Pan-cell type continuous chromatin state annotation of 1,698 epigenomes from the International Human Epigenome Consortium

BACKGROUND: Building on primary data generated by its member consortia, the International Human Epigenome Consortium has uniformly processed a collection of more than 2,000 reference epigenomes profiling histone modifications, DNA methylation, and RNA expression. Existing segmentation and annotation approaches typically produce cell type-specific regulatory maps, which have become increasingly difficult to maintain and apply as the number of profiled cell types has grown. Here, we apply epigenome-ssm, a continuous state-space modeling framework, to generate a unified, interpretable representation of chromatin states across thousands of human epigenomes. RESULTS: Using 9,539 histone modification signal tracks from the 1,698 reference epigenomes with at least one ChIP-seq experiment, epigenome-ssm produces 33 continuous chromatin state features that compactly capture regulatory programs across cell types. These features distinguish canonical activities such as promoters, enhancers, transcription, and heterochromatin, while also encoding cell type-specific regulatory patterns. Compared with alternative pan-cell type annotation methods, the continuous features achieve superior or comparable predictive performance for gene expression, enhancer activity, and evolutionary conservation, despite using fewer dimensions. The model effectively captures both broad and lineage-specific regulatory programs, linking chromatin states to gene expression and functional annotations. Additionally, a derived conservation-associated activity score (SSM-CAAS) highlights genomic regions enriched for disease-associated variants, demonstrating utility for interpreting noncoding variation. CONCLUSIONS: Continuous pan-cell type chromatin state features provide a compact, expressive, and biologically informative representation of the human epigenome. This framework improves integration and interpretation of large-scale epigenomic data, enables accurate prediction of genomic function, and facilitates identification of regulatory elements relevant to disease. The resulting resource offers a scalable foundation for downstream analyses of gene regulation and genetic variation.