文献类型：期刊文献

中文题名：基于卷积长短时记忆神经网络的蛋白质二级结构预测

英文题名：Protein Secondary Structure Prediction Based on Convolutional Long Short-Time Memory Neural Networks

作者：郭延哺[1] 李维华[1] 王兵益[2] 金宸[1]

第一作者：郭延哺

机构：[1]云南大学信息学院;[2]中国林业科学研究院资源昆虫研究所

年份：2018

卷号：31

期号：6

起止页码：562-568

中文期刊名：模式识别与人工智能

外文期刊名：Pattern Recognition and Artificial Intelligence

收录：CSTPCD;;Scopus;北大核心:【北大核心2017】；CSCD:【CSCD2017_2018】；

基金：国家自然科学基金项目(No.11661081);教育部科技发展中心"云数融合科教创新"基金(No.2017B00016);云南省科技创新人才培养项目;云南省创新团队项目资助~~

语种：中文

中文关键词：生物信息学;蛋白质二级结构;卷积神经网络;长短时记忆神经网络

外文关键词：Bioinformatics;Protein Secondary Structure;Convolutional Neural Networks;Long Short-Term Memory Neural Networks

分类号：TP391

摘要：鉴于不同类型氨基酸的相互作用对蛋白质结构预测的影响不同,文中融合卷积神经网络和长短时记忆神经网络模型,提出卷积长短时记忆神经网络,并应用到蛋白质8类二级结构的预测中.首先基于氨基酸序列的类别信息和氨基酸结构的进化信息表示蛋白质序列,并采用卷积提取氨基酸残基之间的局部相关特征,然后利用双向长短时记忆神经网络提取蛋白质序列内部残基之间的远程相互作用,最后将提取的蛋白质的局部相关特征和远程相互作用用于蛋白质8类二级结构的预测.实验表明,相比基准方法,文中模型提高8类二级结构预测的精度,并具有良好的可扩展性.
Since the interaction of different types of amino acid has an influence on the prediction of protein structure, convolutional neural networks and long short-term memory neural networks are integrated. A eonvolutional long short-term memory neural network is proposed to predict 8-class protein secondary structures. Firstly, the protein sequence is represented based on the amino acid sequence class feature and the amino acid structure profile feature. The local correlation characteristics between amino acid residues are extracted by the convolutional operations, and then the long-range interactions between the residues on protein sequences are extracted by the hi-directional long short-term memory network. Finally, the local correlation characteristics and long-range interactions between amino acid residues are employed to predict protein secondary structures. Experimental results show that the proposed model achieves a higher accuracy than the baselines and the framework has good scalability.