Significance of Sequence Features in Classification of Protein–Protein Interactions Using Machine Learning

IF 1.9 4区 生物学 Q4 BIOCHEMISTRY & MOLECULAR BIOLOGY The Protein Journal Pub Date : 2023-12-19 DOI:10.1007/s10930-023-10168-8
Sini S. Raj, S. S. Vinod Chandra
{"title":"Significance of Sequence Features in Classification of Protein–Protein Interactions Using Machine Learning","authors":"Sini S. Raj,&nbsp;S. S. Vinod Chandra","doi":"10.1007/s10930-023-10168-8","DOIUrl":null,"url":null,"abstract":"<div><p>Protein–protein interactions are crucial for the entry of viruses into the cell. Understanding the mechanism of interactions is essential in studying human-virus association, developing new biologics and drug candidates, as well as viral infections and antiviral responses. Experimental methods to analyze human-virus protein–protein interactions based on protein sequence data are time-consuming and labor-intensive, so machine learning models are being developed to predict interactions and determine large-scale interactomes between species. The present work highlights the importance of sequence features in classifying interacting and non-interacting proteins from the protein sequence data. Higher dimensional amino acid sequence features such as Amino Acid Composition (AAC), Dipeptide Composition (DPC), Grouped Amino Acid Composition (GAAC), Pseudo-Amino Acid Composition (PAAC) etc., are extracted. Following feature extraction, three datasets were created: Dataset 1 contains all of the extracted features. While Datasets 2 and 3 contain the most relevant features obtained through dimensionality reduction. To analyze the importance of high-dimensional features and their participation in protein–protein interactions, a random forest classifier is trained on three datasets. With dimensionality reduction, the model exhibited exceptional accuracy, indicating that dimensionality reduction fails to capture the complexity of interactions and the underlying relationships between human and viral proteins. As a result of retaining high-dimensional features, it is possible to capture all the characteristics of protein–protein interactions that resemble host–pathogen associations, leading to the development of biologically meaningful models. Our proposed approach is a more realistic and comprehensive classification model, leading to deeper insights and better applications in virology and drug development.</p></div>","PeriodicalId":793,"journal":{"name":"The Protein Journal","volume":"43 1","pages":"72 - 83"},"PeriodicalIF":1.9000,"publicationDate":"2023-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"The Protein Journal","FirstCategoryId":"2","ListUrlMain":"https://link.springer.com/article/10.1007/s10930-023-10168-8","RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"BIOCHEMISTRY & MOLECULAR BIOLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

Protein–protein interactions are crucial for the entry of viruses into the cell. Understanding the mechanism of interactions is essential in studying human-virus association, developing new biologics and drug candidates, as well as viral infections and antiviral responses. Experimental methods to analyze human-virus protein–protein interactions based on protein sequence data are time-consuming and labor-intensive, so machine learning models are being developed to predict interactions and determine large-scale interactomes between species. The present work highlights the importance of sequence features in classifying interacting and non-interacting proteins from the protein sequence data. Higher dimensional amino acid sequence features such as Amino Acid Composition (AAC), Dipeptide Composition (DPC), Grouped Amino Acid Composition (GAAC), Pseudo-Amino Acid Composition (PAAC) etc., are extracted. Following feature extraction, three datasets were created: Dataset 1 contains all of the extracted features. While Datasets 2 and 3 contain the most relevant features obtained through dimensionality reduction. To analyze the importance of high-dimensional features and their participation in protein–protein interactions, a random forest classifier is trained on three datasets. With dimensionality reduction, the model exhibited exceptional accuracy, indicating that dimensionality reduction fails to capture the complexity of interactions and the underlying relationships between human and viral proteins. As a result of retaining high-dimensional features, it is possible to capture all the characteristics of protein–protein interactions that resemble host–pathogen associations, leading to the development of biologically meaningful models. Our proposed approach is a more realistic and comprehensive classification model, leading to deeper insights and better applications in virology and drug development.

Abstract Image

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
利用机器学习对蛋白质-蛋白质相互作用进行分类时序列特征的重要性。
蛋白质与蛋白质之间的相互作用对病毒进入细胞至关重要。了解相互作用的机制对于研究人类与病毒的关联、开发新的生物制剂和候选药物以及病毒感染和抗病毒反应至关重要。基于蛋白质序列数据分析人类-病毒蛋白质-蛋白质相互作用的实验方法耗时耗力,因此人们正在开发机器学习模型来预测相互作用并确定物种间的大规模相互作用组。本研究强调了序列特征在从蛋白质序列数据中对相互作用和非相互作用蛋白质进行分类方面的重要性。本研究提取了氨基酸组成(AAC)、二肽组成(DPC)、成组氨基酸组成(GAAC)、假氨基酸组成(PAAC)等高维氨基酸序列特征。特征提取后,创建了三个数据集:数据集 1 包含所有提取的特征。数据集 2 和 3 包含通过降维获得的最相关特征。为了分析高维特征的重要性及其在蛋白质-蛋白质相互作用中的参与情况,在三个数据集上训练了随机森林分类器。通过降维,模型表现出了极高的准确性,这表明降维无法捕捉到人类和病毒蛋白质之间相互作用的复杂性和潜在关系。由于保留了高维特征,因此有可能捕捉到与宿主-病原体关联类似的蛋白质-蛋白质相互作用的所有特征,从而开发出具有生物学意义的模型。我们提出的方法是一种更现实、更全面的分类模型,能为病毒学和药物开发带来更深刻的见解和更好的应用。
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 去求助
来源期刊
The Protein Journal
The Protein Journal 生物-生化与分子生物学
CiteScore
5.20
自引率
0.00%
发文量
57
审稿时长
12 months
期刊介绍: The Protein Journal (formerly the Journal of Protein Chemistry) publishes original research work on all aspects of proteins and peptides. These include studies concerned with covalent or three-dimensional structure determination (X-ray, NMR, cryoEM, EPR/ESR, optical methods, etc.), computational aspects of protein structure and function, protein folding and misfolding, assembly, genetics, evolution, proteomics, molecular biology, protein engineering, protein nanotechnology, protein purification and analysis and peptide synthesis, as well as the elucidation and interpretation of the molecular bases of biological activities of proteins and peptides. We accept original research papers, reviews, mini-reviews, hypotheses, opinion papers, and letters to the editor.
期刊最新文献
Influence of Cataract Causing Mutations on αA-Crystallin: A Computational Approach Unraveling the interaction between a glycolytic regulator protein EhPpdk and an anaphase promoting complex protein EhApc10: yeast two hybrid screening, in vitro binding assays and molecular simulation study Unravelling the Significance of Seed Proteomics: Insights into Seed Development, Function, and Agricultural Applications HaloClass: Salt-Tolerant Protein Classification with Protein Language Models Exosomes with Engineered Brain Derived Neurotrophic Factor on Their Surfaces Can Proliferate Menstrual Blood Derived Mesenchymal Stem Cells: Targeted Delivery for a Protein Drug
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1