File size: 3,827 Bytes
7c00697 ac09baf 7c00697 ac09baf 7c00697 ac09baf 7c00697 ac09baf 7c00697 ac09baf 7c00697 ac09baf 7c00697 ac09baf 7c00697 ac09baf |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 |
import gradio as gr
from transformers import pipeline
from rdkit import Chem
from rdkit.Chem import AllChem
from rdkit.Chem.Draw import rdMolDraw2D
import base64
import re
import py3Dmol
import time
# Load model once
bio_gpt = pipeline("text-generation", model="microsoft/BioGPT-Large")
def drug_discovery(disease, symptoms):
# Simplified and efficient medical prompt
prompt = (
f"You're a biomedical AI. A new disease shows symptoms: '{symptoms}'. "
f"Suggest 5 generic drug names and 5 SMILES strings that could help treat this. "
f"List drug names first, then SMILES strings in separate lines like:\n"
f"Drugs: Aspirin, Ibuprofen, Paracetamol, ...\n"
f"SMILES: C1=CC=CC=C1 C(C(=O)O)N ..."
)
try:
start = time.time()
result = bio_gpt(prompt, max_length=150, do_sample=True, temperature=0.6)[0]['generated_text']
except Exception as e:
return f"BioGPT error: {e}", "", "", ""
# Extract drug names and SMILES
drugs_match = re.search(r"Drugs:\s*(.+)", result)
smiles_match = re.search(r"SMILES:\s*(.+)", result)
drug_names = drugs_match.group(1).strip() if drugs_match else "Unknown"
raw_smiles = smiles_match.group(1).strip() if smiles_match else "C1=CC=CC=C1"
smiles_list = re.findall(r"(?<![A-Za-z0-9])[A-Za-z0-9@+\-\[\]\(\)=#$]{5,}(?![A-Za-z0-9])", raw_smiles)
smiles_list = list({sm for sm in smiles_list if Chem.MolFromSmiles(sm)})[:3]
if not smiles_list:
smiles_list = ["C1=CC=CC=C1"]
img_html, viewer_htmls = "", ""
for smiles in smiles_list:
mol = Chem.MolFromSmiles(smiles)
AllChem.Compute2DCoords(mol)
drawer = rdMolDraw2D.MolDraw2DCairo(250, 250)
drawer.DrawMolecule(mol)
drawer.FinishDrawing()
img_data = drawer.GetDrawingText()
img_base64 = base64.b64encode(img_data).decode("utf-8")
img_html += f'''
<div style="display:inline-block; margin:10px;">
<img src="data:image/png;base64,{img_base64}" width="120" height="120">
<p style="color:white; font-size:12px;">{smiles}</p>
</div>'''
# 3D View
mol3d = Chem.AddHs(mol)
AllChem.EmbedMolecule(mol3d, randomSeed=42)
AllChem.UFFOptimizeMolecule(mol3d)
mb = Chem.MolToMolBlock(mol3d)
viewer = py3Dmol.view(width=240, height=240)
viewer.addModel(mb, "mol")
viewer.setStyle({"stick": {"colorscheme": "cyanCarbon"}})
viewer.setBackgroundColor("black")
viewer.zoomTo()
viewer_html_raw = viewer._make_html()
viewer_htmls += f'''
<div style="display:inline-block; margin:10px;">
<iframe srcdoc="{viewer_html_raw.replace('"', '"')}" width="240" height="240" frameborder="0"></iframe>
</div>'''
duration = round(time.time() - start, 2)
literature_summary = f"📋 Drug candidates (auto-generated in {duration}s):\n{drug_names}"
return literature_summary, ", ".join(smiles_list), img_html, viewer_htmls
# Gradio UI setup
iface = gr.Interface(
fn=drug_discovery,
inputs=[
gr.Textbox(label="🧬 Enter Unknown Disease or Name", value="X-disease"),
gr.Textbox(label="📝 Symptoms", value="fever, joint pain")
],
outputs=[
gr.Textbox(label="🔖 AI Literature Summary"),
gr.Textbox(label="🧪 SMILES List"),
gr.HTML(label="🖼️ 2D Molecules"),
gr.HTML(label="🔬 3D Molecules")
],
title="🧪 Drug Discovery for Unknown Diseases",
description="BioGPT + RDKit-powered system to suggest potential drug molecules for unknown or rare diseases.",
css="""
body { background-color: #111; color: #eee; }
.gradio-container { animation: fadeIn 1.5s ease-in-out; }
"""
)
iface.launch(share=True)
|