Novel prediction models for genotoxicity based on biomarker genes in human HepaRG™ cells.

IF 4.5 2区 医学 Q2 MEDICINE, RESEARCH & EXPERIMENTAL
Anouck Thienpont, Stefaan Verhulst, Leo A Van Grunsven, Vera Rogiers, Tamara Vanhaecke, Birgit Mertens
{"title":"Novel prediction models for genotoxicity based on biomarker genes in human HepaRG™ cells.","authors":"Anouck Thienpont,&nbsp;Stefaan Verhulst,&nbsp;Leo A Van Grunsven,&nbsp;Vera Rogiers,&nbsp;Tamara Vanhaecke,&nbsp;Birgit Mertens","doi":"10.14573/altex.2206201","DOIUrl":null,"url":null,"abstract":"<p><p>Transcriptomics-based biomarkers are promising new approach methodologies (NAMs) to identify molecular events underlying the genotoxic mode of action of chemicals. Previously, we developed the GENOMARK biomarker, consisting of 84 genes selected based on whole genomics DNA microarray profiles of 24 (non-)genotoxic reference chemicals covering different modes of action in metabolically competent human HepaRG™ cells. In the present study, new prediction models for genotoxicity were developed based on an extended reference dataset of 38 chemicals including existing as well as newly generated gene expression data. Both unsupervised and supervised machine learning algorithms were used, but as unsupervised machine learning did not clearly distinguish between groups, the performance of two supervised machine learning algorithms, i.e., support vector machine (SVM) and random forest (RF), was evaluated. More specifically, the predictive accuracy was compared, the sensitivity to outliers for one or more biomarker genes was assessed, and the prediction performance for 10 misleading positive chemicals exposed at their IC10 concentration was determined. In addition, the applicability of both prediction models on a publicly available gene expression dataset, generated with RNA-sequencing, was investigated. Overall, the RF and SVM models were complementary in their classification of chemicals for genotoxicity. To facilitate data analysis, an online application was developed, combining the outcomes of both prediction models. This research demonstrates that the combination of gene expression data with supervised machine learning algorithms can contribute to the ongoing paradigm shift towards a more human-relevant in vitro genotoxicity testing strategy without the use of experimental animals.</p>","PeriodicalId":51231,"journal":{"name":"Altex-Alternatives To Animal Experimentation","volume":"40 2","pages":"271-286"},"PeriodicalIF":4.5000,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Altex-Alternatives To Animal Experimentation","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.14573/altex.2206201","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MEDICINE, RESEARCH & EXPERIMENTAL","Score":null,"Total":0}
引用次数: 1

Abstract

Transcriptomics-based biomarkers are promising new approach methodologies (NAMs) to identify molecular events underlying the genotoxic mode of action of chemicals. Previously, we developed the GENOMARK biomarker, consisting of 84 genes selected based on whole genomics DNA microarray profiles of 24 (non-)genotoxic reference chemicals covering different modes of action in metabolically competent human HepaRG™ cells. In the present study, new prediction models for genotoxicity were developed based on an extended reference dataset of 38 chemicals including existing as well as newly generated gene expression data. Both unsupervised and supervised machine learning algorithms were used, but as unsupervised machine learning did not clearly distinguish between groups, the performance of two supervised machine learning algorithms, i.e., support vector machine (SVM) and random forest (RF), was evaluated. More specifically, the predictive accuracy was compared, the sensitivity to outliers for one or more biomarker genes was assessed, and the prediction performance for 10 misleading positive chemicals exposed at their IC10 concentration was determined. In addition, the applicability of both prediction models on a publicly available gene expression dataset, generated with RNA-sequencing, was investigated. Overall, the RF and SVM models were complementary in their classification of chemicals for genotoxicity. To facilitate data analysis, an online application was developed, combining the outcomes of both prediction models. This research demonstrates that the combination of gene expression data with supervised machine learning algorithms can contribute to the ongoing paradigm shift towards a more human-relevant in vitro genotoxicity testing strategy without the use of experimental animals.

基于人类HepaRG™细胞生物标记基因的新型遗传毒性预测模型。
基于转录组学的生物标志物是一种很有前途的新方法方法(NAMs),用于识别化学物质遗传毒性作用模式下的分子事件。此前,我们开发了GENOMARK生物标志物,由84个基因组成,这些基因是根据24种(非)遗传毒性参考化学物质的全基因组DNA微阵列谱选择的,这些化学物质覆盖了代谢能力强的人类HepaRG™细胞中不同的作用模式。在本研究中,基于38种化学物质的扩展参考数据集,包括现有的和新生成的基因表达数据,开发了新的遗传毒性预测模型。我们同时使用了无监督和有监督机器学习算法,但由于无监督机器学习没有明确的分组区分,所以我们对支持向量机(SVM)和随机森林(RF)这两种有监督机器学习算法的性能进行了评估。更具体地说,比较了预测的准确性,评估了对一个或多个生物标记基因的异常值的敏感性,并确定了10种暴露在其IC10浓度下的误导性阳性化学物质的预测性能。此外,研究了这两种预测模型在由rna测序生成的公开基因表达数据集上的适用性。总体而言,RF和SVM模型在化学物质遗传毒性分类方面是互补的。为了便于数据分析,我们开发了一个在线应用程序,将两种预测模型的结果结合起来。这项研究表明,基因表达数据与监督机器学习算法的结合可以促进正在进行的范式转变,在不使用实验动物的情况下,向更与人类相关的体外遗传毒性测试策略转变。
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
Altex-Alternatives To Animal Experimentation
Altex-Alternatives To Animal Experimentation MEDICINE, RESEARCH & EXPERIMENTAL-
CiteScore
7.70
自引率
8.90%
发文量
89
审稿时长
2 months
期刊介绍: ALTEX publishes original articles, short communications, reviews, as well as news and comments and meeting reports. Manuscripts submitted to ALTEX are evaluated by two expert reviewers. The evaluation takes into account the scientific merit of a manuscript and its contribution to animal welfare and the 3R principle.
×
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