Skip to main content
NVIDIA
Explore
Models
Skills
Blueprints
GPUs
Docs
Help Center
Getting Started
  1. Create and verify your account to unlock full access to NVIDIA NIM APIs.
ResourcesDeveloper ForumsContact Support
FAQs
  • Terms of Use
    Privacy Policy
    Your Privacy Choices
    Contact

    Copyright © 2026 NVIDIA Corporation

    Input

    OpenFold2Virtual screening will be performed against the protein entered here. Enter the amino acid sequence of the protein or select an example to predict its 3D structure.
    Protein
    Protein
    Amino Acid Sequence. Sequence must be at least 50 characters long for docking to work.
    Amino Acid Sequence. Sequence must be at least 50 characters long for docking to work.
    MMseqs2 Multiple Sequence Alignment
    The predictions of OpenFold2 use a multiple sequence alignment (MSA). Specify here how to perform the MSA search.

    Select databases to search for similar sequences.

    Uniref30_2303
    PDB70_220313
    colabfold_envdb_202108

    Select e-value and iterations to set the inclusion threshold.

    E value is 10^-n where n is the slider value

    2345678910

    Number of iterations to run the MSA search.

    123456
    GenMol
    This module uses GenMol to generate molecules to screen for activity against the protein. Choose how to generate optimized molecules for the virtual screening.
    Molecule Examples
    Molecule Examples
    Molecule Sequence
    Molecule Sequence

    Number of molecules to generate. Note that identical molecules are filtered out. As a result, the number of molecules displayed will sometimes be less than the number of molecules requested here.

    1112131415161718191100

    Temperature scaling factor for Softmax sampling.

    0.0112345678910

    Noise factor for top-k sampling.

    00.10.20.30.40.50.60.70.80.911

    Diffusion step size.

    12345678910
    Select one of the available properties to be compute.
    Select one of the available properties to be compute.
    DiffDock InputsThe final step of virtual screening uses DiffDock to predict how each generated molecule will interact with the target protein. Choose how the generated molecules and the protein will be docked.
    PDB Generated by OpenFold2
    PDB Generated by OpenFold2
    Molecule Input Generated by GenMol
    Molecule Input Generated by GenMol

    How many poses that will be generated for each molecule

    111213140
    Free APIs for development
    Your API requests may be rate limited. Traffic from other users may cause throttling.
    Coming Soon!

    GOVERNING TERMS: Your use of this API is governed by the NVIDIA API Trial Service Terms of Use; and the use of this blueprint is governed by the NVIDIA AI Foundation Models Community License.

    Output

    Click generateAdjust the settings and click generate to see your outcome here.

    nvidia

    Build A Generative Virtual Screening Pipeline

    Enterprise

    This blueprint shows how generative AI and accelerated NIM microservices can design optimized small molecules smarter and faster.

    openfold2•msa-search•genmol-generate•diffdock
    • BioNemo
    • Chemistry
    • Docking
    • NIM
    • NVIDIA BioNemo
    • Healthcare & Life Sciences
    Download