InsilicoΣ
Drug Discovery, Cheminformatics & Bioinformatics
About Our Team Publications Mobile App Contact Us Login Register

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:

Stark, H., Faltings, F., Choi, M., Xie, Y., Hur, E., O'Donnell, T., Bushuiev, A., Uçar, T., Passaro, S., Mao, W., Reveiz, M., et al. BoltzGen: Toward Universal Binder Design. bioRxiv (2025).
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

AI Lab