Violeta Raverdy

The paper develops a deep learning model combining clinical data, gene expression, and DNA methylation to distinguish NASH from steatosis and identifies new genes involved in liver disease severity.

This study identifies a circadian clock-controlled signaling pathway that drives hepatic stellate cell activation in liver fibrosis, offering potential drug targets and a basis for chronotherapeutic strategies.

The paper identifies shared genetic regulation across mRNA, proteins, and metabolites in blood, revealing networks and mediators of GWAS variants.

The paper examines time-of-day-dependent transcriptome and metabolome variations in human NAFL and NASH livers, finding disruptions in rhythmic gene expression and metabolites.

The paper identifies age-related DNA methylation changes in human skeletal muscle through a meta-analysis and integrates these with transcriptomic and proteomic data, revealing enriched age-related gene expression patterns.

This study develops machine learning models to predict liver fat content using multi-omic and clinical data from NAFLD patients, achieving higher accuracy than existing tools.