2025/01/02 by Wouter Saelens, Olga Pushkarev, Bart Deplancke · 1 voice · 4 citations
Biochemistry, Genetics and Molecular Biology · #Biology #Cancer Genomics and Diagnostics #Computational biology #Computer science #DNA #Expression (computer science) #Gene #Gene expression #Genetics #Genomics and Chromatin Dynamics #Physics #Scale (ratio) #Single-cell and spatial transcriptomics
paper · pdf · doi:10.1038/s41467-024-55447-9
published in Nature Communications 16(1), 317 (Nature Portfolio)
openalex publication_date 2025/01/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/06
Gene regulation is inherently multiscale, but scale-adaptive machine learning methods that fully exploit this property in single-nucleus accessibility data are still lacking. Here, we develop ChromatinHD, a pair of scale-adaptive models that uses the raw accessibility data, without peak-calling or windows, to link regions to gene expression and determine differentially accessible chromatin. We show how ChromatinHD consistently outperforms existing peak and window-based approaches and find that this is due to a large number of uniquely captured, functional accessibility changes within and outside of putative cis-regulatory regions. Furthermore, ChromatinHD can delineate collaborating regulatory regions, including their preferential genomic conformations, that drive gene expression. Finally, our models also use changes in ATAC-seq fragment lengths to identify dense binding of transcription factors, a feature not captured by footprinting methods. Altogether, ChromatinHD, available at https://chromatinhd.org , is a suite of computational tools that enables a data-driven understanding of chromatin accessibility at various scales and how it relates to gene expression. Functional chromatin changes occur at different scales. Here, the authors introduce ChromatinHD, a method that characterises differential and predictive chromatin accessibility changes in a scale-adaptive way, without relying on peak calling or windows.