Skip to main content
Docs

Search guides and API endpoints, for example “Idempotency-Key” or “submit job”.

    Tools · Computational Biology

    DiffDock

    Protein-ligand docking with diffusion models and confidence-ranked poses
    On this page

    Prices, workflows, and method papersOpen in the app

    Run it from the API

    Submit with Submit a job and the job_type below. Price it first with Estimate job reservation cost: submitting reserves that amount from your wallet, and the charge settles at the actual runtime.

    DiffDock diffdock

    Job type
    diffdock
    Hardware
    cput4 (default)l4a10l40sa100-40gba100-80gbh100h200b200
    Typical runtime
    30 min on Nvidia T4

    Payload

    Payload fields
    FieldTypeDescription
    pdb_idstring

    Limits: min length 1

    proteinfile_object
    protein.namestring

    Limits: min length 1

    protein.filenamestring

    Limits: min length 1

    protein.content_b64string

    Limits: min length 1

    protein.contentany
    protein.bytesany
    protein_download_formatstring

    Default: "pdb"One of: "pdb", "cif"

    ligandfile_object
    ligand.namestring

    Limits: min length 1

    ligand.filenamestring

    Limits: min length 1

    ligand.content_b64string

    Limits: min length 1

    ligand.contentany
    ligand.bytesany
    ligands[]file_object[]

    Limits: max items 100

    ligands.namestring

    Limits: min length 1

    ligands.filenamestring

    Limits: min length 1

    ligands.content_b64string

    Limits: min length 1

    ligands.contentany
    ligands.bytesany
    ligand_smilesstring | string[]
    protein_ligand_csvfile_object
    protein_ligand_csv.namestring

    Limits: min length 1

    protein_ligand_csv.filenamestring

    Limits: min length 1

    protein_ligand_csv.content_b64string

    Limits: min length 1

    protein_ligand_csv.contentany
    protein_ligand_csv.bytesany
    additional_filesmap<string, file_object>
    actual_stepsinteger

    Limits: ≥ 1

    batch_sizeinteger

    Limits: ≥ 1

    ckptstring

    Limits: min length 1

    complex_namestring

    Limits: min length 1

    confidence_ckptstring

    Limits: min length 1

    confidence_model_dirstring

    Limits: min length 1

    inference_stepsinteger

    Limits: ≥ 1, ≤ 50

    initial_noise_std_proportionnumber
    loglevelstring

    Limits: min length 1

    model_dirstring

    Limits: min length 1

    no_final_step_noiseboolean
    old_confidence_modelboolean
    old_score_modelboolean
    samples_per_complexinteger

    Limits: ≥ 1, ≤ 100

    save_visualisationboolean
    temp_psi_rotnumber
    temp_psi_tornumber
    temp_psi_trnumber
    temp_sampling_rotnumber
    temp_sampling_tornumber
    temp_sampling_trnumber
    temp_sigma_data_rotnumber
    temp_sigma_data_tornumber
    temp_sigma_data_trnumber

    File fields take {"name": "x.pdb", "content_b64": "…"} or a stored artifact, {"$artifact": {"id": "art-…", "port": "…"}}. Files are up to 25 MiB each.

    Example

    from cognichem_client import CogniChem
    
    client = CogniChem.from_env()  # reads COGNICHEM_API_KEY
    payload = {
        "protein": {
            "name": "protein.pdb",
            "content_b64": "<file contents, base64>",
        },
        "ligand_smiles": "CCO",
        "samples_per_complex": 1,
        "inference_steps": 1,
        "batch_size": 1,
    }
    
    estimate = client.jobs.estimate(job_type="diffdock", payload=payload, resource="t4")
    print(f"Reserves ${estimate.cost:.2f}")
    
    job = client.jobs.submit(
        job_name="my-diffdock-run",
        job_type="diffdock",
        payload=payload,
        resource="t4",
    )
    status = client.jobs.wait(job.process_id)
    if status.status == "completed":
        client.jobs.result(job.process_id, save_path=".")

    Sample data from the job catalog; long values are shortened here. Each job_name must be unique among your jobs.

    Workflow inputs

    • Molecules (list)SDF, MOL, MOL2, SMILES
    • Protein structurePDB, CIF

    Workflow outputs

    • ArchiveZIP
    • Docked posesSDF