Multi-omic-deep-learning-identifies-exercise-responsive-ageing-pathways-in-humans

Abstract Genome-wide association studies of physical activity traits have mapped numerous loci, yet the molecular mechanisms through which exercise influences human biology remain poorly defined. Mechanistic progress has been limited by heritability-dominated signals, siloed single-omic analyses, and the lack of integrative models that connect genetic associations to causal, system-level pathways. We introduce the first deep learning, multi-omic framework for exercise genomics, unifying causal inference, molecular topology, protein structure, and functional context within a supervised Graph Neural Network (GNN) with experimental validation. Using linkage disequilibrium-aware Mendelian randomisation with accelerometer-derived vigorous physical activity as the exposure, we integrated four omic layers—plasma proteomics, blood CpG methylation, blood single-cell transcriptomics, and plasma glycomics. The GNN prioritised a coherent, multi-omic network of exercise-responsive genes spanning glycosylation (glycosyltransferases, glycoproteins), immune signalling (IgG modules, cytokine clusters), proteostasis and autophagy (hydrolases), redox regulation (oxidoreductases), and stress-response regulators (transcription factors, kinases, RNA-binding proteins). Pathway annotation and alignment with ageing biology using differentially methylated regions and principal-component features from five biological ageing clocks (Horvath, Hannum, DunedinPACE, PhenoAge, Proteomic Clock) mapped to: 1) autophagy (Fas signalling); 2) stress and DNA damage response pathways (apoptosis, p53, PI3K, oxidative stress, DNA replication, purine/pyrimidine metabolism, VEGF, synaptic vesicle trafficking, notch signalling, Rho GTPase, Epidermal Growth Factor Receptor; 3) immune and inflammatory pathways (cytokine and interleukin signalling, T and B cell activation, Toll-like receptor signalling); 4) physiological adaptation (Wnt, IGF, GnRH, Fibroblast Growth Factor, ubiquitin proteasome, Platelet-Derived Growth Factor, Thyrotropin-Releasing Hormone, glutamate receptor, plasminogen, endothelin, cholecystokinin, Corticotropin-Releasing Hormone signalling); 5) neuroendocrine and neurotransmitter pathways (acetylcholine, adrenaline, serotonin, dopamine, oxytocin, opioid, β-adrenergic signalling); and 6) neurodegeration pathways (Alzheimer’s, Parkinson’s, Huntington’s disease). Finally, we partially validated GNN predictions in humans, demonstrating acute exercise-induced shifts in plasma glycomic markers consistent with GNN-predicted glycomic remodelling. This work establishes the first deep learning, multi-omic map of exercise-responsive pathways in humans and identifies actionable regulators that couple habitual physical activity to immunometabolic resilience and healthy ageing trajectories. Keywords: deep learning, graph neural network, mendelian randomisation, multi-omics, physical activity, accelerometry, ageing, ageing clocks