A Systematic Review of the Application of Graph Neural Networks to Extract Candidate Genes and Biological Associations.

IF 1.6 3区 医学 Q3 GENETICS & HEREDITY
Ankita Saxena, Bridgette Nixon, Amelia Boyd, James Evans, Stephen V Faraone
{"title":"A Systematic Review of the Application of Graph Neural Networks to Extract Candidate Genes and Biological Associations.","authors":"Ankita Saxena, Bridgette Nixon, Amelia Boyd, James Evans, Stephen V Faraone","doi":"10.1002/ajmg.b.33031","DOIUrl":null,"url":null,"abstract":"<p><p>The development of high throughput technologies has resulted in the collection of large quantities of genomic and transcriptomic data. However, identifying disease-associated genes or networks from these data has remained an ongoing challenge. In recent years, graph neural networks (GNNs) have emerged as a promising analytical tool, but it is not well understood which characteristics of these models result in improved performance. We conducted a systematic search and review of publications that used GNNs to identify disease-associated biological interactions. Information was extracted about model characteristics and performance with the goal of examining the relationship between these factors and performance. Data leakage was found in 31% of these models. For node level tasks, univariate positive associations were identified between model accuracy and use of hyper parameter optimization, data leakage via hyperparameter optimization, test set size, and total dataset size. Among graph level tasks, an increase in AUC was identified in association with testing method and a decrease with optimization reporting. Data leakage may pose an issue for GNN-based approaches; the adoption of best practice guidelines and consistent reporting of model design would be beneficial for future studies.</p>","PeriodicalId":7673,"journal":{"name":"American Journal of Medical Genetics Part B: Neuropsychiatric Genetics","volume":" ","pages":"e33031"},"PeriodicalIF":1.6000,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"American Journal of Medical Genetics Part B: Neuropsychiatric Genetics","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1002/ajmg.b.33031","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"GENETICS & HEREDITY","Score":null,"Total":0}
引用次数: 0

Abstract

The development of high throughput technologies has resulted in the collection of large quantities of genomic and transcriptomic data. However, identifying disease-associated genes or networks from these data has remained an ongoing challenge. In recent years, graph neural networks (GNNs) have emerged as a promising analytical tool, but it is not well understood which characteristics of these models result in improved performance. We conducted a systematic search and review of publications that used GNNs to identify disease-associated biological interactions. Information was extracted about model characteristics and performance with the goal of examining the relationship between these factors and performance. Data leakage was found in 31% of these models. For node level tasks, univariate positive associations were identified between model accuracy and use of hyper parameter optimization, data leakage via hyperparameter optimization, test set size, and total dataset size. Among graph level tasks, an increase in AUC was identified in association with testing method and a decrease with optimization reporting. Data leakage may pose an issue for GNN-based approaches; the adoption of best practice guidelines and consistent reporting of model design would be beneficial for future studies.

图神经网络在提取候选基因和生物关联中的应用综述。
高通量技术的发展导致了大量基因组和转录组数据的收集。然而,从这些数据中识别疾病相关基因或网络仍然是一个持续的挑战。近年来,图神经网络(gnn)已经成为一种很有前途的分析工具,但人们并不清楚这些模型的哪些特征会导致性能的提高。我们对使用gnn识别疾病相关生物相互作用的出版物进行了系统的搜索和回顾。提取有关模型特征和性能的信息,目的是研究这些因素与性能之间的关系。其中31%的模型存在数据泄露。对于节点级任务,模型精度与使用超参数优化、通过超参数优化产生的数据泄漏、测试集大小和总数据集大小之间存在单变量正相关。在图级任务中,AUC的增加与测试方法有关,与优化报告有关。数据泄漏可能对基于gnn的方法构成问题;采用最佳实践指南和一致的模型设计报告将有利于未来的研究。
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
CiteScore
5.90
自引率
7.10%
发文量
40
审稿时长
4-8 weeks
期刊介绍: Neuropsychiatric Genetics, Part B of the American Journal of Medical Genetics (AJMG) , provides a forum for experimental and clinical investigations of the genetic mechanisms underlying neurologic and psychiatric disorders. It is a resource for novel genetics studies of the heritable nature of psychiatric and other nervous system disorders, characterized at the molecular, cellular or behavior levels. Neuropsychiatric Genetics publishes eight times per year.
×
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