DiffDock-L
Diffusion-based protein-ligand docking with SMILES, SDF, or CSV batches.
Basics
- Entry point:
python -m inference; supply one flag per line. - Common flags:
--protein_path,--ligand_description(SMILES),--ligand(SDF/MOL2),--protein_ligand_csv(batch),--out_dir. - Write
--out_dirsomewhere under/outputsso poses and scores are captured.
Quick SMILES docking
--protein_path=/inputs/protein.pdb
--ligand_description=CC(=O)Oc1ccccc1C(=O)O
--complex_name=aspirin_demo
--out_dir=/outputs/aspirin_run
Dock a prepared ligand file
--protein_path=/inputs/target.pdb
--ligand=/inputs/ligand.sdf
--out_dir=/outputs/sdf_run
Batch from CSV
CSV columns: complex_name,protein_path,ligand_description (paths relative to /inputs).
--protein_ligand_csv=/inputs/pairs.csv
--out_dir=/outputs/batch_run
Submit
Launch via New Job -> DiffDock-L; the form pre-fills the SMILES example.