Research and Information Systems, LLC, Indianapolis, IN, USA.
Department of Physics, Indiana University Purdue University Indianapolis, Indianapolis, IN, USA.
Methods Mol Biol. 2021;2190:307-316. doi: 10.1007/978-1-0716-0826-5_15.
We have studied the ability of three types of neural networks to predict the closeness of a given protein model to the native structure associated with its sequence. We show that a partial combination of the Levenberg-Marquardt algorithm and the back-propagation algorithm produced the best results, giving the lowest error and largest Pearson correlation coefficient. We also find, as previous studies, that adding associative memory to a neural network improves its performance. Additionally, we find that the hybrid method we propose was the most robust in the sense that other configurations of it experienced less decline in comparison to the other methods. We find that the hybrid networks also undergo more fluctuations on the path to convergence. We propose that these fluctuations allow for better sampling. Overall we find it may be beneficial to treat different parts of a neural network with varied computational approaches during optimization.
我们研究了三种类型的神经网络预测给定蛋白质模型与序列相关的天然结构接近程度的能力。我们表明，莱文伯格-马夸尔特算法和反向传播算法的部分组合产生了最佳结果，给出了最低的误差和最大的皮尔逊相关系数。我们还发现，像以前的研究一样，向神经网络添加联想记忆可以提高其性能。此外，我们发现，我们提出的混合方法在稳健性方面是最稳健的，因为与其他方法相比，它的其他配置经历的下降较小。我们发现混合网络在收敛过程中也会经历更多的波动。我们提出，这些波动可以实现更好的采样。总的来说，我们发现，在优化过程中，用不同的计算方法处理神经网络的不同部分可能是有益的。
