Interpretable deep learning of single-cell and epigenetic data reveals novel molecular insights in aging

Abstract Deep learning (DL) and explainable artificial intelligence (XAI) have emerged as powerful machine-learning tools to identify complex predictive data patterns in a spatial or temporal domain. Here, we consider the application of DL and XAI to large omic datasets, in order to study biological...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhi-Peng Li, Zhaozhen Du, De-Shuang Huang, Andrew E. Teschendorff
Format: Article
Language:English
Published: Nature Portfolio 2025-02-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-89646-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849764905230532608
author Zhi-Peng Li
Zhaozhen Du
De-Shuang Huang
Andrew E. Teschendorff
author_facet Zhi-Peng Li
Zhaozhen Du
De-Shuang Huang
Andrew E. Teschendorff
author_sort Zhi-Peng Li
collection DOAJ
description Abstract Deep learning (DL) and explainable artificial intelligence (XAI) have emerged as powerful machine-learning tools to identify complex predictive data patterns in a spatial or temporal domain. Here, we consider the application of DL and XAI to large omic datasets, in order to study biological aging at the molecular level. We develop an advanced multi-view graph-level representation learning (MGRL) framework that integrates prior biological network information, to build molecular aging clocks at cell-type resolution, which we subsequently interpret using XAI. We apply this framework to one of the largest single-cell transcriptomic datasets encompassing over a million immune cells from 981 donors, revealing a ribosomal gene subnetwork, whose expression correlates with age independently of cell-type. Application of the same DL-XAI framework to DNA methylation data of sorted monocytes reveals an epigenetically deregulated inflammatory response pathway whose activity increases with age. We show that the ribosomal module and inflammatory pathways would not have been discovered had we used more standard machine-learning methods. In summary, the computational deep learning framework presented here illustrates how deep learning when combined with explainable AI tools, can reveal novel biological insights into the complex process of aging.
format Article
id doaj-art-cbbaea73ed1e404d8157a1b512e44313
institution DOAJ
issn 2045-2322
language English
publishDate 2025-02-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-cbbaea73ed1e404d8157a1b512e443132025-08-20T03:05:01ZengNature PortfolioScientific Reports2045-23222025-02-0115111810.1038/s41598-025-89646-1Interpretable deep learning of single-cell and epigenetic data reveals novel molecular insights in agingZhi-Peng Li0Zhaozhen Du1De-Shuang Huang2Andrew E. Teschendorff3Ningbo Institute of Digital Twin, Eastern Institute of TechnologyCAS Key Laboratory of Computational Biology, Shanghai Institute of Nutrition and Health, University of Chinese Academy of Sciences, Chinese Academy of SciencesNingbo Institute of Digital Twin, Eastern Institute of TechnologyCAS Key Laboratory of Computational Biology, Shanghai Institute of Nutrition and Health, University of Chinese Academy of Sciences, Chinese Academy of SciencesAbstract Deep learning (DL) and explainable artificial intelligence (XAI) have emerged as powerful machine-learning tools to identify complex predictive data patterns in a spatial or temporal domain. Here, we consider the application of DL and XAI to large omic datasets, in order to study biological aging at the molecular level. We develop an advanced multi-view graph-level representation learning (MGRL) framework that integrates prior biological network information, to build molecular aging clocks at cell-type resolution, which we subsequently interpret using XAI. We apply this framework to one of the largest single-cell transcriptomic datasets encompassing over a million immune cells from 981 donors, revealing a ribosomal gene subnetwork, whose expression correlates with age independently of cell-type. Application of the same DL-XAI framework to DNA methylation data of sorted monocytes reveals an epigenetically deregulated inflammatory response pathway whose activity increases with age. We show that the ribosomal module and inflammatory pathways would not have been discovered had we used more standard machine-learning methods. In summary, the computational deep learning framework presented here illustrates how deep learning when combined with explainable AI tools, can reveal novel biological insights into the complex process of aging.https://doi.org/10.1038/s41598-025-89646-1Deep-learningAIGraph-level representation learningAgingSingle-cellEpigenetics
spellingShingle Zhi-Peng Li
Zhaozhen Du
De-Shuang Huang
Andrew E. Teschendorff
Interpretable deep learning of single-cell and epigenetic data reveals novel molecular insights in aging
Scientific Reports
Deep-learning
AI
Graph-level representation learning
Aging
Single-cell
Epigenetics
title Interpretable deep learning of single-cell and epigenetic data reveals novel molecular insights in aging
title_full Interpretable deep learning of single-cell and epigenetic data reveals novel molecular insights in aging
title_fullStr Interpretable deep learning of single-cell and epigenetic data reveals novel molecular insights in aging
title_full_unstemmed Interpretable deep learning of single-cell and epigenetic data reveals novel molecular insights in aging
title_short Interpretable deep learning of single-cell and epigenetic data reveals novel molecular insights in aging
title_sort interpretable deep learning of single cell and epigenetic data reveals novel molecular insights in aging
topic Deep-learning
AI
Graph-level representation learning
Aging
Single-cell
Epigenetics
url https://doi.org/10.1038/s41598-025-89646-1
work_keys_str_mv AT zhipengli interpretabledeeplearningofsinglecellandepigeneticdatarevealsnovelmolecularinsightsinaging
AT zhaozhendu interpretabledeeplearningofsinglecellandepigeneticdatarevealsnovelmolecularinsightsinaging
AT deshuanghuang interpretabledeeplearningofsinglecellandepigeneticdatarevealsnovelmolecularinsightsinaging
AT andreweteschendorff interpretabledeeplearningofsinglecellandepigeneticdatarevealsnovelmolecularinsightsinaging