Genome-wide methylome modeling via generative AI incorporating long- and short-range interactions.

ABSTRACT: Using millions of methylation segments, we developed DiffuCpG, a generative artificial intelligence (AI) diffusion model designed to solve the critical challenge of missing data in high-throughput methylation technologies. DiffuCpG goes beyond conventional methods by leveraging both short-range interactions including nearby CpGs from both latitude and longitude of the dataset, local DNA sequences, and long-range interactions, including three-dimensional genome architecture and long-distance correlations, to comprehensively model the methylome. Compared to previous methods, through extensive independent validations across different tissue types, cancers, and technologies (whole-genome bisulfite sequencing, enhanced reduced representation bisulfite sequencing, single-cell bisulfite sequencin

SUBMITTER: Yan F 

PROVIDER: S-EPMC11988400 | biostudies-literature | 2025 Apr

REPOSITORIES: biostudies-literature