Boltz-1 Democratizing Biomolecular Interaction Modeling

Understanding biomolecular interactions is fundamental to advancing fields like drug discovery and protein design. In this paper, we introduce B<sc>oltz</sc>-1, an open-source deep learning model incorporating innovations in model architecture, speed optimization, and data processing achieving A<sc>lpha</sc>F<sc>old</sc>3-level accuracy in predicting the 3D structures of biomolecular complexes. B<sc>oltz</sc>-1 demonstrates a performance on-par with state-of-the-art commercial models on a range of diverse benchmarks, setting a new benchmark for commercially accessible tools in structural biology. Further, we push the boundary of capabilities of these models with B<sc>oltz-steering</sc>, a new inference time steering technique that is able to fix hallucinations and non-physical predictions from the models. By releasing the training and inference code, model weights, datasets, and benchmarks under the MIT open license, we aim to foster global collaboration, accelerate discoveries, and provide a robust platform for advancing biomolecular modeling.