Precise and interpretable neural networks reveal epigenetic signatures of aging across youth in health and disease
IntroductionDNA methylation (DNAm) age clocks are powerful tools for measuring biological age, providing insights into aging risks and outcomes beyond chronological age. While traditional models are effective, their interpretability is limited by their dependence on small and potentially stochastic...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Aging |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fragi.2024.1526146/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832590799125086208 |
|---|---|
| author | David Martínez-Enguita Thomas Hillerton Julia Åkesson Daniel Kling Maria Lerm Mika Gustafsson |
| author_facet | David Martínez-Enguita Thomas Hillerton Julia Åkesson Daniel Kling Maria Lerm Mika Gustafsson |
| author_sort | David Martínez-Enguita |
| collection | DOAJ |
| description | IntroductionDNA methylation (DNAm) age clocks are powerful tools for measuring biological age, providing insights into aging risks and outcomes beyond chronological age. While traditional models are effective, their interpretability is limited by their dependence on small and potentially stochastic sets of CpG sites. Here, we propose that the reliability of DNAm age clocks should stem from their capacity to detect comprehensive and targeted aging signatures.MethodsWe compiled publicly available DNAm whole-blood samples (n = 17,726) comprising the entire human lifespan (0–112 years). We used a pre-trained network-coherent autoencoder (NCAE) to compress DNAm data into embeddings, with which we trained interpretable neural network epigenetic clocks. We then retrieved their age-specific epigenetic signatures of aging and examined their functional enrichments in age-associated biological processes.ResultsWe introduce NCAE-CombClock, a novel highly precise (R2 = 0.978, mean absolute error = 1.96 years) deep neural network age clock integrating data-driven DNAm embeddings and established CpG age markers. Additionally, we developed a suite of interpretable NCAE-Age neural network classifiers tailored for adolescence and young adulthood. These clocks can accurately classify individuals at critical developmental ages in youth (AUROC = 0.953, 0.972, and 0.927, for 15, 18, and 21 years) and capture fine-grained, single-year DNAm signatures of aging that are enriched in biological processes associated with anatomic and neuronal development, immunoregulation, and metabolism. We showcased the practical applicability of this approach by identifying candidate mechanisms underlying the altered pace of aging observed in pediatric Crohn’s disease.DiscussionIn this study, we present a deep neural network epigenetic clock, named NCAE-CombClock, that improves age prediction accuracy in large datasets, and a suite of explainable neural network clocks for robust age classification across youth. Our models offer broad applications in personalized medicine and aging research, providing a valuable resource for interpreting aging trajectories in health and disease. |
| format | Article |
| id | doaj-art-26f2081f959141408dcdb184d6703671 |
| institution | Kabale University |
| issn | 2673-6217 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Aging |
| spelling | doaj-art-26f2081f959141408dcdb184d67036712025-01-23T06:56:36ZengFrontiers Media S.A.Frontiers in Aging2673-62172025-01-01510.3389/fragi.2024.15261461526146Precise and interpretable neural networks reveal epigenetic signatures of aging across youth in health and diseaseDavid Martínez-Enguita0Thomas Hillerton1Julia Åkesson2Daniel Kling3Maria Lerm4Mika Gustafsson5Division of Bioinformatics, Department of Physics, Chemistry and Biology, Linköping University, Linköping, SwedenDivision of Bioinformatics, Department of Physics, Chemistry and Biology, Linköping University, Linköping, SwedenDivision of Bioinformatics, Department of Physics, Chemistry and Biology, Linköping University, Linköping, SwedenDepartment of Forensic Genetics and Toxicology, Swedish National Board of Forensic Medicine, Linköping, SwedenDivision of Inflammation and Infection, Department of Biomedical and Clinical Sciences, Linköping University, Linköping, SwedenDivision of Bioinformatics, Department of Physics, Chemistry and Biology, Linköping University, Linköping, SwedenIntroductionDNA methylation (DNAm) age clocks are powerful tools for measuring biological age, providing insights into aging risks and outcomes beyond chronological age. While traditional models are effective, their interpretability is limited by their dependence on small and potentially stochastic sets of CpG sites. Here, we propose that the reliability of DNAm age clocks should stem from their capacity to detect comprehensive and targeted aging signatures.MethodsWe compiled publicly available DNAm whole-blood samples (n = 17,726) comprising the entire human lifespan (0–112 years). We used a pre-trained network-coherent autoencoder (NCAE) to compress DNAm data into embeddings, with which we trained interpretable neural network epigenetic clocks. We then retrieved their age-specific epigenetic signatures of aging and examined their functional enrichments in age-associated biological processes.ResultsWe introduce NCAE-CombClock, a novel highly precise (R2 = 0.978, mean absolute error = 1.96 years) deep neural network age clock integrating data-driven DNAm embeddings and established CpG age markers. Additionally, we developed a suite of interpretable NCAE-Age neural network classifiers tailored for adolescence and young adulthood. These clocks can accurately classify individuals at critical developmental ages in youth (AUROC = 0.953, 0.972, and 0.927, for 15, 18, and 21 years) and capture fine-grained, single-year DNAm signatures of aging that are enriched in biological processes associated with anatomic and neuronal development, immunoregulation, and metabolism. We showcased the practical applicability of this approach by identifying candidate mechanisms underlying the altered pace of aging observed in pediatric Crohn’s disease.DiscussionIn this study, we present a deep neural network epigenetic clock, named NCAE-CombClock, that improves age prediction accuracy in large datasets, and a suite of explainable neural network clocks for robust age classification across youth. Our models offer broad applications in personalized medicine and aging research, providing a valuable resource for interpreting aging trajectories in health and disease.https://www.frontiersin.org/articles/10.3389/fragi.2024.1526146/fullDNA methylationneural networksage clockepigenetic ageyouth |
| spellingShingle | David Martínez-Enguita Thomas Hillerton Julia Åkesson Daniel Kling Maria Lerm Mika Gustafsson Precise and interpretable neural networks reveal epigenetic signatures of aging across youth in health and disease Frontiers in Aging DNA methylation neural networks age clock epigenetic age youth |
| title | Precise and interpretable neural networks reveal epigenetic signatures of aging across youth in health and disease |
| title_full | Precise and interpretable neural networks reveal epigenetic signatures of aging across youth in health and disease |
| title_fullStr | Precise and interpretable neural networks reveal epigenetic signatures of aging across youth in health and disease |
| title_full_unstemmed | Precise and interpretable neural networks reveal epigenetic signatures of aging across youth in health and disease |
| title_short | Precise and interpretable neural networks reveal epigenetic signatures of aging across youth in health and disease |
| title_sort | precise and interpretable neural networks reveal epigenetic signatures of aging across youth in health and disease |
| topic | DNA methylation neural networks age clock epigenetic age youth |
| url | https://www.frontiersin.org/articles/10.3389/fragi.2024.1526146/full |
| work_keys_str_mv | AT davidmartinezenguita preciseandinterpretableneuralnetworksrevealepigeneticsignaturesofagingacrossyouthinhealthanddisease AT thomashillerton preciseandinterpretableneuralnetworksrevealepigeneticsignaturesofagingacrossyouthinhealthanddisease AT juliaakesson preciseandinterpretableneuralnetworksrevealepigeneticsignaturesofagingacrossyouthinhealthanddisease AT danielkling preciseandinterpretableneuralnetworksrevealepigeneticsignaturesofagingacrossyouthinhealthanddisease AT marialerm preciseandinterpretableneuralnetworksrevealepigeneticsignaturesofagingacrossyouthinhealthanddisease AT mikagustafsson preciseandinterpretableneuralnetworksrevealepigeneticsignaturesofagingacrossyouthinhealthanddisease |