基于卷积神经网络和Softmax的蛋白质二级结构预测  

Protein Secondary Structure Prediction Using Convolutional Neural Network and Softmax

作　　者：王蕾蕾 成金勇[1] 

机构地区：[1]齐鲁工业大学(山东省科学院),计算机科学与技术学院,山东济南

出　　处：《计算机科学与应用》2019年第2期450-457,共8页Computer Science and Application

基　　金：山东省自然科学基金(No.ZR2017LB024)项目资助.

摘　　要：蛋白质二级结构预测是生物信息学的重要组成部分,在生物信息学领域具有重要意义。本文提出了一种新的卷积神经网络结合Softmax分类器的算法预测蛋白质二级结构。首先用改进的卷积神经网络对蛋白质氨基酸序列进行特征提取,然后把卷积神经网络中第三次卷积后的输出作为Softmax分类器的输入并进行训练和预测。我们将本文提出的方法在25PDB数据集上做了3-折交叉验证,结果证明蛋白质二级结构预测的准确率有提高。Protein secondary structure prediction belongs to bioinformatics, and it’s important in research area. In this paper, we propose a new prediction way of protein using convolutional neural networks and Softmax. First, the improved convolutional neural network is used to extract the characteristics of the protein amino acid sequence, and then the third convolved output in the convolutional neural network is used as input to the Softmax classifier, and these data are trained and predicted. The dataset is a typical 25PDB dataset for protein. In terms of accuracy, the method is the cross validation based on the 3-fold. The results demonstrate that the accuracy of protein secondary structure prediction is improved.

关 键 词：蛋白质二级结构 卷积神经网络 Softmax分类器 

分 类 号：TP1[自动化与计算机技术—控制理论与控制工程]