可扩展的归一化流实现大分子的玻尔兹曼生成器
Scalable Normalizing Flows Enable Boltzmann Generators for Macromolecules
AI总结：
提出一种利用分割通道和门控注意力的新型归一化流架构，结合2-Wasserstein损失的多阶段训练策略，成功实现了大分子的Boltzmann Generators建模。
摘要：
蛋白质的玻尔兹曼分布为其所有功能状态提供了路线图。归一化流是建模该分布的有前景的工具，但现有方法对于典型的药理学靶点不可行；由于系统尺寸、分子内势能的异质性以及长程相互作用，它们在计算上变得不可行。为解决这些问题，我们提出了一种新颖的流架构，利用分割通道和门控注意力来高效学习由内部坐标定义的蛋白质构象分布。我们展示了通过利用2-Wasserstein损失，可以平滑从最大似然训练到基于能量训练的过渡，从而实现大分子的Boltzmann Generators训练。我们在villin headpiece HP35(nle-nle)（一个35残基的亚结构）和protein G（一个56残基的蛋白质）上评估了我们的模型和训练策略。我们证明，仅使用最大似然等标准架构和训练策略会失败，而我们新颖的架构和多阶段训练策略能够成功建模protein G和HP35的构象分布。
英文摘要：
The Boltzmann distribution of a protein provides a roadmap to all of its functional states. Normalizing flows are a promising tool for modeling this distribution, but current methods are intractable for typical pharmacological targets; they become computationally intractable due to the size of the system, heterogeneity of intra-molecular potential energy, and long-range interactions. To remedy these issues, we present a novel flow architecture that utilizes split channels and gated attention to efficiently learn the conformational distribution of proteins defined by internal coordinates. We show that by utilizing a 2-Wasserstein loss, one can smooth the transition from maximum likelihood training to energy-based training, enabling the training of Boltzmann Generators for macromolecules. We evaluate our model and training strategy on villin headpiece HP35(nle-nle), a 35-residue subdomain, and protein G, a 56-residue protein. We demonstrate that standard architectures and training strategies, such as maximum likelihood alone, fail while our novel architecture and multi-stage training strategy are able to model the conformational distributions of protein G and HP35.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
