High-resolution reconstruction of cell-type-specific transcriptional regulatory processes from bulk sequencing samples.
TL;DR
Deep-learning-based deconvolution of tissue profiles with accurate interpretation of locus-specific signals (DeepDETAILS), a quasisupervised framework performing cross-modality deconvolution using scATAC-seq reference libraries for other bulk datasets, and a potential etiology of the disease are introduced.
Abstract
Single-cell sequencing methods such as scRNA-seq and scATAC-seq have advanced our understanding of individual cellular functions but experimentally adapting genome-wide assays measuring other genomic features to achieve single-cell resolution remains a technical challenge. Here we introduce deep-learning-based deconvolution of tissue profiles with accurate interpretation of locus-specific signals (DeepDETAILS), a quasisupervised framework performing cross-modality deconvolution using scATAC-seq reference libraries for other bulk datasets. DeepDETAILS enables base-pair-resolution mapping of genomic signals across diverse cell types, with great versatility for various omics datasets, including nascent transcript sequencing (such as PRO-cap and PRO-seq) and ChIP-seq for chromatin modifications. Using DeepDETAILS, we generated a compendium of high-resolution nascent transcription and histone modification signals across 39 diverse human tissues and 86 distinct cell types. Furthermore, we applied our compendium to fine-map risk variants associated with primary sclerosing cholangitis, a progressive cholestatic liver disorder, and revealed a potential etiology of the disease.