IEEE/ACM Trans Comput Biol Bioinform. 2019 Mar-Apr;16(2):596-606. doi: 10.1109/TCBB.2017.2784434. Epub 2017 Dec 18.
Computational protein structure prediction is a long-standing challenge in bioinformatics. In the process of predicting protein 3D structures, it is common that parts of an experimental structure are missing or parts of a predicted structure need to be remodeled. The process of predicting local protein structures of particular regions is called loop modeling. In this paper, five new loop modeling methods based on machine learning techniques, called NearLooper, ConLooper, ResLooper, HyLooper1, and HyLooper2 are proposed. NearLooper is based on the nearest neighbor technique. ConLooper applies deep convolutional neural networks to predict ${\mathrm{C}}_{{{\alpha }}}$Cα atoms distance matrix as an orientation-independent representation of protein structure. ResLooper uses residual neural networks instead of deep convolutional neural networks. HyLooper1 combines the results of NearLooper and ConLooper while HyLooper2 combines NearLooper and ResLooper. Three commonly used benchmarks for loop modeling are used to compare the performance between these methods and existing state-of-the-art methods. The experiment results show promising performance in which our best method improves existing state-of-the-art methods by 28 and 54 percent of average RMSD on two datasets while being comparable on the other one.
计算蛋白质结构预测是生物信息学中的一个长期挑战。在预测蛋白质 3D 结构的过程中，实验结构的部分缺失或预测结构的部分需要进行重构是很常见的。预测特定区域局部蛋白质结构的过程称为环建模。在本文中，提出了五种基于机器学习技术的新的环建模方法，分别称为 NearLooper、ConLooper、ResLooper、HyLooper1 和 HyLooper2。NearLooper 基于最近邻技术。ConLooper 应用深度卷积神经网络来预测 ${\mathrm{C}}_{{{\alpha }}}$Cα原子距离矩阵，作为蛋白质结构的一种与方向无关的表示。ResLooper 使用残差神经网络代替深度卷积神经网络。HyLooper1 结合了 NearLooper 和 ConLooper 的结果，而 HyLooper2 则结合了 NearLooper 和 ResLooper。使用三种常用的环建模基准来比较这些方法与现有最先进方法之间的性能。实验结果表明，我们的最佳方法在两个数据集上的平均 RMSD 分别提高了现有最先进方法 28%和 54%，而在另一个数据集上则具有可比性。
