Boltz-1: A New Tool for Biomolecular Interaction Modeling
Author Information
Author(s): Wohlwend Jeremy, Corso Gabriele, Passaro Saro, Reveiz Mateo, Leidal Ken, Swiderski Wojtek, Portnoi Tally, Chinn Itamar, Silterra Jacob, Jaakkola Tommi, Barzilay Regina
Primary Institution: Cold Spring Harbor Laboratory
Hypothesis
Can Boltz-1 achieve AlphaFold 3-level accuracy in predicting biomolecular complex structures?
Conclusion
Boltz-1 matches the performance of top commercial models and sets a new standard for accessible structural biology tools.
Supporting Evidence
- Boltz-1 achieves AlphaFold 3-level accuracy in predicting 3D structures.
- The model demonstrates performance on par with state-of-the-art commercial models.
- Training and inference code, model weights, datasets, and benchmarks are released under the MIT open license.
Takeaway
Boltz-1 is a new computer program that helps scientists understand how molecules interact, making it easier for them to discover new drugs.
Methodology
The study introduces an open-source deep learning model with innovations in architecture, speed optimization, and data processing.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website