The biological functions of proteins often depend on dynamic structural
ensembles. In this work, 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. Code is available
at this https URL

生物蛋白质的功能常依赖于动态结构集合，本研究通过开发一种基于流动的生成建模方法来学习和采样蛋白质的构象空间，利用 AlphaFold 和 ESMFold 等高精度单状态预测器进行改进，获得了名为 AlphaFlow 和 ESMFlow 的蛋白质结构的序列有条件的生成模型。在 PDB 上经过训练和评估时，我们的方法在精确性和多样性方面相比于具有 MSA 子采样的 AlphaFold 更具优势。当进一步在全原子 MD 的集合上进行训练后，我们的方法能够准确捕捉未知蛋白质的构象灵活性、位置分布和高阶集合观测量。此外，我们的方法可以使静态 PDB 结构多样化，并具有比复制的 MD 轨迹更快的收敛时间，展示了其作为昂贵的基于物理的仿真的替代品的潜力。