Developing a Kinase-Specific Target Selection Method Using a Structure-Based Machine Learning Approach.

Q2 Biochemistry, Genetics and Molecular Biology
Advances and Applications in Bioinformatics and Chemistry Pub Date : 2020-12-02 eCollection Date: 2020-01-01 DOI:10.2147/AABC.S278900
Arina Afanasyeva, Chioko Nagao, Kenji Mizuguchi
{"title":"Developing a Kinase-Specific Target Selection Method Using a Structure-Based Machine Learning Approach.","authors":"Arina Afanasyeva,&nbsp;Chioko Nagao,&nbsp;Kenji Mizuguchi","doi":"10.2147/AABC.S278900","DOIUrl":null,"url":null,"abstract":"<p><strong>Introduction: </strong>Despite recent advances in the drug discovery field, developing selective kinase inhibitors remains a complicated issue for a number of reasons, one of which is that there are striking structural similarities in the ATP-binding pockets of kinases.</p><p><strong>Objective: </strong>To address this problem, we have designed a machine learning model utilizing various structure-based and energy-based descriptors to better characterize protein-ligand interactions.</p><p><strong>Methods: </strong>In this work, we use a dataset of 104 human kinases with available PDB structures and experimental activity data against 1202 small-molecule compounds from the PubChem BioAssay dataset \"Navigating the Kinome\". We propose structure-based interaction descriptors to build activity predicting machine learning model.</p><p><strong>Results and discussion: </strong>We report a ligand-oriented computational method for accurate kinase target prioritizing. Our method shows high accuracy compared to similar structure-based activity prediction methods, and more importantly shows the same prediction accuracy when tested on the special set of structurally remote compounds, showing that it is unbiased to ligand structural similarity in the training set data. We hope that our approach will be useful for the development of novel highly selective kinase inhibitors.</p>","PeriodicalId":53584,"journal":{"name":"Advances and Applications in Bioinformatics and Chemistry","volume":"13 ","pages":"27-40"},"PeriodicalIF":0.0000,"publicationDate":"2020-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.2147/AABC.S278900","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Advances and Applications in Bioinformatics and Chemistry","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.2147/AABC.S278900","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2020/1/1 0:00:00","PubModel":"eCollection","JCR":"Q2","JCRName":"Biochemistry, Genetics and Molecular Biology","Score":null,"Total":0}
引用次数: 2

Abstract

Introduction: Despite recent advances in the drug discovery field, developing selective kinase inhibitors remains a complicated issue for a number of reasons, one of which is that there are striking structural similarities in the ATP-binding pockets of kinases.

Objective: To address this problem, we have designed a machine learning model utilizing various structure-based and energy-based descriptors to better characterize protein-ligand interactions.

Methods: In this work, we use a dataset of 104 human kinases with available PDB structures and experimental activity data against 1202 small-molecule compounds from the PubChem BioAssay dataset "Navigating the Kinome". We propose structure-based interaction descriptors to build activity predicting machine learning model.

Results and discussion: We report a ligand-oriented computational method for accurate kinase target prioritizing. Our method shows high accuracy compared to similar structure-based activity prediction methods, and more importantly shows the same prediction accuracy when tested on the special set of structurally remote compounds, showing that it is unbiased to ligand structural similarity in the training set data. We hope that our approach will be useful for the development of novel highly selective kinase inhibitors.

Abstract Image

Abstract Image

Abstract Image

使用基于结构的机器学习方法开发激酶特异性靶标选择方法。
导论:尽管最近在药物发现领域取得了进展,但由于许多原因,开发选择性激酶抑制剂仍然是一个复杂的问题,其中一个原因是激酶的atp结合口袋具有惊人的结构相似性。目的:为了解决这个问题,我们设计了一个机器学习模型,利用各种基于结构和基于能量的描述符来更好地表征蛋白质-配体的相互作用。方法:在这项工作中,我们使用了来自PubChem BioAssay数据集“导航Kinome”的104种具有可用PDB结构的人类激酶数据集和针对1202种小分子化合物的实验活性数据。我们提出了基于结构的交互描述符来构建活动预测机器学习模型。结果和讨论:我们报告了一种面向配体的精确激酶目标优先排序的计算方法。与类似的基于结构的活性预测方法相比,我们的方法具有较高的预测精度,更重要的是,在特殊的结构距离较远的化合物集上进行测试时,我们的方法具有相同的预测精度,表明该方法对训练集数据中的配体结构相似性没有偏倚。我们希望我们的方法将有助于开发新的高选择性激酶抑制剂。
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
Advances and Applications in Bioinformatics and Chemistry
Advances and Applications in Bioinformatics and Chemistry Biochemistry, Genetics and Molecular Biology-Biochemistry, Genetics and Molecular Biology (miscellaneous)
CiteScore
6.50
自引率
0.00%
发文量
7
审稿时长
16 weeks
×
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