About BoltzGen
Universal Binder Design with All-Atom Generative Modeling
Cite This Tool
If you use BoltzGen in your research, please cite the original paper:
DOI: 10.1101/2025.11.20.689494
BibTeX
@article{stark2025boltzgen,
title={BoltzGen: Toward Universal Binder Design},
author={Stark, Hannes and Faltings, Felix and Choi, MinGyu and Xie, Yuxin and Hur, Eunsu and O'Donnell, Timothy and Bushuiev, Anton and U{\c{c}}ar, Tal{\i}p and Passaro, Saro and Mao, Weian and Reveiz, Mateo and Bushuiev, Roman and Pluskal, Tom{\'a}{\v{s}} and Sivic, Josef and Kreis, Karsten and Vahdat, Arash and others},
journal={bioRxiv},
year={2025},
publisher={Cold Spring Harbor Laboratory},
doi={10.1101/2025.11.20.689494}
}
License: MIT License — Open source, freely available for academic and commercial use. Developed at MIT by Stark, Corso, Barzilay, Jaakkola et al.
Overview
BoltzGen is an all-atom generative model for designing proteins and peptides of any modality that can bind to a wide range of biomolecular targets, including proteins, nucleic acids, and small molecules.
It unifies binder design and structure prediction into a single model by building strong structural reasoning capabilities about target-binder interactions directly into the generative design process. BoltzGen supports multiple binder modalities (nanobodies, peptides, miniproteins) and reaches state-of-the-art performance in both folding accuracy and binding affinity prediction.
Key Capabilities
-
Multi-Modality Design
Design nanobodies, peptides, and miniproteins with a single model
-
All-Atom Generation
Generates full atomic coordinates, not just sequences
-
Unified Design + Folding
Jointly predicts binder structure and target-binder complex
-
Binding Score Estimation
Provides confidence scores for designed binder-target interactions
Applications
-
Therapeutic Antibody Design
Generate nanobody candidates targeting disease-relevant proteins
-
Peptide Drug Discovery
Design peptide binders with optimized affinity and specificity
-
Protein-Protein Interaction Modulators
Target challenging PPI interfaces with designed miniproteins
-
Biosensor Development
Create binding domains for diagnostic and sensing applications