Learning protein dynamics

所有生物体都含有数百万种蛋白质;生物聚合物折叠成三维生物活性结构，在调节生命和疾病方面发挥着至关重要的作用。研究已经看到了很多关于确定不同蛋白质的原子结构的焦点。然而，这些生物聚合物的灵活运动在其生物（正常）功能中起着至关重要的作用。近年来，机器学习已经彻底改变了我们在许多科学领域解释数据的方式。例如，深度神经网络AlphaFold 2可以预测蛋白质的3-dimensonal结构，其形状在实验上是未知的[1]。在我们的研究中，我们设计了一个深度神经网络，它也可以从分子模拟中学习特定蛋白质的结构集合[2]。该项目建立在这一突破之上。[1]J. Jumper等人，使用AlphaFold进行高精度蛋白质结构预测，Nature 596，2021。[2]V.K.拉马斯瓦米南卡罗来纳州Musson，C.G.马萨诸塞州威尔科克斯德贾科米学习蛋白质构象空间与卷积和潜在插值，物理评论X 11，2021。

All living organisms contain millions of proteins; biopolymers that fold into three-dimensional biologically active structures playing a vital role in the regulation of life and diseases. Research has seen a lot of focus on determining the atomic structure of different proteins. However, the flexible movement of these biopolymers plays a crucial role in their biological (mal)function. In recent years, machine learning has been revolutionizing the way we interpret data in many scientific areas. For example, the deep neural network AlphaFold2 can predict the 3-diminsonal structures of proteins, whose shape is not known experimentally [1]. In our research, we have designed a deep neural network that can also learn an ensemble of structures of specific proteins from molecular simulations [2]. This project builds upon this breakthrough.[1] J. Jumper et al., Highly accurate protein structure prediction with AlphaFold, Nature 596, 2021.[2] V.K. Ramaswamy, S.C. Musson, C.G. Willcocks, M.T. Degiacomi. Learning protein conformational space with convolutions and latent interpolations, Physical Review X 11, 2021.