P2DFlow: A Protein Ensemble Generative Model with SE(3) Flow Matching
This work addresses the need for efficient protein ensemble prediction to aid in understanding protein functions, but it appears incremental as it builds on existing flow matching methods with domain-specific enhancements.
The authors tackled the problem of predicting structural ensembles of proteins, which are crucial for understanding biological functions, by developing P2DFlow, a generative model based on SE(3) flow matching. The model outperformed baseline models on MD datasets, capturing dynamic fluctuations as evidenced in crystal structures and simulations.
Biological processes, functions, and properties are intricately linked to the ensemble of protein conformations, rather than being solely determined by a single stable conformation. In this study, we have developed P2DFlow, a generative model based on SE(3) flow matching, to predict the structural ensembles of proteins. We specifically designed a valuable prior for the flow process and enhanced the model's ability to distinguish each intermediate state by incorporating an additional dimension to describe the ensemble data, which can reflect the physical laws governing the distribution of ensembles, so that the prior knowledge can effectively guide the generation process. When trained and evaluated on the MD datasets of ATLAS, P2DFlow outperforms other baseline models on extensive experiments, successfully capturing the observable dynamic fluctuations as evidenced in crystal structure and MD simulations. As a potential proxy agent for protein molecular simulation, the high-quality ensembles generated by P2DFlow could significantly aid in understanding protein functions across various scenarios. Code is available at https://github.com/BLEACH366/P2DFlow