NVIDIA
Explore
Models
Blueprints
GPUs
Docs
Terms of Use
Privacy Policy
Your Privacy Choices
Contact

Copyright © 2025 NVIDIA Corporation

nvidia

Build A Generative Virtual Screening Pipeline

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

openfold2•msa-search•genmol-generate•diffdock
BioNemoBlueprintChemistryDockingNIMEnterpriseNVIDIA BioNemoDrug Discovery
Download

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.
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.MSA Databases
Uniref30_2303
PDB70_220313
colabfold_envdb_202108

Inclusion Threshold
2
3
4
5
6
7
8
9
10
1
2
3
4
5
6
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 Sequence
1
11
21
31
41
51
61
71
81
91
100
0.01
1.01
2.01
3.01
4.01
5.01
6.01
7.01
8.01
9.01
10
0
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1
1
2
3
4
5
6
7
8
9
10
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
Molecule Input Generated by GenMol
1
11
21
31
40
Using free API for development

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.