Data integration in systems genetics and aging research

TL;DR

This paper discusses how integrating multi-omics and phenotype data using FAIR principles and explainable AI can help understand and combat age-related diseases, aiming to extend healthspan.

Contribution

It introduces a framework combining data management and explainable AI to analyze complex physiological mechanisms in aging research.

Findings

Effective data integration improves understanding of age-related diseases.

Explainable AI helps identify key factors influencing aging.

Framework supports personalized approaches to extend healthspan.

Abstract

Human life expectancy has dramatically improved over the course of the last century. Although this reflects a global improvement in sanitation and medical care, this also implies that more people suffer from diseases that typically manifest later in life, like Alzheimer and atherosclerosis. Increasing healthspan by delaying or reverting the development of these age-related diseases has therefore become an urgent challenge in biomedical research. Research in this field is complicated by the multi-factorial nature of age-related diseases. They are rooted in complex physiological mechanisms impacted by heritable, environment and life-style factors that can be unique to each individual. Although technological advances in high-throughput biomolecular assays have enabled researchers to investigate individual physiology at the molecular level, integrating information about its different components, and accounting for individual variations remains a challenge. We are using a large collection of omics and phenotype data derived from the BXD mouse genetic diversity panel to explore how good data management practices, as fostered by the FAIR principles, paired with an explainable artificial intelligence framework, can provide solutions to decipher the complex roots of age-related diseases. These developments will help to propose innovative approaches to extend healthspan in the aging global population.