Biologically informed deep learning for explainable epigenetic clocks

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Standard

Biologically informed deep learning for explainable epigenetic clocks. / Prosz, Aurel; Pipek, Orsolya; Börcsök, Judit; Palla, Gergely; Szallasi, Zoltan; Spisak, Sandor; Csabai, István.

I: Scientific Reports, Bind 14, 1306, 2024.

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Harvard

Prosz, A, Pipek, O, Börcsök, J, Palla, G, Szallasi, Z, Spisak, S & Csabai, I 2024, 'Biologically informed deep learning for explainable epigenetic clocks', Scientific Reports, bind 14, 1306. https://doi.org/10.1038/s41598-023-50495-5

APA

Prosz, A., Pipek, O., Börcsök, J., Palla, G., Szallasi, Z., Spisak, S., & Csabai, I. (2024). Biologically informed deep learning for explainable epigenetic clocks. Scientific Reports, 14, [1306]. https://doi.org/10.1038/s41598-023-50495-5

Vancouver

Prosz A, Pipek O, Börcsök J, Palla G, Szallasi Z, Spisak S o.a. Biologically informed deep learning for explainable epigenetic clocks. Scientific Reports. 2024;14. 1306. https://doi.org/10.1038/s41598-023-50495-5

Author

Prosz, Aurel ; Pipek, Orsolya ; Börcsök, Judit ; Palla, Gergely ; Szallasi, Zoltan ; Spisak, Sandor ; Csabai, István. / Biologically informed deep learning for explainable epigenetic clocks. I: Scientific Reports. 2024 ; Bind 14.

Bibtex

@article{d7040026d66744b9a844dabba805008a,

title = "Biologically informed deep learning for explainable epigenetic clocks",

abstract = "Ageing is often characterised by progressive accumulation of damage, and it is one of the most important risk factors for chronic disease development. Epigenetic mechanisms including DNA methylation could functionally contribute to organismal aging, however the key functions and biological processes may govern ageing are still not understood. Although age predictors called epigenetic clocks can accurately estimate the biological age of an individual based on cellular DNA methylation, their models have limited ability to explain the prediction algorithm behind and underlying key biological processes controlling ageing. Here we present XAI-AGE, a biologically informed, explainable deep neural network model for accurate biological age prediction across multiple tissue types. We show that XAI-AGE outperforms the first-generation age predictors and achieves similar results to deep learning-based models, while opening up the possibility to infer biologically meaningful insights of the activity of pathways and other abstract biological processes directly from the model.",

author = "Aurel Prosz and Orsolya Pipek and Judit B{\"o}rcs{\"o}k and Gergely Palla and Zoltan Szallasi and Sandor Spisak and Istv{\'a}n Csabai",

note = "Publisher Copyright: {\textcopyright} 2024, The Author(s).",

year = "2024",

doi = "10.1038/s41598-023-50495-5",

language = "English",

volume = "14",

journal = "Scientific Reports",

issn = "2045-2322",

publisher = "nature publishing group",

}

RIS

TY - JOUR

T1 - Biologically informed deep learning for explainable epigenetic clocks

AU - Prosz, Aurel

AU - Pipek, Orsolya

AU - Börcsök, Judit

AU - Palla, Gergely

AU - Szallasi, Zoltan

AU - Spisak, Sandor

AU - Csabai, István

PY - 2024

Y1 - 2024

N2 - Ageing is often characterised by progressive accumulation of damage, and it is one of the most important risk factors for chronic disease development. Epigenetic mechanisms including DNA methylation could functionally contribute to organismal aging, however the key functions and biological processes may govern ageing are still not understood. Although age predictors called epigenetic clocks can accurately estimate the biological age of an individual based on cellular DNA methylation, their models have limited ability to explain the prediction algorithm behind and underlying key biological processes controlling ageing. Here we present XAI-AGE, a biologically informed, explainable deep neural network model for accurate biological age prediction across multiple tissue types. We show that XAI-AGE outperforms the first-generation age predictors and achieves similar results to deep learning-based models, while opening up the possibility to infer biologically meaningful insights of the activity of pathways and other abstract biological processes directly from the model.

AB - Ageing is often characterised by progressive accumulation of damage, and it is one of the most important risk factors for chronic disease development. Epigenetic mechanisms including DNA methylation could functionally contribute to organismal aging, however the key functions and biological processes may govern ageing are still not understood. Although age predictors called epigenetic clocks can accurately estimate the biological age of an individual based on cellular DNA methylation, their models have limited ability to explain the prediction algorithm behind and underlying key biological processes controlling ageing. Here we present XAI-AGE, a biologically informed, explainable deep neural network model for accurate biological age prediction across multiple tissue types. We show that XAI-AGE outperforms the first-generation age predictors and achieves similar results to deep learning-based models, while opening up the possibility to infer biologically meaningful insights of the activity of pathways and other abstract biological processes directly from the model.

U2 - 10.1038/s41598-023-50495-5

DO - 10.1038/s41598-023-50495-5

M3 - Journal article

C2 - 38225268

AN - SCOPUS:85182460405

VL - 14

JO - Scientific Reports

JF - Scientific Reports

SN - 2045-2322

M1 - 1306

ER -

ID: 380359731