Rapid discrimination between deleterious and benign missense mutations in the CAGI 6 experiment.

IF 3.8 3区 医学 Q2 GENETICS & HEREDITY Human Genomics Pub Date : 2024-08-27 DOI:10.1186/s40246-024-00655-z
Eshel Faraggi, Robert L Jernigan, Andrzej Kloczkowski
{"title":"Rapid discrimination between deleterious and benign missense mutations in the CAGI 6 experiment.","authors":"Eshel Faraggi, Robert L Jernigan, Andrzej Kloczkowski","doi":"10.1186/s40246-024-00655-z","DOIUrl":null,"url":null,"abstract":"<p><p>We describe the machine learning tool that we applied in the CAGI 6 experiment to predict whether single residue mutations in proteins are deleterious or benign. This tool was trained using only single sequences, i.e., without multiple sequence alignments or structural information. Instead, we used global characterizations of the protein sequence. Training and testing data for human gene mutations was obtained from ClinVar (ncbi.nlm.nih.gov/pub/ClinVar/), and for non-human gene mutations from Uniprot (www.uniprot.org). Testing was done on post-training data from ClinVar. This testing yielded high AUC and Matthews correlation coefficient (MCC) for well trained examples but low generalizability. For genes with either sparse or unbalanced training data, the prediction accuracy is poor. The resulting prediction server is available online at http://www.mamiris.com/Shoni.cagi6.</p>","PeriodicalId":13183,"journal":{"name":"Human Genomics","volume":"18 1","pages":"89"},"PeriodicalIF":3.8000,"publicationDate":"2024-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11350969/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Human Genomics","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1186/s40246-024-00655-z","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"GENETICS & HEREDITY","Score":null,"Total":0}
引用次数: 0

Abstract

We describe the machine learning tool that we applied in the CAGI 6 experiment to predict whether single residue mutations in proteins are deleterious or benign. This tool was trained using only single sequences, i.e., without multiple sequence alignments or structural information. Instead, we used global characterizations of the protein sequence. Training and testing data for human gene mutations was obtained from ClinVar (ncbi.nlm.nih.gov/pub/ClinVar/), and for non-human gene mutations from Uniprot (www.uniprot.org). Testing was done on post-training data from ClinVar. This testing yielded high AUC and Matthews correlation coefficient (MCC) for well trained examples but low generalizability. For genes with either sparse or unbalanced training data, the prediction accuracy is poor. The resulting prediction server is available online at http://www.mamiris.com/Shoni.cagi6.

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
在 CAGI 6 实验中快速区分有害和良性错义突变。
我们介绍了在 CAGI 6 实验中应用的机器学习工具,该工具用于预测蛋白质中的单残基突变是有害的还是良性的。该工具仅使用单序列进行训练,即不使用多序列比对或结构信息。相反,我们使用了蛋白质序列的全局特征。人类基因突变的训练和测试数据来自 ClinVar (ncbi.nlm.nih.gov/pub/ClinVar/),非人类基因突变的训练和测试数据来自 Uniprot (www.uniprot.org)。对来自 ClinVar 的训练后数据进行了测试。测试结果表明,训练有素的示例具有较高的 AUC 和马修斯相关系数 (MCC),但通用性较低。对于训练数据稀少或不平衡的基因,预测准确率较低。由此产生的预测服务器可在 http://www.mamiris.com/Shoni.cagi6 在线查阅。
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
Human Genomics
Human Genomics GENETICS & HEREDITY-
CiteScore
6.00
自引率
2.20%
发文量
55
审稿时长
11 weeks
期刊介绍: Human Genomics is a peer-reviewed, open access, online journal that focuses on the application of genomic analysis in all aspects of human health and disease, as well as genomic analysis of drug efficacy and safety, and comparative genomics. Topics covered by the journal include, but are not limited to: pharmacogenomics, genome-wide association studies, genome-wide sequencing, exome sequencing, next-generation deep-sequencing, functional genomics, epigenomics, translational genomics, expression profiling, proteomics, bioinformatics, animal models, statistical genetics, genetic epidemiology, human population genetics and comparative genomics.
期刊最新文献
Integration of single-cell sequencing and drug sensitivity profiling reveals an 11-gene prognostic model for liver cancer. SCAN: a nanopore-based, cost effective decision-supporting tool for mass screening of aneuploidies. Advancing understanding of human variability through toxicokinetic modeling, in vitro-in vivo extrapolation, and new approach methodologies. Genetic heterogeneity in familial forms of genetic generalized epilepsy: from mono- to oligogenism. Analysis of public perceptions on the use of artificial intelligence in genomic medicine.
×
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