Phenome-Wide Multi-Omics Integration Uncovers Distinct Archetypes of Human Aging

2025-10-14

AI Summary

Human aging is highly heterogeneous, and single-omics–based biological age (BA) models inadequately capture its molecular complexity. Method: We developed a nonlinear, machine learning–driven multi-omics aging clock by integrating transcriptomic, lipidomic, metabolomic, and microbiomic data with clinical and behavioral phenotypes. Using unsupervised clustering on a large-scale longitudinal cohort (n = 12,000), we identified distinct, pathway-specific biological aging subtypes. Contribution/Results: This is the first study to systematically characterize molecularly defined aging trajectories and their underlying mechanisms. The multi-omics clock significantly improves prediction accuracy for health decline, multiple age-related diseases, and all-cause mortality compared to single-omics models. It overcomes key limitations of unimodal approaches and provides a subtype-aware framework—both theoretical and computational—for precision geroscience and targeted anti-aging interventions.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• User Modeling, Personalization and Recommendation: Studies of user behavior, including longitudinal effects of personalized systems
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Aging is a highly complex and heterogeneous process that progresses at different rates across individuals, making biological age (BA) a more accurate indicator of physiological decline than chronological age. While previous studies have built aging clocks using single-omics data, they often fail to capture the full molecular complexity of human aging. In this work, we leveraged the Human Phenotype Project, a large-scale cohort of 12,000 adults aged 30--70 years, with extensive longitudinal profiling that includes clinical, behavioral, environmental, and multi-omics datasets -- spanning transcriptomics, lipidomics, metabolomics, and the microbiome. By employing advanced machine learning frameworks capable of modeling nonlinear biological dynamics, we developed and rigorously validated a multi-omics aging clock that robustly predicts diverse health outcomes and future disease risk. Unsupervised clustering of the integrated molecular profiles from multi-omics uncovered distinct biological subtypes of aging, revealing striking heterogeneity in aging trajectories and pinpointing pathway-specific alterations associated with different aging patterns. These findings demonstrate the power of multi-omics integration to decode the molecular landscape of aging and lay the groundwork for personalized healthspan monitoring and precision strategies to prevent age-related diseases.

Problem

• Developing multi-omics aging clock predicting health outcomes
• Uncovering distinct biological subtypes of human aging
• Capturing molecular complexity to personalize aging interventions

Innovation

• Multi-omics integration captures aging complexity
• Machine learning predicts health outcomes and risks
• Unsupervised clustering reveals distinct aging subtypes