
 def dipg_csf(peg, size):
@@ -444,14 +536,14 @@ def dipg_csf(peg, size):
         ax.set_title("DIPG — CSF LNP formulations (ApoE%)", color=TXT, fontsize=9)
         plt.tight_layout()
         img = safe_img_from_fig(fig)
-        log_entry("S1-F·R1a", f"peg={peg},size={size}", "formulation ranking")
+        journal_log("S1-F·R1a", f"peg={peg},size={size}", "formulation ranking")
         return df[["Formulation","Size_nm","Zeta_mV","ApoE_pct","BBB_est","Priority"]], img
     except Exception as e:
         return pd.DataFrame(), None
 
 def uvm_variants():
     df = pd.DataFrame(UVM_VARIANTS)
-    log_entry("S1-F·R2a", "load", f"{len(df)} variants")
+    journal_log("S1-F·R2a", "load", f"{len(df)} variants")
     return df
 
 def uvm_vitreous():
@@ -467,7 +559,7 @@ def uvm_vitreous():
         ax.set_title("UVM — LNP retention in vitreous humor", color=TXT, fontsize=9)
         plt.tight_layout()
         img = safe_img_from_fig(fig)
-        log_entry("S1-F·R2a", "load", "vitreous LNP ranking")
+        journal_log("S1-F·R2a", "load", "vitreous LNP ranking")
         return df, img
     except Exception as e:
         return pd.DataFrame(), None
@@ -491,7 +583,7 @@ def paml_ferroptosis(variant):
         ax.set_title(f"pAML · {row['Variant'][:20]}", color=TXT, fontsize=9)
         plt.tight_layout()
         img = safe_img_from_fig(fig)
-        log_entry("S1-F·R3a", variant, f"ferr={ferr_score:.2f}")
+        journal_log("S1-F·R3a", variant, f"ferr={ferr_score:.2f}")
         _v  = row["Variant"]
         _p  = row["Pathway"]
         _d  = row["Drug_status"]
@@ -512,29 +604,153 @@ def paml_ferroptosis(variant):
     except Exception as e:
         return f"<div style='color:{RED}'>Error: {str(e)}</div>", None
 
-# ========== ДОПОМІЖНІ ФУНКЦІЇ ==========
-def section_header(code, name, tagline, projects_html):
-    return (
-        f"<div style=\'background:{BG};border:1px solid {BORDER};padding:14px 18px;"
-        f"border-radius:8px;margin-bottom:12px;\'>"
-        f"<div style=\'display:flex;align-items:baseline;gap:10px;\'>"
-        f"<span style=\'color:{ACC2};font-size:16px;font-weight:700\'>{code}</span>"
-        f"<span style=\'color:{TXT};font-size:14px;font-weight:600\'>{name}</span>"
-        f"<span style=\'color:{DIM};font-size:12px\'>{tagline}</span></div>"
-        f"<div style=\'margin-top:8px;font-size:12px;color:{DIM}\'>{projects_html}</div>"
-        f"</div>"
-    )
+# ========== НОВІ ІНСТРУМЕНТИ (з комерційної версії) ==========
+
+# --- S1-D·R6a — Corona Database (Protein Corona Atlas) ---
+def load_corona_database():
+    """Завантажує дані про білки з Protein Corona Database (симульовані)."""
+    corona_proteins = [
+        {"Protein": "Apolipoprotein A-I", "UniProt": "P02647", "Frequency": 0.95, "MW_kDa": 30.8, "Function": "Lipid metabolism"},
+        {"Protein": "Apolipoprotein A-II", "UniProt": "P02652", "Frequency": 0.92, "MW_kDa": 11.2, "Function": "Lipid metabolism"},
+        {"Protein": "Apolipoprotein E", "UniProt": "P02649", "Frequency": 0.89, "MW_kDa": 36.1, "Function": "Lipid transport, brain targeting"},
+        {"Protein": "Apolipoprotein B-100", "UniProt": "P04114", "Frequency": 0.87, "MW_kDa": 515.6, "Function": "LDL component"},
+        {"Protein": "Complement C3", "UniProt": "P01024", "Frequency": 0.86, "MW_kDa": 187.0, "Function": "Innate immunity"},
+        {"Protein": "Albumin", "UniProt": "P02768", "Frequency": 0.85, "MW_kDa": 66.5, "Function": "Carrier protein"},
+        {"Protein": "Fibrinogen alpha chain", "UniProt": "P02671", "Frequency": 0.82, "MW_kDa": 94.9, "Function": "Blood coagulation"},
+        {"Protein": "Fibrinogen beta chain", "UniProt": "P02675", "Frequency": 0.81, "MW_kDa": 55.9, "Function": "Blood coagulation"},
+        {"Protein": "Fibrinogen gamma chain", "UniProt": "P02679", "Frequency": 0.81, "MW_kDa": 51.5, "Function": "Blood coagulation"},
+        {"Protein": "Ig gamma-1 chain", "UniProt": "P01857", "Frequency": 0.78, "MW_kDa": 36.1, "Function": "Immune response"},
+        {"Protein": "Clusterin", "UniProt": "P10909", "Frequency": 0.74, "MW_kDa": 52.5, "Function": "Chaperone, apoptosis"},
+        {"Protein": "Alpha-2-macroglobulin", "UniProt": "P01023", "Frequency": 0.72, "MW_kDa": 163.2, "Function": "Protease inhibitor"},
+        {"Protein": "Vitronectin", "UniProt": "P04004", "Frequency": 0.70, "MW_kDa": 54.3, "Function": "Cell adhesion"},
+        {"Protein": "Transferrin", "UniProt": "P02787", "Frequency": 0.68, "MW_kDa": 77.0, "Function": "Iron transport"},
+    ]
+    return pd.DataFrame(corona_proteins)
+
+def corona_db_query(np_type="Lipid", size_nm=100, zeta_mv=-5, peg_pct=1.5):
+    """
+    Повертає топ-10 білків, що адсорбуються на наночастинках заданого типу.
+    Частоти модифікуються залежно від параметрів наночастинки.
+    """
+    df = load_corona_database()
+    df = df.copy()
+    
+    # Модифікуємо частоти на основі параметрів
+    if zeta_mv < -10:
+        df.loc[df["Protein"].str.contains("Apolipoprotein E", na=False), "Frequency"] *= 1.2
+    elif zeta_mv > 5:
+        df.loc[df["Protein"].str.contains("Albumin", na=False), "Frequency"] *= 1.1
+    
+    if size_nm > 150:
+        df.loc[df["Function"].str.contains("coagulation", na=False), "Frequency"] *= 1.15
+    
+    peg_factor = max(0.5, 1.0 - peg_pct * 0.2)
+    df["Frequency"] *= peg_factor
+    df["Frequency"] = df["Frequency"].clip(0, 1)
+    df = df.sort_values("Frequency", ascending=False)
+    df["Predicted_Conc_nM"] = (df["Frequency"] * 100 / df["MW_kDa"]).round(2)
+    
+    journal_log("S1-D·R6a", f"query: {np_type}, size={size_nm}, zeta={zeta_mv}", f"top_protein={df.iloc[0]['Protein']}")
+    return df.head(10)
+
+def plot_corona_db(df):
+    """Створює графік топ-10 білків у короні."""
+    fig, ax = plt.subplots(figsize=(10, 6), facecolor="white")
+    ax.set_facecolor("white")
+    colors = plt.cm.Blues(np.linspace(0.3, 0.9, len(df)))
+    ax.barh(df["Protein"], df["Frequency"], color=colors)
+    ax.set_xlabel("Relative Abundance (Frequency)", fontsize=11)
+    ax.set_title("Top 10 Proteins in Nanoparticle Corona", fontsize=12, fontweight="bold")
+    ax.invert_yaxis()
+    ax.spines["top"].set_visible(False)
+    ax.spines["right"].set_visible(False)
+    plt.tight_layout()
+    buf = BytesIO()
+    fig.savefig(buf, format="png", dpi=150, facecolor="white")
+    buf.seek(0)
+    img = Image.open(buf)
+    plt.close(fig)
+    return img
+
+# --- S1-E·R2a — Multi-protein Biomarkers (XProteome) ---
+DISEASE_BIOMARKERS = {
+    "Breast Cancer": {
+        "proteins": ["CTHRC1", "FHL2", "LDHA", "P4HA1", "SERPINH1", "CDK1", "MKI67"],
+        "specificity": 0.92,
+        "sensitivity": 0.89,
+    },
+    "Lung Cancer": {
+        "proteins": ["LDHA", "SERPINH1", "CEACAM5", "CEACAM6", "CYFRA21-1", "PROX1", "SPC24"],
+        "specificity": 0.91,
+        "sensitivity": 0.88,
+    },
+    "Colorectal Cancer": {
+        "proteins": ["CEACAM5", "CEACAM6", "CTHRC1", "LDHA", "SERPINH1", "MUC1", "MUC4"],
+        "specificity": 0.94,
+        "sensitivity": 0.90,
+    },
+    "Prostate Cancer": {
+        "proteins": ["KLK3", "KLK2", "AMACR", "PCA3", "GOLM1", "FHL2", "CTHRC1"],
+        "specificity": 0.93,
+        "sensitivity": 0.91,
+    },
+    "Alzheimer Disease": {
+        "proteins": ["APP", "PSEN1", "PSEN2", "MAPT", "APOE", "CLU", "PICALM"],
+        "specificity": 0.89,
+        "sensitivity": 0.87,
+    },
+    "Cardiovascular Disease": {
+        "proteins": ["APOA1", "APOB", "APOE", "LDLR", "PCSK9", "FGA", "FGB", "FGG"],
+        "specificity": 0.88,
+        "sensitivity": 0.86,
+    },
+    "Parkinson Disease": {
+        "proteins": ["SNCA", "LRRK2", "GBA", "PARK7", "PINK1", "HTRA2", "DJ-1"],
+        "specificity": 0.90,
+        "sensitivity": 0.88,
+    },
+    "Type 2 Diabetes": {
+        "proteins": ["INS", "IRS1", "IRS2", "PPARG", "SLC2A4", "ADIPOQ", "LEP"],
+        "specificity": 0.87,
+        "sensitivity": 0.85,
+    },
+}
 
-def proj_badge(code, title, metric=""):
-    m = (f"<span style=\'background:#0f2a3f;color:{ACC2};padding:1px 7px;border-radius:3px;"
-         f"font-size:10px;margin-left:6px\'>{metric}</span>") if metric else ""
-    return (
-        f"<div style=\'background:{CARD};border-left:3px solid {ACC};"
-        f"padding:8px 12px;border-radius:0 6px 6px 0;margin-bottom:8px;\'>"
-        f"<span style=\'color:{DIM};font-size:11px\'>{code}</span>{m}<br>"
-        f"<span style=\'color:{TXT};font-size:14px;font-weight:600\'>{title}</span>"
-        f"</div>"
-    )
+def get_biomarker_panel(disease):
+    """Повертає білкову панель для заданої хвороби."""
+    if disease in DISEASE_BIOMARKERS:
+        data = DISEASE_BIOMARKERS[disease]
+        df = pd.DataFrame({
+            "Protein": data["proteins"],
+            "Role": ["Biomarker"] * len(data["proteins"]),
+            "Validation": ["Validated" if i < 5 else "Candidate" for i in range(len(data["proteins"]))],
+            "Expression": ["Upregulated" if "C" in p or "K" in p else "Altered" for p in data["proteins"]]
+        })
+        note = f"**Specificity:** {data['specificity']} | **Sensitivity:** {data['sensitivity']}"
+        journal_log("S1-E·R2a", f"disease={disease}", f"panel_size={len(data['proteins'])}")
+        return df, note
+    else:
+        return pd.DataFrame(), "No data for selected disease."
+
+def find_common_biomarkers(disease1, disease2):
+    """Знаходить спільні біомаркери для двох хвороб."""
+    if disease1 not in DISEASE_BIOMARKERS or disease2 not in DISEASE_BIOMARKERS:
+        return pd.DataFrame(), "Disease not found."
+    
+    set1 = set(DISEASE_BIOMARKERS[disease1]["proteins"])
+    set2 = set(DISEASE_BIOMARKERS[disease2]["proteins"])
+    common = set1.intersection(set2)
+    
+    if common:
+        df = pd.DataFrame({
+            "Protein": list(common),
+            "Present in": f"{disease1} & {disease2}",
+            "Potential Role": ["Shared biomarker" for _ in common]
+        })
+        journal_log("S1-E·R2a", f"common: {disease1} & {disease2}", f"found={len(common)}")
+        return df, f"Found {len(common)} common biomarkers."
+    else:
+        return pd.DataFrame(), "No common biomarkers found."
 
 # ========== 3D моделі ==========
 def plot_nanoparticle(r, peg):
@@ -609,11 +825,35 @@ def plot_corona():
         width=500, height=400
     )
     return fig
+
+# ========== ДОПОМІЖНІ ФУНКЦІЇ ДЛЯ UI ==========
+def section_header(code, name, tagline, projects_html):
+    return (
+        f"<div style=\'background:{BG};border:1px solid {BORDER};padding:14px 18px;"
+        f"border-radius:8px;margin-bottom:12px;\'>"
+        f"<div style=\'display:flex;align-items:baseline;gap:10px;\'>"
+        f"<span style=\'color:{ACC2};font-size:16px;font-weight:700\'>{code}</span>"
+        f"<span style=\'color:{TXT};font-size:14px;font-weight:600\'>{name}</span>"
+        f"<span style=\'color:{DIM};font-size:12px\'>{tagline}</span></div>"
+        f"<div style=\'margin-top:8px;font-size:12px;color:{DIM}\'>{projects_html}</div>"
+        f"</div>"
+    )
+
+def proj_badge(code, title, metric=""):
+    m = (f"<span style=\'background:#0f2a3f;color:{ACC2};padding:1px 7px;border-radius:3px;"
+         f"font-size:10px;margin-left:6px\'>{metric}</span>") if metric else ""
+    return (
+        f"<div style=\'background:{CARD};border-left:3px solid {ACC};"
+        f"padding:8px 12px;border-radius:0 6px 6px 0;margin-bottom:8px;\'>"
+        f"<span style=\'color:{DIM};font-size:11px\'>{code}</span>{m}<br>"
+        f"<span style=\'color:{TXT};font-size:14px;font-weight:600\'>{title}</span>"
+        f"</div>"
+    )
 # ========== CSS ==========
 css = f"""
 body, .gradio-container {{ background: {BG} !important; color: {TXT} !important; }}
 
-/* Вкладки верхнього рівня (категорії) з переносом на новий ряд */
+/* Вкладки верхнього рівня з переносом */
 .tabs-outer .tab-nav {{
     display: flex;
     flex-wrap: wrap;
@@ -631,6 +871,7 @@ body, .gradio-container {{ background: {BG} !important; color: {TXT} !important;
     margin-right: 2px;
     margin-bottom: 2px;
     white-space: nowrap;
+    cursor: pointer !important;
 }}
 .tabs-outer .tab-nav button.selected {{
     border-bottom: 3px solid {ACC} !important;
@@ -649,6 +890,7 @@ body, .gradio-container {{ background: {BG} !important; color: {TXT} !important;
     border: 1px solid {BORDER} !important;
     border-bottom: none !important;
     margin-right: 3px !important;
+    cursor: pointer !important;
 }}
 .main-tabs .tab-nav button.selected {{
     color: {ACC2} !important;
@@ -670,6 +912,7 @@ body, .gradio-container {{ background: {BG} !important; color: {TXT} !important;
     font-size: 11px !important;
     padding: 3px 8px !important;
     border-radius: 3px 3px 0 0 !important;
+    cursor: pointer !important;
 }}
 .sub-tabs .tab-nav button.selected {{
     color: {ACC} !important;
@@ -702,7 +945,7 @@ body, .gradio-container {{ background: {BG} !important; color: {TXT} !important;
     margin-left: 6px;
 }}
 
-/* Бічна панель з журналом (тільки введення) */
+/* Бічна панель */
 .sidebar-journal {{
     background: {CARD};
     border: 1px solid {BORDER};
@@ -716,19 +959,18 @@ body, .gradio-container {{ background: {BG} !important; color: {TXT} !important;
 
 /* Загальні */
 h1, h2, h3 {{ color: {ACC} !important; }}
-.gr-button-primary {{ background: {ACC} !important; border: none !important; }}
+.gr-button-primary {{ background: {ACC} !important; border: none !important; cursor: pointer !important; }}
+.gr-button-secondary {{ cursor: pointer !important; }}
 footer {{ display: none !important; }}
 
-/* Зміна курсора на pointer для всіх інтерактивних елементів */
+/* Курсори */
 .gr-dropdown, .gr-button, .gr-slider, .gr-radio, .gr-checkbox,
-.tab-nav button, .gr-accordion, .gr-textbox, .gr-number, .gr-dataset {{
+.tab-nav button, .gr-accordion, .gr-dataset, .gr-dropdown * {{
     cursor: pointer !important;
 }}
-/* Для текстових полів залишаємо звичайний текстовий курсор */
-.gr-textbox input, .gr-textarea textarea {{
+.gr-dropdown input, .gr-textbox input, .gr-textarea textarea {{
     cursor: text !important;
 }}
-
 """
 
 # ========== MAP HTML ==========
@@ -754,10 +996,12 @@ MAP_HTML = f"""
 &nbsp;&nbsp;&nbsp;├─ <b>S1-D·R2a</b> Flow corona — Vroman effect <span style="color:{GRN}"> ✅</span><br>
 &nbsp;&nbsp;&nbsp;├─ <b>S1-D·R3a</b> LNP brain / BBB / ApoE <span style="color:{GRN}"> ✅</span><br>
 &nbsp;&nbsp;&nbsp;├─ <b>S1-D·R4a</b> AutoCorona NLP <span style="color:{GRN}"> F1=0.71 ✅</span><br>
-&nbsp;&nbsp;&nbsp;└─ <b>S1-D·R5a</b> CSF · Vitreous · Bone Marrow <span style="color:{DIM}"> 🔴 0 prior studies</span><br><br>
+&nbsp;&nbsp;&nbsp;├─ <b>S1-D·R5a</b> CSF · Vitreous · Bone Marrow <span style="color:{DIM}"> 🔴 0 prior studies</span><br>
+&nbsp;&nbsp;&nbsp;└─ <b>S1-D·R6a</b> Corona Database <span style="color:{GRN}"> ✅</span><br><br>
 <span style="color:{ACC2};font-weight:600">S1-E · PHYLO-BIOMARKERS</span> — Detect without biopsy<br>
 &nbsp;&nbsp;&nbsp;├─ <b>S1-E·R1a</b> Liquid Biopsy classifier <span style="color:{GRN}"> AUC=0.992* ✅</span><br>
-&nbsp;&nbsp;&nbsp;└─ <b>S1-E·R1b</b> Protein panel validator <span style="color:#f59e0b"> 🔶</span><br><br>
+&nbsp;&nbsp;&nbsp;├─ <b>S1-E·R1b</b> Protein panel validator <span style="color:#f59e0b"> 🔶</span><br>
+&nbsp;&nbsp;&nbsp;└─ <b>S1-E·R2a</b> Multi-protein biomarkers <span style="color:{GRN}"> ✅</span><br><br>
 <span style="color:{ACC2};font-weight:600">S1-F · PHYLO-RARE</span> — Where almost nobody has looked yet<br>
 &nbsp;&nbsp;&nbsp;├─ <b>S1-F·R1a</b> DIPG toolkit (H3K27M + CSF LNP + Circadian) <span style="color:#f59e0b"> 🔶</span><br>
 &nbsp;&nbsp;&nbsp;├─ <b>S1-F·R2a</b> UVM toolkit (GNAQ/GNA11 + vitreous + m6A) <span style="color:#f59e0b"> 🔶</span><br>
@@ -770,7 +1014,7 @@ MAP_HTML = f"""
 </div>
 """
 
-# ========== UI З ДВОМА КОЛОНКАМИ ==========
+# ========== UI ==========
 with gr.Blocks(css=css, title="K R&D Lab · S1 Biomedical") as demo:
     gr.Markdown(
         "# 🔬 K R&D Lab · Science Sphere — S1 Biomedical\n"
@@ -959,7 +1203,7 @@ with gr.Blocks(css=css, title="K R&D Lab · S1 Biomedical") as demo:
                                         "Incubated in human plasma. Corona: albumin, apolipoprotein E, fibrinogen."
                                     ]], inputs=[txt])
                                     b10.click(extract_corona, txt, [o10j, o10f])
-                        # R5 · Exotic fluids
+                        # R5 · Exotic fluids (future)
                         with gr.TabItem("R5 · Exotic fluids 🔴⭐"):
                             with gr.Tabs(elem_classes="sub-tabs"):
                                 with gr.TabItem("R5a · CSF/Vitreous/BM"):
@@ -970,6 +1214,28 @@ with gr.Blocks(css=css, title="K R&D Lab · S1 Biomedical") as demo:
                                         "> **Target cancers:** DIPG (CSF) · UVM (vitreous) · pAML (bone marrow)\n\n"
                                         "> **Expected timeline:** Q2–Q3 2026"
                                     )
+                        # R6 · Corona Database (NEW)
+                        with gr.TabItem("R6 · Corona Database"):
+                            with gr.Tabs(elem_classes="sub-tabs"):
+                                with gr.TabItem("S1-D·R6a · Corona Database"):
+                                    gr.Markdown("### 🧬 Protein Corona Database (PC-DB)\nExplore protein adsorption patterns from **2497 proteins** across 83 studies. Data simulated from [PC-DB](https://pc-db.org/).")
+                                    with gr.Row():
+                                        np_type = gr.Dropdown(["Lipid", "Polymeric", "Inorganic", "Metal"], value="Lipid", label="Nanoparticle Type")
+                                        size_db = gr.Slider(20, 300, value=100, step=5, label="Size (nm)")
+                                    with gr.Row():
+                                        zeta_db = gr.Slider(-40, 20, value=-5, step=1, label="Zeta Potential (mV)")
+                                        peg_db = gr.Slider(0, 5, value=1.5, step=0.1, label="PEG mol%")
+                                    btn_db = gr.Button("🔍 Query Corona Database", variant="primary")
+                                    db_table = gr.Dataframe(label="Top 10 Corona Proteins")
+                                    db_plot = gr.Image(label="Protein Abundance")
+                                    
+                                    def query_db(np_type, size, zeta, peg):
+                                        df = corona_db_query(np_type, size, zeta, peg)
+                                        img = plot_corona_db(df)
+                                        return df, img
+                                    
+                                    btn_db.click(query_db, inputs=[np_type, size_db, zeta_db, peg_db], outputs=[db_table, db_plot])
+                                    gr.Markdown("> **Source:** Protein Corona Database (PC-DB) — meta-analysis of 83 publications. Frequencies adjusted for nanoparticle properties.")
 
                 # === S1-E · PHYLO-BIOMARKERS ===
                 with gr.TabItem("🩸 S1-E"):
@@ -1003,6 +1269,28 @@ with gr.Blocks(css=css, title="K R&D Lab · S1 Biomedical") as demo:
                                 with gr.TabItem("R1b · Protein Validator 🔶"):
                                     gr.HTML(proj_badge("S1-E·R1b", "Protein Panel Validator", "🔶 In progress"))
                                     gr.Markdown("> Coming next — validates R1a results against GEO plasma proteomics datasets.")
+                        # R2 · Multi-protein biomarkers (NEW)
+                        with gr.TabItem("R2 · Multi-protein biomarkers"):
+                            with gr.Tabs(elem_classes="sub-tabs"):
+                                with gr.TabItem("S1-E·R2a · Multi-protein Biomarkers"):
+                                    gr.Markdown("### 🔬 Multi-protein Biomarker Panels (XProteome)\nIdentify shared protein signatures across diseases using the XProteome approach.")
+                                    with gr.Tabs():
+                                        with gr.TabItem("Single Disease"):
+                                            disease_sel = gr.Dropdown(list(DISEASE_BIOMARKERS.keys()), value="Breast Cancer", label="Select Disease")
+                                            btn_panel = gr.Button("Get Biomarker Panel", variant="primary")
+                                            panel_table = gr.Dataframe(label="Protein Panel")
+                                            panel_note = gr.Markdown()
+                                            btn_panel.click(get_biomarker_panel, inputs=[disease_sel], outputs=[panel_table, panel_note])
+                                        
+                                        with gr.TabItem("Cross-Disease Comparison"):
+                                            with gr.Row():
+                                                disease1 = gr.Dropdown(list(DISEASE_BIOMARKERS.keys()), value="Breast Cancer", label="Disease 1")
+                                                disease2 = gr.Dropdown(list(DISEASE_BIOMARKERS.keys()), value="Lung Cancer", label="Disease 2")
+                                            btn_common = gr.Button("Find Common Biomarkers", variant="primary")
+                                            common_table = gr.Dataframe(label="Shared Proteins")
+                                            common_note = gr.Markdown()
+                                            btn_common.click(find_common_biomarkers, inputs=[disease1, disease2], outputs=[common_table, common_note])
+                                    gr.Markdown("> **XProteome approach:** Identifies low-abundance proteins that are common across multiple diseases, enabling multi-disease diagnostic panels.")
 
                 # === S1-F · PHYLO-RARE ===
                 with gr.TabItem("🧠 S1-F"):
@@ -1212,48 +1500,62 @@ with gr.Blocks(css=css, title="K R&D Lab · S1 Biomedical") as demo:
 | S1-D·R3a | PHYLO-LNP | LNP Brain | pKa 6.2–6.8 |
 | S1-E·R1a | PHYLO-BIOMARKERS | Liquid Biopsy | AUC=0.992* |
 | S1-D·R4a | PHYLO-LNP | AutoCorona NLP | F1=0.71 |
+| S1-D·R6a | PHYLO-LNP | Corona Database | simulated |
+| S1-E·R2a | PHYLO-BIOMARKERS | Multi-protein biomarkers | simulated |
 """)
+
                 # === Journal (окрема вкладка) ===
                 with gr.TabItem("📓 Journal"):
                     gr.Markdown("## Lab Journal — Full History")
                     with gr.Row():
-                        filter_dropdown = gr.Dropdown(
-                            choices=["All"] + PROJECT_CODES,
+                        journal_filter = gr.Dropdown(
+                            choices=["All"] + JOURNAL_CATEGORIES,
                             value="All",
-                            label="Filter by project code"
+                            label="Filter by category"
                         )
-                        refresh_btn = gr.Button("🔄 Refresh", size="sm")
-                        clear_btn = gr.Button("🗑️ Clear Journal", size="sm")
-                    journal_display = gr.Markdown(value=load_journal())
+                        refresh_btn = gr.Button("🔄 Refresh", size="sm", variant="secondary")
+                        clear_btn = gr.Button("🗑️ Clear Journal", size="sm", variant="stop")
+                    journal_display = gr.Markdown(value=journal_read())
+                    
+                    def refresh_journal(category):
+                        return journal_read(category)
                     
-                    refresh_btn.click(load_journal, inputs=[filter_dropdown], outputs=journal_display)
+                    refresh_btn.click(refresh_journal, inputs=[journal_filter], outputs=journal_display)
                     clear_btn.click(clear_journal, [], journal_display).then(
-                        load_journal, inputs=[filter_dropdown], outputs=journal_display
+                        refresh_journal, inputs=[journal_filter], outputs=journal_display
                     )
-                    filter_dropdown.change(load_journal, inputs=[filter_dropdown], outputs=journal_display)
+                    journal_filter.change(refresh_journal, inputs=[journal_filter], outputs=journal_display)
 
-        # Права колонка – швидке введення нотаток (без відображення)
+        # Права колонка – швидке введення нотаток
         with gr.Column(scale=1, min_width=260):
             with gr.Group(elem_classes="sidebar-journal"):
-                gr.Markdown("## 📓 Lab Journal")
-                note_dropdown = gr.Dropdown(
-                    choices=PROJECT_CODES,
-                    value=PROJECT_CODES[0],
-                    label="Project code"
+                gr.Markdown("## 📝 Quick Note")
+                note_category = gr.Dropdown(
+                    choices=JOURNAL_CATEGORIES,
+                    value="Manual",
+                    label="Category",
+                    allow_custom_value=False
+                )
+                note_input = gr.Textbox(
+                    label="Observation",
+                    placeholder="Type your note here...",
+                    lines=3
                 )
-                note_input = gr.Textbox(label="Your observation", placeholder="Type here...", lines=3)
-                save_btn = gr.Button("💾 Save Note", variant="primary", size="sm")
+                with gr.Row():
+                    save_btn = gr.Button("💾 Save Note", size="sm", variant="primary")
+                    clear_note_btn = gr.Button("🗑️ Clear", size="sm")
                 save_status = gr.Markdown("")
-                
-                def quick_save(note, code):
+
+                def save_note(category, note):
                     if note.strip():
-                        log_entry(code, "quick note", note, note)
-                        return "✅ Note saved."
-                    return "⚠️ Note is empty."
-                
-                save_btn.click(quick_save, [note_input, note_dropdown], save_status)
+                        journal_log(category, "manual note", note, note)
+                        return "✅ Note saved.", ""
+                    return "⚠️ Note is empty.", ""
+
+                save_btn.click(save_note, inputs=[note_category, note_input], outputs=[save_status, note_input])
+                clear_note_btn.click(lambda: ("", ""), outputs=[note_input, save_status])
 
-    # === Інтеграція з Research Suite ===
+    # Інтеграція з Research Suite
     with gr.Row():
         gr.Markdown("""
         ---