Earl, A. S. | Search bioRxiv

bioRxiv2023

Single-cell multi-scale footprinting reveals the modular organization of DNA regulatory elements

Cis-regulatory elements control gene expression and are dynamic in their structure, reflecting changes to the composition of diverse effector proteins over time1-3. Here we sought to connect the structural changes at cis-regulatory elements to alterations in cellular fate and function. To do this we developed PRINT, a computational method that uses deep learning to correct sequence bias in chromatin accessibility data and identifies multi-scale footprints of DNA-protein interactions. We find that multi-scale footprints enable more accurate inference of TF and nucleosome binding. Using PRINT with single-cell multi-omics, we discover wide-spread changes to the structure and function of candidate cis-regulatory elements (cCREs) across hematopoiesis, wherein nucleosomes slide, expose DNA for TF binding, and promote gene expression. Activity segmentation using the co-variance across cell states identifies "sub-cCREs" as modular cCRE subunits of regulatory DNA. We apply this single-cell and PRINT approach to characterize the age-associated alterations to cCREs within hematopoietic stem cells (HSCs). Remarkably, we find a spectrum of aging alterations among HSCs corresponding to a global gain of sub-cCRE activity while preserving cCRE accessibility. Collectively, we reveal the functional importance of cCRE structure across cell states, highlighting changes to gene regulation at single-cell and single-base-pair resolution.

genomics↗

bioRxiv2022

Photoselective sequencing: microscopically-guided genomic measurements with subcellular resolution

In biological systems, spatial organization is interconnected with genome function and regulation. However, methods that couple high-throughput genomic and epigenomic profiling with spatial information are lacking. Here, we developed Photoselective Sequencing, a spatially-informed DNA sequencing method to assay collections of cells or subcellular regions that share a unifying morphological trait. In Photoselective Sequencing, we prepare a blocked fragment library within a fixed biological specimen. Guided by fluorescence imaging, we remove the block in specific regions of interest using targeted illumination with near-UV light, ultimately allowing high-throughput sequencing of the selected fragments. To validate Photoselective Sequencing, we profile chromatin openness in fluorescently-labeled cell types within the mouse brain and demonstrate strong agreement with published single-cell ATAC-seq data. Using Photoselective Sequencing, we characterize the accessibility profiles of oligodendrocyte-lineage cells within the cortex and corpus-callosum regions of the brain. We develop a new computational strategy for decomposing bulk accessibility profiles by individual cell types, and report a relative enrichment of oligodendrocyte-progenitor-like cells in the cortex. Finally, we leverage Photoselective Sequencing for unbiased profiling of DNA at the nuclear periphery, a key chromatin organizing region. We compare and contrast the Photoselective Sequencing profile with lamin ChIP-seq data, and identify features beyond lamin interaction that are correlated with positioning at the nuclear periphery. These results collectively demonstrate that Photoselective Sequencing is a flexible and generalizable platform for exploring the interplay of spatial structures with genomic and epigenomic properties.

genomics↗