MethylGPT: a foundation model for the DNA methylome.

DNA methylation serves as a powerful biomarker for disease diagnosis and biological age assessment. However, current analytical approaches often rely on linear models that cannot capture the complex, context-dependent nature of methylation regulation. Here we present MethylGPT, a transformer-based foundation model trained on 226,555 (154,063 after QC and deduplication) human methylation profiles spanning diverse tissue types from 5,281 datasets, curated 49,156 CpG sites, and 7.

Plasma protein-based organ-specific aging and mortality models unveil diseases as accelerated aging of organismal systems.

Aging is a complex process manifesting at molecular, cellular, organ, and organismal levels. It leads to functional decline, disease, and ultimately death, but the relationship between these fundamental biomedical features remains elusive. By applying elastic net regularization to plasma proteome data of over 50,000 human subjects in the UK Biobank and other cohorts, we report interpretable organ-specific and conventional aging models trained on chronological age, mortality, and longitudinal proteome data.

Leveraging metabolic modeling and machine learning to uncover modulators of quiescence depth.

Quiescence, a temporary withdrawal from the cell cycle, plays a key role in tissue homeostasis and regeneration. Quiescence is increasingly viewed as a continuum between shallow and deep quiescence, reflecting different potentials to proliferate. The depth of quiescence is altered in a range of diseases and during aging.

Maresin 1 repletion improves muscle regeneration after volumetric muscle loss.

The acute traumatic or surgical loss of skeletal muscle, known as volumetric muscle loss (VML), is a devastating type of injury that results in exacerbated and persistent inflammation followed by fibrosis. The mechanisms that mediate the magnitude and duration of the inflammatory response and ensuing fibrosis after VML remain understudied, and as such, the development of regenerative therapies has been limited. To address this need, we profiled how lipid mediators, which are potent regulators of the immune response after injury, varied with VML injuries that heal or result in fibrosis.

Next-Generation Genome-Scale Metabolic Modeling through Integration of Regulatory Mechanisms.

Genome-scale metabolic models (GEMs) are powerful tools for understanding metabolism from a systems-level perspective. However, GEMs in their most basic form fail to account for cellular regulation. A diverse set of mechanisms regulate cellular metabolism, enabling organisms to respond to a wide range of conditions.