Upload 2 files

app.py

@@ -0,0 +1,496 @@
+import gradio as gr
+import pandas as pd
+import numpy as np
+import json
+import re
+import matplotlib
+matplotlib.use("Agg")
+import matplotlib.pyplot as plt
+import matplotlib.patches as mpatches
+from io import BytesIO
+from PIL import Image
+
+# ── Shared theme colours ──────────────────────────────────────────────────────
+BG   = "#0f172a"
+CARD = "#1e293b"
+ACC  = "#f97316"
+ACC2 = "#38bdf8"
+TXT  = "#f1f5f9"
+
+# ══════════════════════════════════════════════════════════════════════════════
+# TAB 1 — BRCA2 miRNA  (A1)
+# ══════════════════════════════════════════════════════════════════════════════
+MIRNA_DB = {
+    "BRCA2": [
+        {"miRNA":"hsa-miR-148a-3p","log2FC":-0.70,"padj":0.013,"targets":"DNMT1, AKT2","pathway":"Epigenetic reprogramming"},
+        {"miRNA":"hsa-miR-30e-5p", "log2FC":-0.49,"padj":0.032,"targets":"MYC, KRAS","pathway":"Oncogene suppression"},
+        {"miRNA":"hsa-miR-551b-3p","log2FC":-0.59,"padj":0.048,"targets":"SMAD4, CDK6","pathway":"TGF-β / CDK4/6"},
+        {"miRNA":"hsa-miR-22-3p",  "log2FC":-0.43,"padj":0.041,"targets":"HIF1A, PTEN","pathway":"Hypoxia / PI3K"},
+        {"miRNA":"hsa-miR-200c-3p","log2FC":-0.38,"padj":0.044,"targets":"ZEB1, ZEB2","pathway":"EMT suppression"},
+    ],
+    "BRCA1": [
+        {"miRNA":"hsa-miR-155-5p", "log2FC":-0.81,"padj":0.008,"targets":"SHIP1, SOCS1","pathway":"Immune evasion"},
+        {"miRNA":"hsa-miR-146a-5p","log2FC":-0.65,"padj":0.019,"targets":"TRAF6, IRAK1","pathway":"NF-κB signalling"},
+        {"miRNA":"hsa-miR-21-5p",  "log2FC":-0.55,"padj":0.027,"targets":"PTEN, PDCD4","pathway":"Apoptosis"},
+        {"miRNA":"hsa-miR-17-5p",  "log2FC":-0.47,"padj":0.036,"targets":"RB1, E2F1","pathway":"Cell cycle"},
+        {"miRNA":"hsa-miR-34a-5p", "log2FC":-0.41,"padj":0.049,"targets":"BCL2, CDK6","pathway":"p53 axis"},
+    ],
+    "TP53": [
+        {"miRNA":"hsa-miR-34a-5p", "log2FC":-1.10,"padj":0.001,"targets":"BCL2, CDK6","pathway":"p53-miR-34 axis"},
+        {"miRNA":"hsa-miR-192-5p", "log2FC":-0.90,"padj":0.005,"targets":"MDM2, DHFR","pathway":"p53 feedback"},
+        {"miRNA":"hsa-miR-145-5p", "log2FC":-0.75,"padj":0.012,"targets":"MYC, EGFR","pathway":"Growth suppression"},
+        {"miRNA":"hsa-miR-107",    "log2FC":-0.62,"padj":0.023,"targets":"CDK6, HIF1B","pathway":"Hypoxia / cell cycle"},
+        {"miRNA":"hsa-miR-215-5p", "log2FC":-0.51,"padj":0.038,"targets":"DTL, DHFR","pathway":"DNA damage response"},
+    ],
+}
+
+def predict_mirna(gene):
+    rows = MIRNA_DB.get(gene, [])
+    df = pd.DataFrame(rows)
+    return df
+
+# ══════════════════════════════════════════════════════════════════════════════
+# TAB 2 — TP53 siRNA  (A2)
+# ══════════════════════════════════════════════════════════════════════════════
+SIRNA_DB = {
+    "LUAD": [
+        {"Gene":"SPC24","ΔCERES":-0.175,"log2FC":1.13,"Drug status":"Novel","siRNA":"GCAGCUGAAGAAACUGAAU"},
+        {"Gene":"BUB1B","ΔCERES":-0.119,"log2FC":1.12,"Drug status":"Novel","siRNA":"CCAAAGAGCUGAAGAACAU"},
+        {"Gene":"CDC45","ΔCERES":-0.144,"log2FC":1.26,"Drug status":"Novel","siRNA":"GCAUCAAGAUGAAGGAGAU"},
+        {"Gene":"PLK1", "ΔCERES":-0.239,"log2FC":1.03,"Drug status":"Clinical","siRNA":"GACGCUCAAGAUGCAGAUU"},
+        {"Gene":"CDK1", "ΔCERES":-0.201,"log2FC":1.00,"Drug status":"Clinical","siRNA":"GCAGAAGCACUGAAGAUUU"},
+    ],
+    "BRCA": [
+        {"Gene":"AURKA","ΔCERES":-0.165,"log2FC":1.20,"Drug status":"Clinical","siRNA":"GCACUGAAGAUGCAGAAUU"},
+        {"Gene":"AURKB","ΔCERES":-0.140,"log2FC":1.15,"Drug status":"Clinical","siRNA":"CCUGAAGACGCUCAAGGUU"},
+        {"Gene":"CENPW","ΔCERES":-0.125,"log2FC":0.95,"Drug status":"Novel","siRNA":"GCAGAAGCACUGAAGAUUU"},
+        {"Gene":"RFC2", "ΔCERES":-0.136,"log2FC":0.50,"Drug status":"Novel","siRNA":"GCAAGAUGCAGAAGCACUU"},
+        {"Gene":"TYMS", "ΔCERES":-0.131,"log2FC":0.72,"Drug status":"Approved","siRNA":"GGACGCUCAAGAUGCAGAU"},
+    ],
+    "COAD": [
+        {"Gene":"KRAS", "ΔCERES":-0.210,"log2FC":0.80,"Drug status":"Clinical","siRNA":"GCUGGAGCUGGUGGUAGUU"},
+        {"Gene":"WEE1", "ΔCERES":-0.180,"log2FC":1.05,"Drug status":"Clinical","siRNA":"GCAGCUGAAGAAACUGAAU"},
+        {"Gene":"CHEK1","ΔCERES":-0.155,"log2FC":0.90,"Drug status":"Clinical","siRNA":"CCAAAGAGCUGAAGAACAU"},
+        {"Gene":"RFC2", "ΔCERES":-0.130,"log2FC":0.55,"Drug status":"Novel","siRNA":"GCAUCAAGAUGAAGGAGAU"},
+        {"Gene":"PKMYT1","ΔCERES":-0.122,"log2FC":1.07,"Drug status":"Clinical","siRNA":"GACGCUCAAGAUGCAGAUU"},
+    ],
+}
+
+def predict_sirna(cancer):
+    return pd.DataFrame(SIRNA_DB.get(cancer, []))
+
+# ══════════════════════════════════════════════════════════════════════════════
+# TAB 3 — lncRNA-TREM2  (A3)
+# ══════════════════════════════════════════════════════════════════════════════
+LNCRNA_DATA = {
+    "ceRNA_network": [
+        {"lncRNA":"CYTOR","miRNA":"hsa-miR-138-5p","target":"AKT1","pathway":"TREM2 core signaling"},
+        {"lncRNA":"CYTOR","miRNA":"hsa-miR-138-5p","target":"NFKB1","pathway":"Neuroinflammation"},
+        {"lncRNA":"GAS5","miRNA":"hsa-miR-21-5p","target":"PTEN","pathway":"Neuroinflammation"},
+        {"lncRNA":"GAS5","miRNA":"hsa-miR-222-3p","target":"IL1B","pathway":"Neuroinflammation"},
+        {"lncRNA":"HOTAIRM1","miRNA":"hsa-miR-9-5p","target":"TREM2","pathway":"Direct TREM2 regulation"},
+    ],
+    "aso_candidates": [
+        {"lncRNA":"GAS5","position":119,"accessibility":0.653,"GC_pct":50,"Tm":47.2,"priority":"HIGH"},
+        {"lncRNA":"CYTOR","position":507,"accessibility":0.653,"GC_pct":50,"Tm":46.8,"priority":"HIGH"},
+        {"lncRNA":"HOTAIRM1","position":234,"accessibility":0.621,"GC_pct":44,"Tm":44.1,"priority":"MEDIUM"},
+        {"lncRNA":"LINC00847","position":89,"accessibility":0.598,"GC_pct":56,"Tm":48.3,"priority":"MEDIUM"},
+        {"lncRNA":"ZFAS1","position":312,"accessibility":0.571,"GC_pct":48,"Tm":45.5,"priority":"MEDIUM"},
+    ]
+}
+
+def get_lncrna():
+    return pd.DataFrame(LNCRNA_DATA["ceRNA_network"]), pd.DataFrame(LNCRNA_DATA["aso_candidates"])
+
+# ══════════════════════════════════════════════════════════════════════════════
+# TAB 4 — FGFR3 RNA Drug  (A4)
+# ══════════════════════════════════════════════════════════════════════════════
+FGFR3_COMPOUNDS = {
+    "P1 (hairpin loop)": [
+        {"Compound":"CHEMBL1575701","RNA_score":0.809,"Toxicity":0.01,"Final_score":0.793,"MW":342.4,"logP":2.1},
+        {"Compound":"CHEMBL15727",  "RNA_score":0.805,"Toxicity":0.00,"Final_score":0.789,"MW":298.3,"logP":1.8},
+        {"Compound":"Thioguanine",  "RNA_score":0.888,"Toxicity":32.5,"Final_score":0.742,"MW":167.2,"logP":-1.2},
+        {"Compound":"Deazaguanine", "RNA_score":0.888,"Toxicity":35.0,"Final_score":0.735,"MW":151.2,"logP":-0.9},
+        {"Compound":"CHEMBL441",    "RNA_score":0.775,"Toxicity":5.2, "Final_score":0.721,"MW":312.4,"logP":2.4},
+    ],
+    "P10 (G-quadruplex)": [
+        {"Compound":"CHEMBL15727",  "RNA_score":0.805,"Toxicity":0.00,"Final_score":0.789,"MW":298.3,"logP":1.8},
+        {"Compound":"CHEMBL5411515","RNA_score":0.945,"Toxicity":37.1,"Final_score":0.761,"MW":415.5,"logP":3.2},
+        {"Compound":"CHEMBL90",     "RNA_score":0.760,"Toxicity":2.1, "Final_score":0.745,"MW":267.3,"logP":1.5},
+        {"Compound":"CHEMBL102",    "RNA_score":0.748,"Toxicity":8.4, "Final_score":0.712,"MW":388.4,"logP":2.8},
+        {"Compound":"Berberine",    "RNA_score":0.735,"Toxicity":3.2, "Final_score":0.708,"MW":336.4,"logP":1.3},
+    ],
+}
+
+def predict_drug(pocket):
+    df = pd.DataFrame(FGFR3_COMPOUNDS.get(pocket, []))
+    fig, ax = plt.subplots(figsize=(6,4), facecolor=CARD)
+    ax.set_facecolor(CARD)
+    bars = ax.barh(df["Compound"], df["Final_score"], color=ACC)
+    ax.set_xlabel("Final Score", color=TXT)
+    ax.tick_params(colors=TXT)
+    for spine in ax.spines.values(): spine.set_edgecolor("#334155")
+    ax.set_title(f"Top compounds — {pocket}", color=TXT, fontsize=10)
+    plt.tight_layout()
+    buf = BytesIO(); plt.savefig(buf, format="png", dpi=120, facecolor=CARD); plt.close()
+    buf.seek(0); return df, Image.open(buf)
+
+# ══════════════════════════════════════════════════════════════════════════════
+# TAB 5 — OpenVariant  (A5) ← STAR TOOL
+# ══════════════════════════════════════════════════════════════════════════════
+VARIANT_DB = {
+    "BRCA1:p.R1699Q": {"score":0.03,"class":"Benign","confidence":"High","sift":0.82,"polyphen":0.05,"gnomad":0.0012,"domain":False},
+    "BRCA1:p.R1699W": {"score":0.97,"class":"Pathogenic","confidence":"High","sift":0.00,"polyphen":0.99,"gnomad":0.0,"domain":True},
+    "BRCA2:p.D2723A": {"score":0.999,"class":"Pathogenic","confidence":"High","sift":0.01,"polyphen":0.98,"gnomad":0.0,"domain":True},
+    "TP53:p.R248W":   {"score":0.998,"class":"Pathogenic","confidence":"High","sift":0.00,"polyphen":1.00,"gnomad":0.0,"domain":True},
+    "TP53:p.R248Q":   {"score":0.995,"class":"Pathogenic","confidence":"High","sift":0.01,"polyphen":0.99,"gnomad":0.0,"domain":True},
+    "EGFR:p.L858R":   {"score":0.96,"class":"Pathogenic","confidence":"High","sift":0.00,"polyphen":0.97,"gnomad":0.0,"domain":True},
+    "ALK:p.F1174L":   {"score":0.94,"class":"Pathogenic","confidence":"High","sift":0.02,"polyphen":0.95,"gnomad":0.0,"domain":True},
+}
+
+PLAIN_LANGUAGE = {
+    "Pathogenic": "⚠️ This variant is likely to cause disease. It disrupts a critical protein region. Clinical follow-up is strongly recommended.",
+    "Likely Pathogenic": "⚠️ This variant is probably harmful. Evidence suggests it impairs protein function. Discuss with your doctor.",
+    "Benign": "✅ This variant is likely harmless. It is common in the general population and does not disrupt protein function.",
+    "Likely Benign": "✅ This variant is probably harmless. Limited evidence, but no strong reason for concern.",
+}
+
+def predict_variant(hgvs, sift, polyphen, gnomad):
+    hgvs = hgvs.strip()
+    if hgvs in VARIANT_DB:
+        r = VARIANT_DB[hgvs]
+    else:
+        # Rule-based fallback
+        score = 0.0
+        if sift < 0.05: score += 0.4
+        if polyphen > 0.85: score += 0.35
+        if gnomad < 0.0001: score += 0.25
+        r = {"score": round(score,3),
+             "class": "Pathogenic" if score>0.6 else ("Likely Pathogenic" if score>0.4 else "Benign"),
+             "confidence": "High" if (sift<0.01 or sift>0.9) else "Moderate"}
+
+    cls, conf, score = r["class"], r["confidence"], r["score"]
+    colour = "#ef4444" if "Pathogenic" in cls else "#22c55e"
+    bar_html = f"""<div style='background:{CARD};padding:16px;border-radius:8px;font-family:monospace;color:{TXT}'>
+    <h3 style='color:{colour}'>{cls}</h3>
+    <p>Score: <b>{score:.3f}</b> &nbsp;|&nbsp; Confidence: <b>{conf}</b></p>
+    <div style='background:#334155;border-radius:4px;height:16px;width:100%'>
+      <div style='background:{colour};height:16px;border-radius:4px;width:{int(score*100)}%'></div>
+    </div>
+    <p style='margin-top:12px'>{PLAIN_LANGUAGE.get(cls,"")}</p>
+    </div>"""
+    return bar_html
+
+# ══════════════════════════════════════════════════════════════════════════════
+# TAB 6 — LNP Corona ML  (B1)
+# ══════════════════════════════════════════════════════════════════════════════
+def predict_corona(size, zeta, peg, lipid):
+    score = 0
+    if lipid == "Ionizable": score += 2
+    elif lipid == "Cationic": score += 1
+    if abs(zeta) < 10: score += 1
+    if peg > 1.5: score += 2
+    if size < 100: score += 1
+    proteins = ["ApoE","Albumin","Fibrinogen","Vitronectin","ApoA-I"]
+    dominant = proteins[min(score, 4)]
+    efficacy = "High" if score >= 4 else "Medium" if score >= 2 else "Low"
+    return f"**Dominant corona protein:** {dominant}
+
+**Predicted efficacy class:** {efficacy}
+
+**Score:** {score}/6"
+
+# ══════════════════════════════════════════════════════════════════════════════
+# TAB 7 — Cancer Liquid Biopsy  (B2)
+# ══════════════════════════════════════════════════════════════════════════════
+BIOMARKER_WEIGHTS = {"CTHRC1":0.18,"FHL2":0.15,"LDHA":0.14,"P4HA1":0.13,
+                     "SERPINH1":0.12,"ABCA8":-0.11,"CA4":-0.10,"CKB":-0.09,
+                     "NNMT":0.08,"CACNA2D2":-0.07}
+
+def predict_cancer(cthrc1,fhl2,ldha,p4ha1,serpinh1,abca8,ca4,ckb,nnmt,cacna2d2):
+    vals = [cthrc1,fhl2,ldha,p4ha1,serpinh1,abca8,ca4,ckb,nnmt,cacna2d2]
+    names = list(BIOMARKER_WEIGHTS.keys())
+    weights = list(BIOMARKER_WEIGHTS.values())
+    score = sum(v*w for v,w in zip(vals,weights))
+    prob = 1/(1+np.exp(-score*2))
+    label = "🔴 CANCER" if prob>0.5 else "🟢 HEALTHY"
+    conf = abs(prob-0.5)*2
+    fig,ax = plt.subplots(figsize=(6,3.5),facecolor=CARD)
+    ax.set_facecolor(CARD)
+    contribs = [v*w for v,w in zip(vals,weights)]
+    colours = [ACC if c>0 else ACC2 for c in contribs]
+    ax.barh(names,contribs,color=colours)
+    ax.axvline(0,color=TXT,linewidth=0.8)
+    ax.set_xlabel("Contribution to cancer score",color=TXT)
+    ax.tick_params(colors=TXT,labelsize=8)
+    for sp in ax.spines.values(): sp.set_edgecolor("#334155")
+    ax.set_title("Protein contributions",color=TXT,fontsize=10)
+    plt.tight_layout()
+    buf=BytesIO(); plt.savefig(buf,format="png",dpi=120,facecolor=CARD); plt.close()
+    buf.seek(0)
+    result = f"**{label}**
+
+Probability: {prob:.2f} | Confidence: {conf:.2f}"
+    return result, Image.open(buf)
+
+# ══════════════════════════════════════════════════════════════════════════════
+# TAB 8 — Corona Flow  (B3)
+# ══════════════════════════════════════════════════════════════════════════════
+def predict_flow(size, zeta, peg, charge, flow_rate):
+    csi = (flow_rate/40)*0.6 + (peg/5)*0.2 + (1 if charge=="Cationic" else 0)*0.2
+    csi = round(min(csi,1.0),3)
+    stability = "🔴 High remodeling" if csi>0.6 else "🟡 Medium" if csi>0.3 else "🟢 Stable"
+    t = np.linspace(0,60,200)
+    k_fast_s = 0.03*(1+flow_rate/40)
+    k_slow_s = 0.005*(1+flow_rate/80)
+    alb_static  = 60*np.exp(-0.03*t)+20
+    alb_flow    = 60*np.exp(-k_fast_s*t)+10
+    apoe_static = 5*(1-np.exp(-0.005*t))+5
+    apoe_flow   = 5*(1-np.exp(-k_slow_s*t))+10
+    fig,ax = plt.subplots(figsize=(6,3.5),facecolor=CARD)
+    ax.set_facecolor(CARD)
+    ax.plot(t,alb_static, color="#60a5fa",ls="--",label="Albumin (static)")
+    ax.plot(t,alb_flow,   color="#60a5fa",label="Albumin (flow)")
+    ax.plot(t,apoe_static,color=ACC,      ls="--",label="ApoE (static)")
+    ax.plot(t,apoe_flow,  color=ACC,      label="ApoE (flow)")
+    ax.set_xlabel("Time (min)",color=TXT); ax.set_ylabel("% Corona",color=TXT)
+    ax.tick_params(colors=TXT); ax.legend(fontsize=7,labelcolor=TXT,facecolor=CARD)
+    for sp in ax.spines.values(): sp.set_edgecolor("#334155")
+    ax.set_title("Vroman Effect: Albumin → ApoE exchange",color=TXT,fontsize=9)
+    plt.tight_layout()
+    buf=BytesIO(); plt.savefig(buf,format="png",dpi=120,facecolor=CARD); plt.close()
+    buf.seek(0)
+    return f"**Corona Shift Index: {csi}** → {stability}", Image.open(buf)
+
+# ══════════════════════════════════════════════════════════════════════════════
+# TAB 9 — LNP Brain Delivery  (B4)
+# ══════════════════════════════════════════════════════════════════════════════
+def predict_bbb(smiles, pka, zeta):
+    mw = len(smiles)*5 + 200
+    logp = smiles.count("C")*0.3 - smiles.count("O")*0.5 + 1.5
+    apoe_pct = max(0, min(40, (7.0-pka)*8 + abs(zeta)*0.5 + logp*0.8))
+    bbb_prob  = min(0.95, apoe_pct/30)
+    tier = "🟢 HIGH (>20%)" if apoe_pct>20 else "🟡 MEDIUM (10-20%)" if apoe_pct>10 else "🔴 LOW (<10%)"
+    categories=["ApoE %","BBB Prob","logP fit","pKa fit","Zeta fit"]
+    vals=[apoe_pct/40, bbb_prob, min(logp/5,1), (7-abs(pka-6.5))/7, (10-abs(zeta))/10]
+    fig,ax=plt.subplots(figsize=(5,4),subplot_kw={"polar":True},facecolor=CARD)
+    ax.set_facecolor(CARD)
+    angles=np.linspace(0,2*np.pi,len(categories),endpoint=False).tolist()
+    vals_plot=vals+[vals[0]]; angles=angles+[angles[0]]
+    ax.plot(angles,vals_plot,color=ACC,linewidth=2)
+    ax.fill(angles,vals_plot,color=ACC,alpha=0.2)
+    ax.set_xticks(angles[:-1]); ax.set_xticklabels(categories,color=TXT,fontsize=8)
+    ax.tick_params(colors=TXT); ax.set_facecolor(CARD)
+    plt.tight_layout()
+    buf=BytesIO(); plt.savefig(buf,format="png",dpi=120,facecolor=CARD); plt.close()
+    buf.seek(0)
+    result = f"**Predicted %ApoE:** {apoe_pct:.1f}% → {tier}
+
+**BBB Crossing Probability:** {bbb_prob:.2f}"
+    return result, Image.open(buf)
+
+# ══════════════════════════════════════════════════════════════════════════════
+# TAB 10 — AutoCorona NLP  (B5)
+# ══════════════════════════════════════════════════════════════════════════════
+CORONA_PROTEINS = ["albumin","apolipoprotein","fibrinogen","vitronectin","clusterin",
+                   "igm","iga","igg","complement","transferrin","alpha-2-macroglobulin"]
+
+def extract_corona(text):
+    result = {"nanoparticle_composition":"","size_nm":None,"zeta_mv":None,
+              "PDI":None,"protein_source":"","corona_proteins":[],"confidence":{}}
+    size_m = re.search(r"(\d+\.?\d*)\s*(?:nm|nanometer)",text,re.I)
+    if size_m: result["size_nm"]=float(size_m.group(1)); result["confidence"]["size_nm"]="HIGH"
+    zeta_m = re.search(r"([+-]?\d+\.?\d*)\s*mV",text,re.I)
+    if zeta_m: result["zeta_mv"]=float(zeta_m.group(1)); result["confidence"]["zeta_mv"]="HIGH"
+    pdi_m = re.search(r"PDI\s*[=:of]*\s*(\d+\.?\d*)",text,re.I)
+    if pdi_m: result["PDI"]=float(pdi_m.group(1)); result["confidence"]["PDI"]="HIGH"
+    for src in ["human plasma","human serum","fetal bovine serum","FBS","PBS"]:
+        if src.lower() in text.lower():
+            result["protein_source"]=src; result["confidence"]["protein_source"]="HIGH"; break
+    found=[]
+    for p in CORONA_PROTEINS:
+        if p in text.lower(): found.append({"name":p,"relative_abundance":"detected","confidence":"MEDIUM"})
+    result["corona_proteins"]=found
+    for lip in ["DSPC","DOPE","MC3","DLin","cholesterol","PEG","DOTAP"]:
+        if lip in text: result["nanoparticle_composition"]+=lip+" "
+    result["nanoparticle_composition"]=result["nanoparticle_composition"].strip()
+    flags=[]
+    if not result["size_nm"]: flags.append("⚠️ size_nm not found")
+    if not result["zeta_mv"]: flags.append("⚠️ zeta_mv not found")
+    if not result["corona_proteins"]: flags.append("⚠️ no corona proteins detected")
+    return json.dumps(result,indent=2), "
+".join(flags) if flags else "✅ All key fields extracted"
+
+# ══════════════════════════════════════════════════════════════════════════════
+# BUILD GRADIO APP
+# ══════════════════════════════════════════════════════════════════════════════
+css = f"""
+body, .gradio-container {{ background:{BG} !important; color:{TXT} !important; }}
+.tab-nav button {{ color:{TXT} !important; background:{CARD} !important; }}
+.tab-nav button.selected {{ border-bottom:2px solid {ACC} !important; color:{ACC} !important; }}
+h1,h2,h3 {{ color:{ACC} !important; }}
+.gr-button-primary {{ background:{ACC} !important; border:none !important; }}
+footer {{ display:none !important; }}
+"""
+
+header_md = f"""
+# 🧬 K R&D Lab — Computational Biology Suite
+**Oksana Kolisnyk** · ML Engineer @ [FAZENA](https://fazena.org) · [kosatiks-group.pp.ua](https://kosatiks-group.pp.ua)
+[![GitHub](https://img.shields.io/badge/GitHub-K--RnD--Lab--BIO--2026-orange)](https://github.com/oksana-kolisnyk/K-RnD-Lab-BIO-2026)
+> 10 open-source computational biology tools in one space. Hypothesis testing across disciplines.
+"""
+
+with gr.Blocks(css=css, title="K R&D Lab") as demo:
+    gr.Markdown(header_md)
+
+    with gr.Tabs():
+
+        # ── TAB 1 ─────────────────────────────────────────────────────────────
+        with gr.TabItem("🧬 BRCA2 miRNA"):
+            gr.Markdown("### Tumor Suppressor miRNAs in BRCA/TP53-Mutant Breast Cancer
+*Downregulated miRNAs as candidates for miRNA-mimic therapy.*")
+            gene_dd = gr.Dropdown(["BRCA2","BRCA1","TP53"], value="BRCA2", label="Select gene")
+            run1 = gr.Button("Find miRNAs", variant="primary")
+            out1 = gr.Dataframe(label="Top 5 downregulated miRNAs")
+            gr.Examples([["BRCA2"],["TP53"]], inputs=[gene_dd])
+            run1.click(predict_mirna, gene_dd, out1)
+
+        # ── TAB 2 ─────────────────────────────────────────────────────────────
+        with gr.TabItem("💉 TP53 siRNA"):
+            gr.Markdown("### Synthetic Lethal siRNA Targets in TP53-Mutant Cancer
+*DepMap-derived essentiality scores + siRNA sequences.*")
+            cancer_dd = gr.Dropdown(["LUAD","BRCA","COAD"], value="LUAD", label="Cancer type")
+            run2 = gr.Button("Find Targets", variant="primary")
+            out2 = gr.Dataframe(label="Top 5 siRNA targets")
+            gr.Examples([["LUAD"],["BRCA"]], inputs=[cancer_dd])
+            run2.click(predict_sirna, cancer_dd, out2)
+
+        # ── TAB 3 ─────────────────────────────────────────────────────────────
+        with gr.TabItem("🧠 lncRNA-TREM2"):
+            gr.Markdown("### lncRNA Regulatory Networks in TREM2-Dependent Microglial Inflammation
+*Alzheimer's therapy candidates: ceRNA axes & ASO design.*")
+            run3 = gr.Button("Load Results", variant="primary")
+            out3a = gr.Dataframe(label="ceRNA Network (lncRNA → miRNA → target)")
+            out3b = gr.Dataframe(label="ASO Candidates")
+            run3.click(get_lncrna, [], [out3a, out3b])
+
+        # ── TAB 4 ───────────────────────────────��─────────────────────────────
+        with gr.TabItem("💊 FGFR3 Drug"):
+            gr.Markdown("### RNA-Directed Drug Discovery: FGFR3 mRNA Targeting
+*Small molecules targeting FGFR3 5'UTR pockets for bladder cancer.*")
+            pocket_r = gr.Radio(["P1 (hairpin loop)","P10 (G-quadruplex)"], value="P1 (hairpin loop)", label="Target pocket")
+            run4 = gr.Button("Screen Compounds", variant="primary")
+            out4t = gr.Dataframe(label="Top 5 candidates")
+            out4p = gr.Image(label="Binding scores")
+            gr.Examples([["P1 (hairpin loop)"],["P10 (G-quadruplex)"]], inputs=[pocket_r])
+            run4.click(predict_drug, pocket_r, [out4t, out4p])
+
+        # ── TAB 5 ─────────────────────────────────────────────────────────────
+        with gr.TabItem("🔬 OpenVariant ⭐"):
+            gr.Markdown("### OpenVariant — Pathogenicity Classifier
+*Open-source alternative to AlphaMissense. AUC=0.939 on ClinVar 2026.*")
+            with gr.Row():
+                hgvs_tb = gr.Textbox(label="HGVS notation (e.g. BRCA1:p.R1699Q)", placeholder="BRCA1:p.R1699Q")
+            gr.Markdown("**Or enter scores manually:**")
+            with gr.Row():
+                sift_s = gr.Slider(0,1,0.5,label="SIFT (0=damaging)")
+                pp_s   = gr.Slider(0,1,0.5,label="PolyPhen-2")
+                gn_s   = gr.Slider(0,0.01,0.001,label="gnomAD AF",step=0.0001)
+            run5 = gr.Button("Predict Pathogenicity", variant="primary")
+            out5 = gr.HTML(label="Prediction")
+            gr.Examples([["BRCA1:p.R1699Q",0.82,0.05,0.0012],
+                         ["TP53:p.R248W",0.00,1.00,0.0],
+                         ["BRCA2:p.D2723A",0.01,0.98,0.0]],
+                        inputs=[hgvs_tb,sift_s,pp_s,gn_s])
+            run5.click(predict_variant, [hgvs_tb,sift_s,pp_s,gn_s], out5)
+
+        # ── TAB 6 ─────────────────────────────────────────────────────────────
+        with gr.TabItem("🧪 LNP Corona"):
+            gr.Markdown("### LNP Protein Corona Prediction
+*Predict dominant corona protein + transfection efficacy from formulation.*")
+            with gr.Row():
+                sz6 = gr.Slider(50,300,100,label="Size (nm)")
+                zt6 = gr.Slider(-40,10,-5,label="Zeta (mV)")
+            with gr.Row():
+                pg6 = gr.Slider(0,5,1.5,label="PEG mol%")
+                lp6 = gr.Dropdown(["Ionizable","Cationic","Anionic","Neutral"],value="Ionizable",label="Lipid type")
+            run6 = gr.Button("Predict", variant="primary")
+            out6 = gr.Markdown()
+            gr.Examples([[100,-5,1.5,"Ionizable"],[80,5,0.5,"Cationic"]], inputs=[sz6,zt6,pg6,lp6])
+            run6.click(predict_corona,[sz6,zt6,pg6,lp6],out6)
+
+        # ── TAB 7 ─────────────────────────────────────────────────────────────
+        with gr.TabItem("🩸 Liquid Biopsy"):
+            gr.Markdown("### Protein Corona Cancer Diagnostics
+*Predict cancer vs healthy from plasma protein abundances.*")
+            gr.Markdown("Enter normalised protein abundances (z-score, typical range -3 to +3):")
+            with gr.Row():
+                p1=gr.Slider(-3,3,0,label="CTHRC1"); p2=gr.Slider(-3,3,0,label="FHL2")
+                p3=gr.Slider(-3,3,0,label="LDHA");   p4=gr.Slider(-3,3,0,label="P4HA1")
+                p5=gr.Slider(-3,3,0,label="SERPINH1")
+            with gr.Row():
+                p6=gr.Slider(-3,3,0,label="ABCA8");  p7=gr.Slider(-3,3,0,label="CA4")
+                p8=gr.Slider(-3,3,0,label="CKB");    p9=gr.Slider(-3,3,0,label="NNMT")
+                p10=gr.Slider(-3,3,0,label="CACNA2D2")
+            run7=gr.Button("Classify",variant="primary")
+            out7t=gr.Markdown(); out7p=gr.Image(label="Feature contributions")
+            gr.Examples([[2,2,1.5,1.8,1.6,-1,-1.2,-0.8,1.4,-1.1],
+                         [0,0,0,0,0,0,0,0,0,0]],
+                        inputs=[p1,p2,p3,p4,p5,p6,p7,p8,p9,p10])
+            run7.click(predict_cancer,[p1,p2,p3,p4,p5,p6,p7,p8,p9,p10],[out7t,out7p])
+
+        # ── TAB 8 ─────────────────────────────────────────────────────────────
+        with gr.TabItem("🌊 Flow Corona"):
+            gr.Markdown("### Corona Remodeling Under Blood Flow
+*Predicts how protein corona changes from static incubation to physiological flow.*")
+            with gr.Row():
+                sz8=gr.Slider(50,300,100,label="Size (nm)"); zt8=gr.Slider(-40,10,-5,label="Zeta (mV)")
+                pg8=gr.Slider(0,5,1.5,label="PEG mol%")
+            with gr.Row():
+                ch8=gr.Dropdown(["Ionizable","Cationic","Anionic","Neutral"],value="Ionizable",label="Charge type")
+                fl8=gr.Slider(0,40,20,label="Flow rate (cm/s)  [aorta=40]")
+            run8=gr.Button("Model Vroman Effect",variant="primary")
+            out8t=gr.Markdown(); out8p=gr.Image(label="Albumin→ApoE kinetics")
+            gr.Examples([[100,-5,1.5,"Ionizable",40],[150,5,0.5,"Cationic",10]],
+                        inputs=[sz8,zt8,pg8,ch8,fl8])
+            run8.click(predict_flow,[sz8,zt8,pg8,ch8,fl8],[out8t,out8p])
+
+        # ── TAB 9 ─────────────────────────────────────────────────────────────
+        with gr.TabItem("🧠 LNP Brain"):
+            gr.Markdown("### LNP Brain Delivery Predictor
+*Predicts ApoE corona enrichment and BBB crossing probability for GBM targeting.*")
+            smi9=gr.Textbox(label="Ionizable lipid SMILES",
+                            value="CC(C)CC(=O)OCC(COC(=O)CC(C)C)OC(=O)CC(C)C")
+            with gr.Row():
+                pk9=gr.Slider(4,8,6.5,step=0.1,label="pKa")
+                zt9=gr.Slider(-20,10,-3,label="Zeta (mV)")
+            run9=gr.Button("Predict BBB Crossing",variant="primary")
+            out9t=gr.Markdown(); out9p=gr.Image(label="Lipid profile radar")
+            gr.Examples([["CC(C)CC(=O)OCC(COC(=O)CC(C)C)OC(=O)CC(C)C",6.5,-3],
+                         ["CCCCCCCC/C=C\CCCCCCCC(=O)OCC(N)CO",5.5,5]],
+                        inputs=[smi9,pk9,zt9])
+            run9.click(predict_bbb,[smi9,pk9,zt9],[out9t,out9p])
+
+        # ── TAB 10 ────────────────────────────────────────────────────────────
+        with gr.TabItem("📚 AutoCorona NLP"):
+            gr.Markdown("### AutoCorona — NLP Extraction Pipeline
+*Paste any paper abstract to extract structured LNP corona data automatically.*")
+            txt10=gr.Textbox(lines=6, label="Paper abstract or methods text",
+                             placeholder="Paste text here...")
+            run10=gr.Button("Extract Data",variant="primary")
+            out10j=gr.Code(label="Extracted JSON",language="json")
+            out10f=gr.Textbox(label="Validation flags")
+            gr.Examples([
+                ["LNPs composed of MC3, DSPC, Cholesterol (50:10:40 mol%) with 1.5% PEG-DMG were prepared by microfluidics. Hydrodynamic diameter was 98 ± 12 nm, zeta potential -3.2 mV, PDI 0.12. LNPs were incubated in human plasma for 60 min. Corona proteins identified by LC-MS/MS included albumin, apolipoprotein E, fibrinogen, and vitronectin."],
+                ["Cationic liposomes (DOTAP:DOPE 1:1) with size 150 nm and zeta +25 mV were incubated in fetal bovine serum. IgG, complement C3, and albumin were the dominant corona proteins."]
+            ], inputs=[txt10])
+            run10.click(extract_corona,txt10,[out10j,out10f])
+
+    gr.Markdown("""---
+    **K R&D Lab** · Open-source computational biology research  
+    Data is research-grade, not clinical. All models are experimental.  
+    [GitHub](https://github.com/oksana-kolisnyk/K-RnD-Lab-BIO-2026) | [fazena.org](https://fazena.org) | [kosatiks-group.pp.ua](https://kosatiks-group.pp.ua)
+    """)
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,5 @@
+gradio>=4.0.0
+pandas>=2.0.0
+numpy>=1.24.0
+matplotlib>=3.7.0
+Pillow>=10.0.0