条件通用微分方程捕捉c肽生产中的种群动态和个体间变化。

IF 3.5 2区 生物学 Q1 MATHEMATICAL & COMPUTATIONAL BIOLOGY
Max de Rooij, Natal A W van Riel, Shauna D O'Donovan
{"title":"条件通用微分方程捕捉c肽生产中的种群动态和个体间变化。","authors":"Max de Rooij, Natal A W van Riel, Shauna D O'Donovan","doi":"10.1038/s41540-025-00570-6","DOIUrl":null,"url":null,"abstract":"<p><p>Universal differential equations (UDEs) are an emerging approach in biomedical systems biology, integrating physiology-driven mathematical models with machine learning for data-driven model discovery in areas where knowledge of the underlying physiology is limited. However, current approaches to training UDEs do not directly accommodate heterogeneity in the underlying data. As a data-driven approach, UDEs are also vulnerable to overfitting and consequently cannot sufficiently generalize to heterogeneous populations. We propose a conditional UDE (cUDE) where we assume that the structure and weights of the embedded neural network are common across individuals, and introduce a conditioning parameter that is allowed to vary between individuals. In this way, the cUDE architecture can accommodate inter-individual variation in data while learning a generalizable network representation. We demonstrate the effectiveness of the cUDE as an extension of the UDE framework by training a cUDE model of c-peptide production. We show that our cUDE model can accurately describe postprandial c-peptide levels in individuals with normal glucose tolerance, impaired glucose tolerance, and type 2 diabetes mellitus. Furthermore, we show that the conditional parameter captures relevant inter-individual variation. Subsequently, we use symbolic regression to derive a generalizable analytical expression for c-peptide production.</p>","PeriodicalId":19345,"journal":{"name":"NPJ Systems Biology and Applications","volume":"11 1","pages":"84"},"PeriodicalIF":3.5000,"publicationDate":"2025-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12313987/pdf/","citationCount":"0","resultStr":"{\"title\":\"Conditional universal differential equations capture population dynamics and interindividual variation in c-peptide production.\",\"authors\":\"Max de Rooij, Natal A W van Riel, Shauna D O'Donovan\",\"doi\":\"10.1038/s41540-025-00570-6\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Universal differential equations (UDEs) are an emerging approach in biomedical systems biology, integrating physiology-driven mathematical models with machine learning for data-driven model discovery in areas where knowledge of the underlying physiology is limited. However, current approaches to training UDEs do not directly accommodate heterogeneity in the underlying data. As a data-driven approach, UDEs are also vulnerable to overfitting and consequently cannot sufficiently generalize to heterogeneous populations. We propose a conditional UDE (cUDE) where we assume that the structure and weights of the embedded neural network are common across individuals, and introduce a conditioning parameter that is allowed to vary between individuals. In this way, the cUDE architecture can accommodate inter-individual variation in data while learning a generalizable network representation. We demonstrate the effectiveness of the cUDE as an extension of the UDE framework by training a cUDE model of c-peptide production. We show that our cUDE model can accurately describe postprandial c-peptide levels in individuals with normal glucose tolerance, impaired glucose tolerance, and type 2 diabetes mellitus. Furthermore, we show that the conditional parameter captures relevant inter-individual variation. Subsequently, we use symbolic regression to derive a generalizable analytical expression for c-peptide production.</p>\",\"PeriodicalId\":19345,\"journal\":{\"name\":\"NPJ Systems Biology and Applications\",\"volume\":\"11 1\",\"pages\":\"84\"},\"PeriodicalIF\":3.5000,\"publicationDate\":\"2025-07-31\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12313987/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"NPJ Systems Biology and Applications\",\"FirstCategoryId\":\"99\",\"ListUrlMain\":\"https://doi.org/10.1038/s41540-025-00570-6\",\"RegionNum\":2,\"RegionCategory\":\"生物学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"MATHEMATICAL & COMPUTATIONAL BIOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"NPJ Systems Biology and Applications","FirstCategoryId":"99","ListUrlMain":"https://doi.org/10.1038/s41540-025-00570-6","RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MATHEMATICAL & COMPUTATIONAL BIOLOGY","Score":null,"Total":0}
引用次数: 0

摘要

通用微分方程(UDEs)是生物医学系统生物学中的一种新兴方法,将生理学驱动的数学模型与机器学习相结合,用于在基础生理学知识有限的领域发现数据驱动的模型。然而,目前训练数据集的方法并不能直接适应底层数据的异质性。作为一种数据驱动的方法,u也容易过度拟合,因此不能充分推广到异质人群。我们提出了一个条件UDE (cUDE),其中我们假设嵌入式神经网络的结构和权重在个体之间是共同的,并引入一个允许在个体之间变化的条件参数。通过这种方式,cUDE架构可以在学习可推广的网络表示的同时适应数据中的个体间变化。我们通过训练c肽生产的cUDE模型来证明cUDE作为UDE框架扩展的有效性。我们发现我们的cUDE模型可以准确地描述糖耐量正常、糖耐量受损和2型糖尿病个体的餐后c肽水平。此外,我们表明条件参数捕获相关的个体间变化。随后,我们使用符号回归来推导c肽生产的可推广的分析表达式。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Conditional universal differential equations capture population dynamics and interindividual variation in c-peptide production.

Universal differential equations (UDEs) are an emerging approach in biomedical systems biology, integrating physiology-driven mathematical models with machine learning for data-driven model discovery in areas where knowledge of the underlying physiology is limited. However, current approaches to training UDEs do not directly accommodate heterogeneity in the underlying data. As a data-driven approach, UDEs are also vulnerable to overfitting and consequently cannot sufficiently generalize to heterogeneous populations. We propose a conditional UDE (cUDE) where we assume that the structure and weights of the embedded neural network are common across individuals, and introduce a conditioning parameter that is allowed to vary between individuals. In this way, the cUDE architecture can accommodate inter-individual variation in data while learning a generalizable network representation. We demonstrate the effectiveness of the cUDE as an extension of the UDE framework by training a cUDE model of c-peptide production. We show that our cUDE model can accurately describe postprandial c-peptide levels in individuals with normal glucose tolerance, impaired glucose tolerance, and type 2 diabetes mellitus. Furthermore, we show that the conditional parameter captures relevant inter-individual variation. Subsequently, we use symbolic regression to derive a generalizable analytical expression for c-peptide production.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
NPJ Systems Biology and Applications
NPJ Systems Biology and Applications Mathematics-Applied Mathematics
CiteScore
5.80
自引率
0.00%
发文量
46
审稿时长
8 weeks
期刊介绍: npj Systems Biology and Applications is an online Open Access journal dedicated to publishing the premier research that takes a systems-oriented approach. The journal aims to provide a forum for the presentation of articles that help define this nascent field, as well as those that apply the advances to wider fields. We encourage studies that integrate, or aid the integration of, data, analyses and insight from molecules to organisms and broader systems. Important areas of interest include not only fundamental biological systems and drug discovery, but also applications to health, medical practice and implementation, big data, biotechnology, food science, human behaviour, broader biological systems and industrial applications of systems biology. We encourage all approaches, including network biology, application of control theory to biological systems, computational modelling and analysis, comprehensive and/or high-content measurements, theoretical, analytical and computational studies of system-level properties of biological systems and computational/software/data platforms enabling such studies.
×
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:604180095
Book学术官方微信