Create app.py

app.py

@@ -0,0 +1,124 @@
+from Bio import PDB
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from rdkit import Chem
+import py3Dmol
+import re
+import io
+import selfies as sf
+import torch
+import time
+import gradio as gr
+
+# إعداد العشوائية
+torch.manual_seed(int(time.time()))
+if torch.cuda.is_available():
+    torch.cuda.manual_seed_all(int(time.time()))
+
+# تحميل النموذج
+model_name = "ncfrey/ChemGPT-1.2B"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+
+def load_pdb(file_obj):
+    parser = PDB.PDBParser(QUIET=True)
+    structure = parser.get_structure('protein', file_obj)
+    return structure
+
+def get_protein_3d_html(pdb_str):
+    view = py3Dmol.view(width=600, height=400)
+    view.addModel(pdb_str, "pdb")
+    view.setStyle({"cartoon": {"color": "spectrum"}})
+    view.zoomTo()
+    return view._make_html()
+
+def clean_and_decode_selfies(raw_output):
+    tokens = re.findall(r'\[[^\[\]]+\]', raw_output)
+    valid_tokens = [t for t in tokens if all(x not in t for x in ['Branch', 'Ring', 'expl'])]
+    cleaned_selfies = ''.join(valid_tokens)
+    try:
+        smiles = sf.decoder(cleaned_selfies)
+        mol = Chem.MolFromSmiles(smiles)
+        if mol:
+            return Chem.MolToSmiles(mol)
+    except:
+        return None
+
+def generate_multiple_valid_smiles(prompt, n=10, max_length=100):
+    valid_smiles = set()
+    tries = 0
+    while len(valid_smiles) < n and tries < n * 5:
+        inputs = tokenizer(prompt, return_tensors="pt")
+        outputs = model.generate(
+            **inputs,
+            max_length=max_length,
+            do_sample=True,
+            temperature=1.0,
+            top_k=100,
+            pad_token_id=tokenizer.eos_token_id
+        )
+        selfies_output = tokenizer.decode(outputs[0], skip_special_tokens=True)
+        smiles = clean_and_decode_selfies(selfies_output)
+        if smiles:
+            valid_smiles.add(smiles)
+        tries += 1
+    return list(valid_smiles)
+
+def generate_from_pdb(pdb_file):
+    try:
+        if isinstance(pdb_file, (str, bytes)):
+            pdb_str = pdb_file if isinstance(pdb_file, str) else pdb_file.decode('utf-8', errors='ignore')
+        else:
+            pdb_bytes = pdb_file.read()
+            pdb_str = pdb_bytes.decode('utf-8', errors='ignore')
+
+        if len(pdb_str.strip()) == 0:
+            return "❌ الملف فارغ أو غير صالح", None, None
+
+        pdb_file_io = io.StringIO(pdb_str)
+        try:
+            load_pdb(pdb_file_io)
+        except Exception as e:
+            return f"❌ خطأ أثناء تحليل ملف PDB:\n{str(e)}", None, None
+
+        html_3d = get_protein_3d_html(pdb_str)
+
+        prompt = "Generate a molecule in SELFIES that binds to the mutated KRAS protein"
+        smiles_list = generate_multiple_valid_smiles(prompt, n=10)
+
+        if not smiles_list:
+            return "❌ لم يتم توليد أي SMILES صالحة", html_3d, None
+
+        smiles_txt = "\n".join(smiles_list)
+        smiles_file_path = "/tmp/generated_smiles.txt"
+        with open(smiles_file_path, "w") as f:
+            f.write(smiles_txt)
+
+        return "✅ تم توليد المركبات بنجاح", html_3d, smiles_file_path
+
+    except Exception as e:
+        return f"❌ حدث خطأ:\n{str(e)}", None, None
+
+css = """
+body {background-color: #f0f9ff;}
+h1 {color: #004d66; text-align: center;}
+"""
+
+with gr.Blocks(css=css) as demo:
+    gr.Markdown("<h1>🔬 توليد مركبات دوائية باستخدام ChemGPT من ملف PDB</h1>")
+    gr.Markdown("🧪 ارفع ملف PDB يحتوي على طفرات في بروتين KRAS وسيتم توليد مركبات SMILES مناسبة.")
+
+    with gr.Row():
+        pdb_input = gr.File(label="📁 ارفع ملف PDB")
+        run_btn = gr.Button("🚀 توليد المركبات")
+
+    status = gr.Textbox(label="📢 الحالة")
+    view3d = gr.HTML(label="🧬 عرض ثلاثي الأبعاد")
+    file_output = gr.File(label="📄 تحميل ملف SMILES")
+
+    run_btn.click(
+        fn=generate_from_pdb,
+        inputs=pdb_input,
+        outputs=[status, view3d, file_output]
+    )
+
+demo.launch()