drug-discovery-pipeline

import requests, json, os
import safe as sf                          # pip install safe-mol
from pathlib import Path
 
NGC_API_KEY = os.getenv("NGC_API_KEY")
HOSTED = True
 
if HOSTED:
    genmol_url = "https://health.api.nvidia.com/v1/biology/nvidia/genmol/generate"
    headers = {"Content-Type": "application/json",
               "Authorization": f"Bearer {NGC_API_KEY}"}
else:
    genmol_url = "http://localhost:8000/generate"
    headers = {"Content-Type": "application/json"}
 
# De novo generation (no scaffold):
safe_input = "[*{20-30}]"
 
# Scaffold decoration (known core):
# scaffold_smiles = "c1ccccc1"
# safe_input = sf.encode(scaffold_smiles) + ".[*{5-10}]"
 
payload = {
    "smiles": safe_input,              # field is named 'smiles' but takes SAFE notation
    "num_molecules": 30,               # request more to compensate for post-generation filtering
    "scoring": "QED",                  # QED or LogP
    "unique": True,
    "temperature": "1.0",             # NOTE: must be string, not float
    "noise": "1.0",                   # NOTE: must be string, not float
}
 
r = requests.post(genmol_url, headers=headers, json=payload)
r.raise_for_status()
molecules = r.json()["molecules"]
molecules_sorted = sorted(molecules, key=lambda x: x["score"], reverse=True)
top_20 = molecules_sorted[:20]
 
print(f"Generated {len(molecules)} valid molecules (requested 30)")
print("Top 5 by QED score:")
for m in top_20[:5]:
    print(f"  {m['smiles'][:50]}  score={m['score']:.4f}")

# Load protein (ATOM records only)
receptor_pdb_raw = Path("target.pdb").read_text()
receptor_pdb = "\n".join(line for line in receptor_pdb_raw.splitlines()
                          if line.startswith("ATOM"))
 
if HOSTED:
    diffdock_url = "https://health.api.nvidia.com/v1/biology/mit/diffdock"
else:
    diffdock_url = "http://localhost:8000/molecular-docking/diffdock/generate"
 
docking_results = []
 
for i, mol in enumerate(top_20):
    payload = {
        "protein": receptor_pdb,
        "ligand": mol["smiles"],
        "ligand_file_type": "txt",     # "txt" for SMILES input
        "num_poses": 5,
        "time_divisions": 20,
        "steps": 18,
        "save_trajectory": False,
    }
 
    r = requests.post(diffdock_url, headers=headers, json=payload)
    r.raise_for_status()
    result = r.json()
 
    best_conf = result["position_confidence"][0]  # rank 1 pose
    best_pose = result["ligand_positions"][0]
 
    docking_results.append({
        "smiles": mol["smiles"],
        "qed_score": mol["score"],
        "docking_confidence": best_conf,
        "best_pose_sdf": best_pose,
    })
    print(f"  Mol {i+1:2d}: QED={mol['score']:.3f}  docking_conf={best_conf:.4f}")
 
# Rank by docking confidence
docking_results.sort(key=lambda x: x["docking_confidence"], reverse=True)
print(f"\nTop 3 by docking confidence:")
for d in docking_results[:3]:
    print(f"  {d['smiles'][:50]}  conf={d['docking_confidence']:.4f}")

if HOSTED:
    boltz_url = "https://health.api.nvidia.com/v1/biology/mit/boltz2/predict"
else:
    boltz_url = "http://localhost:8000/biology/mit/boltz2/predict"
 
# Use the target protein sequence (not PDB)
target_sequence = "<YOUR_TARGET_PROTEIN_SEQUENCE>"
 
affinity_results = []
for d in docking_results[:5]:  # score top 5 docking hits
    payload = {
        "polymers": [
            {"id": "A", "molecule_type": "protein", "sequence": target_sequence}
        ],
        "ligands": [
            {"id": "L1", "smiles": d["smiles"], "predict_affinity": True}
        ],
        "recycling_steps": 3,
        "sampling_steps": 50,
        "diffusion_samples": 1,
        "output_format": "mmcif",
    }
 
    r = requests.post(boltz_url, headers=headers, json=payload)
    r.raise_for_status()
    result = r.json()
 
    aff = result["affinities"]["L1"]
    pic50 = aff["affinity_pic50"][0]
    prob_binding = aff["affinity_probability_binary"][0]
 
    affinity_results.append({
        **d,
        "pic50": pic50,
        "probability_binding": prob_binding,
    })
    print(f"  {d['smiles'][:40]}  pIC50={pic50:.2f}  P(bind)={prob_binding:.3f}")
 
# Final ranking by pIC50
affinity_results.sort(key=lambda x: x["pic50"], reverse=True)