A novel hybrid CNN and BiGRU-Attention based deep learning model for protein function prediction.

IF 0.9 4区 数学 Q3 Mathematics
Lavkush Sharma, Akshay Deepak, Ashish Ranjan, Gopalakrishnan Krishnasamy
{"title":"A novel hybrid CNN and BiGRU-Attention based deep learning model for protein function prediction.","authors":"Lavkush Sharma,&nbsp;Akshay Deepak,&nbsp;Ashish Ranjan,&nbsp;Gopalakrishnan Krishnasamy","doi":"10.1515/sagmb-2022-0057","DOIUrl":null,"url":null,"abstract":"<p><p>Proteins are the building blocks of all living things. Protein function must be ascertained if the molecular mechanism of life is to be understood. While CNN is good at capturing short-term relationships, GRU and LSTM can capture long-term dependencies. A hybrid approach that combines the complementary benefits of these deep-learning models motivates our work. Protein Language models, which use attention networks to gather meaningful data and build representations for proteins, have seen tremendous success in recent years processing the protein sequences. In this paper, we propose a hybrid CNN + BiGRU - Attention based model with protein language model embedding that effectively combines the output of CNN with the output of BiGRU-Attention for predicting protein functions. We evaluated the performance of our proposed hybrid model on human and yeast datasets. The proposed hybrid model improves the Fmax value over the state-of-the-art model SDN2GO for the cellular component prediction task by 1.9 %, for the molecular function prediction task by 3.8 % and for the biological process prediction task by 0.6 % for human dataset and for yeast dataset the cellular component prediction task by 2.4 %, for the molecular function prediction task by 5.2 % and for the biological process prediction task by 1.2 %.</p>","PeriodicalId":49477,"journal":{"name":"Statistical Applications in Genetics and Molecular Biology","volume":"22 1","pages":""},"PeriodicalIF":0.9000,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Statistical Applications in Genetics and Molecular Biology","FirstCategoryId":"100","ListUrlMain":"https://doi.org/10.1515/sagmb-2022-0057","RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"Mathematics","Score":null,"Total":0}
引用次数: 0

Abstract

Proteins are the building blocks of all living things. Protein function must be ascertained if the molecular mechanism of life is to be understood. While CNN is good at capturing short-term relationships, GRU and LSTM can capture long-term dependencies. A hybrid approach that combines the complementary benefits of these deep-learning models motivates our work. Protein Language models, which use attention networks to gather meaningful data and build representations for proteins, have seen tremendous success in recent years processing the protein sequences. In this paper, we propose a hybrid CNN + BiGRU - Attention based model with protein language model embedding that effectively combines the output of CNN with the output of BiGRU-Attention for predicting protein functions. We evaluated the performance of our proposed hybrid model on human and yeast datasets. The proposed hybrid model improves the Fmax value over the state-of-the-art model SDN2GO for the cellular component prediction task by 1.9 %, for the molecular function prediction task by 3.8 % and for the biological process prediction task by 0.6 % for human dataset and for yeast dataset the cellular component prediction task by 2.4 %, for the molecular function prediction task by 5.2 % and for the biological process prediction task by 1.2 %.

一种基于CNN和BiGRU-Attention的新型混合深度学习模型用于蛋白质功能预测。
蛋白质是所有生物的基本组成部分。如果要了解生命的分子机制,就必须确定蛋白质的功能。CNN擅长捕捉短期关系,而GRU和LSTM可以捕捉长期依赖关系。结合了这些深度学习模型的互补优势的混合方法激励了我们的工作。蛋白质语言模型使用注意力网络来收集有意义的数据并建立蛋白质的表示,近年来在处理蛋白质序列方面取得了巨大的成功。在本文中,我们提出了一种基于蛋白质语言模型嵌入的CNN + BiGRU-Attention混合模型,有效地将CNN的输出与BiGRU-Attention的输出相结合,用于预测蛋白质功能。我们在人类和酵母数据集上评估了我们提出的混合模型的性能。所提出的混合模型比最先进的模型sn2go在细胞成分预测任务中的Fmax值提高了1.9 %,在分子功能预测任务中提高了3.8 %,在生物过程预测任务中提高了0.6 %,在人类数据集和酵母数据集的细胞成分预测任务中提高了2.4 %,在分子功能预测任务中提高了5.2 %,在生物过程预测任务中提高了1.2 %。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
CiteScore
1.20
自引率
11.10%
发文量
8
审稿时长
6-12 weeks
期刊介绍: Statistical Applications in Genetics and Molecular Biology seeks to publish significant research on the application of statistical ideas to problems arising from computational biology. The focus of the papers should be on the relevant statistical issues but should contain a succinct description of the relevant biological problem being considered. The range of topics is wide and will include topics such as linkage mapping, association studies, gene finding and sequence alignment, protein structure prediction, design and analysis of microarray data, molecular evolution and phylogenetic trees, DNA topology, and data base search strategies. Both original research and review articles will be warmly received.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信