
Chains GenMol, DiffDock and Boltz2 NIMs to generate, dock and score drug candidates
- Open source
- 4K GitHub stars
- Health and science


Chains GenMol, DiffDock and Boltz2 NIMs to generate, dock and score drug candidates

Predicts biomolecular structures and ligand binding affinity via Boltz2 NIM

Guides an agent through OpenFold3 protein and complex structure prediction via NVIDIA NIM

Generates protein backbone structures via NVIDIA's RFDiffusion NIM, hosted or local

Predicts single-chain protein structures from amino-acid sequences via OpenFold2 NIM

Runs RFD4-Proteina to generate protein structures and sequences via NVIDIA API or local

Designs protein sequences for a backbone PDB using ProteinMPNN via NVIDIA NIM

Generates novel drug-like molecules with the GenMol NIM microservice

Generates and optimizes small molecules from a seed SMILES using NVIDIA's MolMIM NIM

Generates protein multiple sequence alignments and templates via the ColabFold MSA-Search

Generates DNA sequences with NVIDIA's Evo 2 model and extracts local layer outputs

Guides writing and debugging GPU-accelerated RDKit cheminformatics code with nvMolKit
The closest alternatives to Diffdock nim are Drug discovery pipeline, Boltz2 nim, Openfold3 nim, Rfdiffusion nim and Openfold2 nim.
Yes. Drug discovery pipeline, Boltz2 nim, Openfold3 nim have a free or open-source option.