Modeling transcriptomic age using knowledge-primed artificial neural networks.

IF 5.4 Q1 GERIATRICS & GERONTOLOGY NPJ Aging and Mechanisms of Disease Pub Date : 2021-06-01 DOI:10.1038/s41514-021-00068-5
Nicholas Holzscheck, Cassandra Falckenhayn, Jörn Söhle, Boris Kristof, Ralf Siegner, André Werner, Janka Schössow, Clemens Jürgens, Henry Völzke, Horst Wenck, Marc Winnefeld, Elke Grönniger, Lars Kaderali
{"title":"Modeling transcriptomic age using knowledge-primed artificial neural networks.","authors":"Nicholas Holzscheck, Cassandra Falckenhayn, Jörn Söhle, Boris Kristof, Ralf Siegner, André Werner, Janka Schössow, Clemens Jürgens, Henry Völzke, Horst Wenck, Marc Winnefeld, Elke Grönniger, Lars Kaderali","doi":"10.1038/s41514-021-00068-5","DOIUrl":null,"url":null,"abstract":"<p><p>The development of 'age clocks', machine learning models predicting age from biological data, has been a major milestone in the search for reliable markers of biological age and has since become an invaluable tool in aging research. However, beyond their unquestionable utility, current clocks offer little insight into the molecular biological processes driving aging, and their inner workings often remain non-transparent. Here we propose a new type of age clock, one that couples predictivity with interpretability of the underlying biology, achieved through the incorporation of prior knowledge into the model design. The clock, an artificial neural network constructed according to well-described biological pathways, allows the prediction of age from gene expression data of skin tissue with high accuracy, while at the same time capturing and revealing aging states of the pathways driving the prediction. The model recapitulates known associations of aging gene knockdowns in simulation experiments and demonstrates its utility in deciphering the main pathways by which accelerated aging conditions such as Hutchinson-Gilford progeria syndrome, as well as pro-longevity interventions like caloric restriction, exert their effects.</p>","PeriodicalId":19334,"journal":{"name":"NPJ Aging and Mechanisms of Disease","volume":null,"pages":null},"PeriodicalIF":5.4000,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8169742/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"NPJ Aging and Mechanisms of Disease","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1038/s41514-021-00068-5","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"GERIATRICS & GERONTOLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

The development of 'age clocks', machine learning models predicting age from biological data, has been a major milestone in the search for reliable markers of biological age and has since become an invaluable tool in aging research. However, beyond their unquestionable utility, current clocks offer little insight into the molecular biological processes driving aging, and their inner workings often remain non-transparent. Here we propose a new type of age clock, one that couples predictivity with interpretability of the underlying biology, achieved through the incorporation of prior knowledge into the model design. The clock, an artificial neural network constructed according to well-described biological pathways, allows the prediction of age from gene expression data of skin tissue with high accuracy, while at the same time capturing and revealing aging states of the pathways driving the prediction. The model recapitulates known associations of aging gene knockdowns in simulation experiments and demonstrates its utility in deciphering the main pathways by which accelerated aging conditions such as Hutchinson-Gilford progeria syndrome, as well as pro-longevity interventions like caloric restriction, exert their effects.

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
利用知识先导人工神经网络建立转录组年龄模型
年龄钟 "是从生物数据中预测年龄的机器学习模型,它的开发是寻找可靠的生物年龄标志物的一个重要里程碑,自此成为衰老研究中的一个宝贵工具。然而,除了其无可置疑的实用性之外,目前的时钟对驱动衰老的分子生物学过程几乎没有提供深入的见解,而且其内部工作原理往往仍然不透明。在这里,我们提出了一种新型的年龄钟,它通过将先验知识纳入模型设计,将预测性与底层生物学的可解释性结合在一起。该时钟是一个人工神经网络,根据描述完善的生物通路构建而成,可以从皮肤组织的基因表达数据中高精度地预测年龄,同时捕捉并揭示驱动预测的通路的衰老状态。该模型再现了模拟实验中已知的衰老基因敲除关联,并证明了它在破译哈钦森-吉尔福德早衰综合征等加速衰老病症以及热量限制等长寿干预措施产生影响的主要途径方面的实用性。
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
NPJ Aging and Mechanisms of Disease
NPJ Aging and Mechanisms of Disease Medicine-Geriatrics and Gerontology
自引率
0.00%
发文量
0
审稿时长
8 weeks
期刊介绍: npj Aging and Mechanisms of Disease is an online open access journal that provides a forum for the world’s most important research in the fields of aging and aging-related disease. The journal publishes papers from all relevant disciplines, encouraging those that shed light on the mechanisms behind aging and the associated diseases. The journal’s scope includes, but is not restricted to, the following areas (not listed in order of preference): • cellular and molecular mechanisms of aging and aging-related diseases • interventions to affect the process of aging and longevity • homeostatic regulation and aging • age-associated complications • translational research into prevention and treatment of aging-related diseases • mechanistic bases for epidemiological aspects of aging-related disease.
期刊最新文献
EPB41L4A-AS1 is required to maintain basal autophagy to modulates Aβ clearance Dynamics of Wnt/β-catenin reporter activity throughout whole life in a naturally short-lived vertebrate Healthcare on the brink: navigating the challenges of an aging society in the United States Oxidative damage in the gastrocnemius predicts long-term survival in patients with peripheral artery disease The use of a systems approach to increase NAD+ in human participants
×
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