Fast and effective protein model refinement using deep graph neural networks.
Fast and effective protein model refinement using deep graph neural networks.
复制标题
DOI：
10.1038/s43588-021-00098-9
复制
发表时间：
2021-07
期刊：
影响因子：
--
通讯作者：
Xu J
中科院分区：
文献类型：
--
作者：
Jing X;Xu J
蛋白质模型精化是用于提高预测蛋白质模型质量的最后一步。目前最成功的改进方法依赖于广泛的构象采样，因此，即使是单个蛋白质模型也需要数小时或数天来改进。在这里，我们提出了一种快速有效的模型细化方法，该方法应用GNN（图神经网络）从初始模型预测细化的原子间距离概率分布，然后从预测的距离分布重建3D模型。在CASP（结构预测的关键评估）细化目标上进行测试，我们的方法具有与两个领先的人类小组Feig和Baker相当的准确性，但运行速度更快。我们的方法可以在1个CPU上在~11分钟内细化一个蛋白质模型，而Baker在60个CPU上需要~30小时，Feig在1个GPU上需要~16小时。最后，我们的研究表明，当允许非常有限的构象采样时，GNN在模型细化方面优于ResNet（卷积残差神经网络）。深度图神经网络可以用更少的计算资源有效地改进预测的蛋白质模型。准确性与主要的基于物理的方法相当，这些方法依赖于耗时的构象采样。
Protein model refinement is the last step applied to improve the quality of a predicted protein model. Currently the most successful refinement methods rely on extensive conformational sampling and thus, take hours or days to refine even a single protein model. Here we propose a fast and effective model refinement method that applies GNN (graph neural networks) to predict refined inter-atom distance probability distribution from an initial model and then rebuilds 3D models from the predicted distance distribution. Tested on the CASP (Critical Assessment of Structure Prediction) refinement targets, our method has comparable accuracy as two leading human groups Feig and Baker, but runs substantially faster. Our method may refine one protein model within ~11 minutes on 1 CPU while Baker needs ~30 hours on 60 CPUs and Feig needs ~16 hours on 1 GPU. Finally, our study shows that GNN outperforms ResNet (convolutional residual neural networks) for model refinement when very limited conformational sampling is allowed. Deep graph neural networks can refine a predicted protein model efficiently with less computing resources. The accuracy is comparable to that of the leading physics-based methods that rely on time consuming conformation sampling.