Clinical Utility of Protein Language Models in Resolution of Variants of Uncertain Significance in KCNQ1, KCNH2, and SCN5A Compared With Patch-Clamp Functional Characterization.

IF 6 2区 医学 Q1 CARDIAC & CARDIOVASCULAR SYSTEMS
Dan Ye, Ramin Garmany, Estefania Martinez-Barrios, Xiaozhi Gao, Raquel Almeida Lopes Neves, David J Tester, Sahej Bains, Wei Zhou, John R Giudicessi, Michael J Ackerman
{"title":"Clinical Utility of Protein Language Models in Resolution of Variants of Uncertain Significance in <i>KCNQ1, KCNH2</i>, and <i>SCN5A</i> Compared With Patch-Clamp Functional Characterization.","authors":"Dan Ye, Ramin Garmany, Estefania Martinez-Barrios, Xiaozhi Gao, Raquel Almeida Lopes Neves, David J Tester, Sahej Bains, Wei Zhou, John R Giudicessi, Michael J Ackerman","doi":"10.1161/CIRCGEN.124.004584","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Genetic testing for cardiac channelopathies is the standard of care. However, many rare genetic variants remain classified as variants of uncertain significance (VUS) due to lack of epidemiological and functional data. Whether deep protein language models may aid in VUS resolution remains unknown. Here, we set out to compare how 2 deep protein language models perform at VUS resolution in the 3 most common long-QT syndrome-causative genes compared with the gold-standard patch clamp.</p><p><strong>Methods: </strong>A total of 72 rare nonsynonymous VUS (9 <i>KCNQ1,</i> 19 <i>KCNH2</i>, and 50 <i>SCN5A</i>) were engineered by site-directed mutagenesis and expressed in either HEK293 cells or TSA201 cells. Whole-cell patch-clamp technique was used to functionally characterize these variants. The protein language models, evolutionary scale modeling, version 1b and AlphaMissense, were used to predict the variant effect of missense variants and compared with patch clamp.</p><p><strong>Results: </strong>Considering variants in all 3 genes, the evolutionary scale modeling, version 1b model had a receiver operating characteristic curve-area under the curve of 0.75 (<i>P</i>=0.0003). It had a sensitivity of 88% and a specificity of 50%. AlphaMissense performed well compared with patch-clamp with an receiver operating characteristic curve-area under the curve of 0.85 (<i>P</i><0.0001), sensitivity of 80%, and specificity of 76%.</p><p><strong>Conclusions: </strong>Deep protein language models aid in VUS resolution with high sensitivity but lower specificity. Thus, these tools cannot fully replace functional characterization but can aid in reducing the number of variants that may require functional analysis.</p>","PeriodicalId":10326,"journal":{"name":"Circulation: Genomic and Precision Medicine","volume":null,"pages":null},"PeriodicalIF":6.0000,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Circulation: Genomic and Precision Medicine","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1161/CIRCGEN.124.004584","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/8/9 0:00:00","PubModel":"Epub","JCR":"Q1","JCRName":"CARDIAC & CARDIOVASCULAR SYSTEMS","Score":null,"Total":0}
引用次数: 0

Abstract

Background: Genetic testing for cardiac channelopathies is the standard of care. However, many rare genetic variants remain classified as variants of uncertain significance (VUS) due to lack of epidemiological and functional data. Whether deep protein language models may aid in VUS resolution remains unknown. Here, we set out to compare how 2 deep protein language models perform at VUS resolution in the 3 most common long-QT syndrome-causative genes compared with the gold-standard patch clamp.

Methods: A total of 72 rare nonsynonymous VUS (9 KCNQ1, 19 KCNH2, and 50 SCN5A) were engineered by site-directed mutagenesis and expressed in either HEK293 cells or TSA201 cells. Whole-cell patch-clamp technique was used to functionally characterize these variants. The protein language models, evolutionary scale modeling, version 1b and AlphaMissense, were used to predict the variant effect of missense variants and compared with patch clamp.

Results: Considering variants in all 3 genes, the evolutionary scale modeling, version 1b model had a receiver operating characteristic curve-area under the curve of 0.75 (P=0.0003). It had a sensitivity of 88% and a specificity of 50%. AlphaMissense performed well compared with patch-clamp with an receiver operating characteristic curve-area under the curve of 0.85 (P<0.0001), sensitivity of 80%, and specificity of 76%.

Conclusions: Deep protein language models aid in VUS resolution with high sensitivity but lower specificity. Thus, these tools cannot fully replace functional characterization but can aid in reducing the number of variants that may require functional analysis.

蛋白质语言模型在解决 KCNQ1、KCNH2 和 SCN5A 中意义不确定的变异方面的临床实用性与膜片钳功能表征的比较。
背景:心脏通道病的基因检测是治疗的标准。然而,由于缺乏流行病学和功能数据,许多罕见的基因变异仍被归类为意义不确定的变异(VUS)。深度蛋白质语言模型能否帮助解决 VUS 问题仍是未知数。在此,我们着手比较两种深度蛋白质语言模型与黄金标准膜片钳相比在 3 个最常见长 QT 综合征致病基因的 VUS 解析中的表现:通过定点突变共设计了 72 个罕见的非同义 VUS(9 个 KCNQ1、19 个 KCNH2 和 50 个 SCN5A),并在 HEK293 细胞或 TSA201 细胞中表达。利用全细胞贴片钳技术对这些变体进行了功能表征。蛋白质语言模型ESM1b和AlphaMissense被用来预测错义变体的变异效应,并与膜片钳进行比较:考虑到所有 3 个基因中的变异,ESM1b 模型的接收运算曲线下面积为 0.75(P=0.0003)。灵敏度为 88%,特异性为 50%。与膜片钳相比,AlphaMissense 表现出色,接收器运算曲线下面积为 0.85(PConclusions.P=0.0003):深度蛋白质语言模型有助于解析 VUS,灵敏度较高,但特异性较低。因此,这些工具不能完全取代功能表征,但可以帮助减少可能需要进行功能分析的变体数量。
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
Circulation: Genomic and Precision Medicine
Circulation: Genomic and Precision Medicine Biochemistry, Genetics and Molecular Biology-Genetics
CiteScore
9.20
自引率
5.40%
发文量
144
期刊介绍: Circulation: Genomic and Precision Medicine is a distinguished journal dedicated to advancing the frontiers of cardiovascular genomics and precision medicine. It publishes a diverse array of original research articles that delve into the genetic and molecular underpinnings of cardiovascular diseases. The journal's scope is broad, encompassing studies from human subjects to laboratory models, and from in vitro experiments to computational simulations. Circulation: Genomic and Precision Medicine is committed to publishing studies that have direct relevance to human cardiovascular biology and disease, with the ultimate goal of improving patient care and outcomes. The journal serves as a platform for researchers to share their groundbreaking work, fostering collaboration and innovation in the field of cardiovascular genomics and precision 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
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