Skip to main content
    Ivy Biosciences Docs/Call the platform/API/Reference/Job Types Catalog

    Job Types Catalog

    Searchable catalog of computational biology tools with categories and typical runtimes

    referencetoolscatalog

    The Job Types Catalog is the reference list of every computational tool you can run on the platform, grouped by category with its compute profile and typical runtime. Reach for it when you're deciding which tool fits your task or need a tool's exact name before submitting. Each entry can be invoked through the REST API, the SDK, or the Harness.

    Difficulty

    beginner

    Time

    10 min

    Job Types Catalog

    Complete catalog of computational tools available on the IvyAI platform. Each tool can be invoked via the REST API, SDK, or Harness.


    Structure Prediction

    ToolDescriptionComputeTypical Runtime
    esmfoldESMFold protein structure predictionGPU30s–5min
    esm3_generateESM3 protein generationGPU1–3min
    esm3_inverse_foldESM3 inverse folding (structure → sequence)GPU30s–2min
    esm3_embeddingsESM3 protein embeddingsGPU15–45s
    colabfoldColabFold MSA-based structure predictionGPU2–15min

    Molecular Docking & Design

    ToolDescriptionComputeTypical Runtime
    diffdockDiffDock protein-ligand dockingGPU1–5min
    gninaGNINA CNN-scored docking. Retired: use diffdock, then rescore with MM-GBSAGPU—
    colabdockColabDock flexible docking. Not currently callable: its AlphaFold2 model weights are missingGPU—
    smart_dockSmartDock consensus dockingGPU3–8min
    reinvent4REINVENT4 de novo molecule generationGPU5–30min
    genmolGenMol molecular generation (SAFE native)GPU2–10min
    denovoDe novo drug designGPU5–20min

    Property Prediction

    ToolDescriptionComputeTypical Runtime
    admet_aiADMET property predictionCPU10–30s
    admetlab3ADMETlab3 comprehensive ADMET profilingCPU15–45s
    graphsolGraphSol aqueous solubility predictionCPU10–20s
    deepsolDeepSol deep learning solubility. Not currently callable: disabled upstream (protobuf incompatibility); use graphsolCPU—
    protox3ProTox-3 toxicity prediction. Retired: use admet_ai for the overlapping endpointsCPU—
    deeppurposeDeepPurpose drug-target interactionGPU30s–2min

    Database Screening

    ToolDescriptionComputeTypical Runtime
    rdkit_fullRDKit SMILES validation and molecular propertiesCPU5–15s
    zincZINC database compound screeningCPU10–30s
    pubchemPubChem compound queriesCPU5–15s
    pubchem_substructurePubChem substructure searchCPU10–30s
    chemblChEMBL bioactivity database searchCPU10–30s

    Sequence Analysis

    ToolDescriptionComputeTypical Runtime
    blastBLAST sequence homology searchCPU10s–2min
    biotite_fetchUniProt/PDB structure fetchingCPU5–15s
    aizynthfinderAiZynthFinder retrosynthetic route planningCPU30s–5min

    Fragment & Scaffold Design

    ToolDescriptionComputeTypical Runtime
    fragment_growingFragment-based drug design. Retired: no replacementGPU—
    fragment_libraryFragment library management. Retired: no replacementCPU—
    fragment_searchFragment discovery and searchCPU10–30s
    fragment_extractFragment extraction from structuresCPU10–30s
    scaffold_decorationScaffold decoration with R-groupsGPU2–10min
    linker_designLinker design between fragmentsGPU2–10min
    motif_extensionMotif-based molecule extensionGPU2–10min

    Literature & NLP

    ToolDescriptionComputeTypical Runtime
    biobert_pubmedBioBERT scientific literature miningGPU15–45s

    Protein Preparation

    ToolDescriptionComputeTypical Runtime
    pdb2pqrProtonation state and charge assignment (PDB2PQR + PROPKA)CPU15–30s
    p2rankBinding pocket detection (P2Rank)CPU30s–2min

    Protein preparation is these two job types, the same ones the chat interface runs (pdb2pqr_protonate, p2rank_predict). pdb2pqr takes inline structure text (pdb_content); p2rank takes pdb_content, a pdb_id or a uniprot_id. There are no proteinprep* job types, and no structure-quality job.


    Regulatory & Safety

    ToolDescriptionComputeTypical Runtime
    drugcentral_regulatoryDrugCentral regulatory approvals lookupCPU5–10s
    chembl_drug_warningsChEMBL drug warnings and withdrawalsCPU5–10s
    pubchem_regulatoryPubChem regulatory data (DEA, ATC)CPU5–10s

    Genomics & Databases

    ToolDescriptionComputeTypical Runtime
    encode_searchENCODE database functional genomics searchCPU10–30s
    string_networkSTRING protein-protein interaction networksCPU10–30s
    uniprot_searchUniProt protein database searchCPU5–15s
    pdb_searchRCSB PDB structure database searchCPU5–15s

    Analysis Levels

    All tools support three analysis levels that control the depth of result processing:

    LevelDescription
    basicFast results with standard output only
    standardBalanced analysis with key quality metrics (default)
    comprehensiveFull analytical suite with extended result fields

    Example

    await ivy.jobs.submit({
      toolName: "esmfold",
      parameters: { protein_sequence: "MKFLILLFNILCLFPVLAADNH" },
      analysisLevel: "comprehensive", // Full pLDDT breakdown, per-residue scores, etc.
    })

    Guest-Accessible Tools

    Callers with no key reach an allowlisted guest catalog through the keyless orchestrate request, not by submitting a job type directly. See Guest curl for the request and its limit.


    Programmatic Tool Discovery

    Harness API

    The web app serves the tool registry at /api/harness/tools:

    # List tools with filtering
    curl "https://www.ivybiosciences.com/api/harness/tools?category=docking&maxCost=standard" \
      -H "Authorization: Bearer ivy_your_key"
    
    # Get specific tool details with JSON Schema
    curl https://www.ivybiosciences.com/api/harness/tools/diffdock \
      -H "Authorization: Bearer ivy_your_key"

    SDK (planned)

    @ivybiosciences/sdk is a planned specification, not a released package. Today, list tools with the REST calls above or ivybloom in the CLI.

    import { JOB_TYPES } from "@ivybiosciences/sdk"
    import type { JobType } from "@ivybiosciences/sdk"
    
    // All registered tool names
    const tools = Object.keys(JOB_TYPES)
    
    // Type-safe tool validation
    function isValidTool(name: string): name is JobType {
      return name in JOB_TYPES
    }

    Was this page helpful?

    Loading...