当前位置: X-MOL 学术Proteins Struct. Funct. Bioinform. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Hierarchical, rotation‐equivariant neural networks to select structural models of protein complexes
Proteins: Structure, Function, and Bioinformatics ( IF 3.2 ) Pub Date : 2020-12-02 , DOI: 10.1002/prot.26033
Stephan Eismann 1, 2 , Raphael J L Townshend 2 , Nathaniel Thomas 3 , Milind Jagota 2, 4 , Bowen Jing 2 , Ron O Dror 2, 5, 6, 7
Affiliation  

Predicting the structure of multi‐protein complexes is a grand challenge in biochemistry, with major implications for basic science and drug discovery. Computational structure prediction methods generally leverage predefined structural features to distinguish accurate structural models from less accurate ones. This raises the question of whether it is possible to learn characteristics of accurate models directly from atomic coordinates of protein complexes, with no prior assumptions. Here we introduce a machine learning method that learns directly from the 3D positions of all atoms to identify accurate models of protein complexes, without using any precomputed physics‐inspired or statistical terms. Our neural network architecture combines multiple ingredients that together enable end‐to‐end learning from molecular structures containing tens of thousands of atoms: a point‐based representation of atoms, equivariance with respect to rotation and translation, local convolutions, and hierarchical subsampling operations. When used in combination with previously developed scoring functions, our network substantially improves the identification of accurate structural models among a large set of possible models. Our network can also be used to predict the accuracy of a given structural model in absolute terms. The architecture we present is readily applicable to other tasks involving learning on 3D structures of large atomic systems.

中文翻译:

用于选择蛋白质复合物结构模型的分层、旋转等变神经网络

预测多蛋白复合物的结构是生物化学中的一项巨大挑战,对基础科学和药物发现具有重大意义。计算结构预测方法通常利用预定义的结构特征来区分准确的结构模型和不太准确的结构模型。这就提出了一个问题,即是否有可能直接从蛋白质复合物的原子坐标中学习准确模型的特征,而无需事先假设。在这里,我们介绍了一种机器学习方法,该方法直接从所有原子的 3D 位置学习,以识别蛋白质复合物的准确模型,而不使用任何预先计算的物理启发或统计术语。我们的神经网络架构结合了多种成分,可以从包含数万个原子的分子结构中进行端到端学习:基于点的原子表示、旋转和平移的等方差、局部卷积和分层子采样操作。当与先前开发的评分函数结合使用时,我们的网络大大提高了在大量可能模型中识别准确结构模型的能力。我们的网络还可用于以绝对值来预测给定结构模型的准确性。我们提出的架构很容易适用于其他涉及学习大型原子系统 3D 结构的任务。局部卷积和分层子采样操作。当与先前开发的评分函数结合使用时,我们的网络大大提高了在大量可能模型中识别准确结构模型的能力。我们的网络还可用于以绝对值来预测给定结构模型的准确性。我们提出的架构很容易适用于其他涉及学习大型原子系统 3D 结构的任务。局部卷积和分层子采样操作。当与先前开发的评分函数结合使用时,我们的网络大大提高了在大量可能模型中识别准确结构模型的能力。我们的网络还可用于以绝对值来预测给定结构模型的准确性。我们提出的架构很容易适用于其他涉及学习大型原子系统 3D 结构的任务。
更新日期:2020-12-02
down
wechat
bug