Integrating Deep Learning Models with Genome-Wide Association Study-Based Identification Enhanced Phenotype Predictions in Group A Streptococcus.

IF 2.5 4区 生物学 Q3 BIOTECHNOLOGY & APPLIED MICROBIOLOGY
Peng-Ying Wang, Zhi-Song Chen, Xiaoguo Jiao, Yun-Juan Bao
{"title":"Integrating Deep Learning Models with Genome-Wide Association Study-Based Identification Enhanced Phenotype Predictions in Group A <i>Streptococcus</i>.","authors":"Peng-Ying Wang, Zhi-Song Chen, Xiaoguo Jiao, Yun-Juan Bao","doi":"10.4014/jmb.2411.11010","DOIUrl":null,"url":null,"abstract":"<p><p>Group A <i>Streptococcus</i> (GAS) is a major pathogen with diverse clinical outcomes linked to its genetic variability, making accurate phenotype prediction essential. While previous studies have identified many GAS-associated genetic factors, translating these findings into predictive models remains challenging due to data complexity. The current study aimed to integrate deep learning models with genome-wide association study-derived genetic variants to predict pathogenic phenotypes in GAS. We evaluated the performance of several deep neural network models, including CNN, ResNet18, LSTM, and their ensemble approach in predicting GAS phenotypes. It was found that the ensemble model consistently achieved the highest prediction accuracy across phenotypes. Models trained on the full 4722-genotype set outperformed those trained on a reduced 175-genotype set, underscoring the importance of comprehensive variant data in capturing complex genotype-phenotype interactions. Performance changes in the reduced 175-genotype set compared to the full-set genotype scenarios revealed the impact of data dimensionality on model effectiveness, with CNN remaining robust, while ResNet18 and LSTM underperformed. Our findings emphasized the potential of deep learning in phenotype prediction and the critical role of data-model compatibility.</p>","PeriodicalId":16481,"journal":{"name":"Journal of microbiology and biotechnology","volume":"35 ","pages":"e2411010"},"PeriodicalIF":2.5000,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of microbiology and biotechnology","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.4014/jmb.2411.11010","RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"BIOTECHNOLOGY & APPLIED MICROBIOLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

Group A Streptococcus (GAS) is a major pathogen with diverse clinical outcomes linked to its genetic variability, making accurate phenotype prediction essential. While previous studies have identified many GAS-associated genetic factors, translating these findings into predictive models remains challenging due to data complexity. The current study aimed to integrate deep learning models with genome-wide association study-derived genetic variants to predict pathogenic phenotypes in GAS. We evaluated the performance of several deep neural network models, including CNN, ResNet18, LSTM, and their ensemble approach in predicting GAS phenotypes. It was found that the ensemble model consistently achieved the highest prediction accuracy across phenotypes. Models trained on the full 4722-genotype set outperformed those trained on a reduced 175-genotype set, underscoring the importance of comprehensive variant data in capturing complex genotype-phenotype interactions. Performance changes in the reduced 175-genotype set compared to the full-set genotype scenarios revealed the impact of data dimensionality on model effectiveness, with CNN remaining robust, while ResNet18 and LSTM underperformed. Our findings emphasized the potential of deep learning in phenotype prediction and the critical role of data-model compatibility.

整合深度学习模型与基于全基因组关联研究的识别增强了A群链球菌的表型预测。
A群链球菌(GAS)是一种主要的病原体,其多种临床结果与其遗传变异性有关,因此准确的表型预测至关重要。虽然之前的研究已经确定了许多与天然气相关的遗传因素,但由于数据的复杂性,将这些发现转化为预测模型仍然具有挑战性。目前的研究旨在将深度学习模型与全基因组关联研究衍生的遗传变异相结合,以预测GAS的致病表型。我们评估了几种深度神经网络模型的性能,包括CNN、ResNet18、LSTM,以及它们的集成方法在预测GAS表型方面的性能。结果发现,集合模型在所有表型中均具有最高的预测精度。在完整4722基因型集上训练的模型优于在减少的175基因型集上训练的模型,强调了综合变异数据在捕获复杂的基因型-表型相互作用中的重要性。与完整的基因型场景相比,减少的175基因型集的性能变化揭示了数据维度对模型有效性的影响,CNN保持鲁棒性,而ResNet18和LSTM表现不佳。我们的研究结果强调了深度学习在表型预测中的潜力以及数据模型兼容性的关键作用。
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 求助全文
来源期刊
Journal of microbiology and biotechnology
Journal of microbiology and biotechnology BIOTECHNOLOGY & APPLIED MICROBIOLOGY-MICROBIOLOGY
CiteScore
5.50
自引率
3.60%
发文量
151
审稿时长
2 months
期刊介绍: The Journal of Microbiology and Biotechnology (JMB) is a monthly international journal devoted to the advancement and dissemination of scientific knowledge pertaining to microbiology, biotechnology, and related academic disciplines. It covers various scientific and technological aspects of Molecular and Cellular Microbiology, Environmental Microbiology and Biotechnology, Food Biotechnology, and Biotechnology and Bioengineering (subcategories are listed below). Launched in March 1991, the JMB is published by the Korean Society for Microbiology and Biotechnology (KMB) and distributed worldwide.
×
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