Poster
AlphaFold Meets Flow Matching for Generating Protein Ensembles
Bowen Jing · Bonnie Berger · Tommi Jaakkola
The biological functions of proteins often depend on dynamic structural ensembles, but existing protein structure prediction methods have largely focused on static experimental structures. To bridge this gap, we develop a flow-based generative modeling approach for learning and sampling the conformational landscapes of proteins. We repurpose highly accurate single-state predictors such as AlphaFold and ESMFold and fine-tune them under a custom flow matching framework to obtain sequence-conditoned generative models of protein structure called AlphaFlow and ESMFlow. When trained and evaluated on the PDB, our method provides a superior combination of precision and diversity compared to AlphaFold with MSA subsampling. When further trained on ensembles from all-atom MD, our method accurately captures conformational flexibility, positional distributions, and higher-order ensemble observables for unseen proteins. Moreover, our method can diversify a static PDB structure with faster wall-clock convergence to certain equilibrium properties than replicate MD trajectories, demonstrating its potential as a proxy for expensive physics-based simulations.
Live content is unavailable. Log in and register to view live content