CTCF and R-loops are boundaries of cohesin-mediated DNA looping

Abstract

Cohesin and CCCTC-binding factor (CTCF) are key regulatory proteins of three-dimensional (3D) genome organization. Cohesin extrudes DNA loops that are anchored by CTCF in a polar orientation. Here, we present direct evidence that CTCF binding polarity controls cohesin-mediated DNA looping. Using single-molecule imaging of CTCF-cohesin collisions, we demonstrate that a critical N-terminal motif of CTCF blocks cohesin translocation and DNA looping. The cryo-electron microscopy structure of the intact cohesin-CTCF complex reveals that a CTCF linker ahead of zinc-fingers can only reach its binding motif on the STAG1 cohesin subunit when the N-terminus of CTCF faces cohesin. Remarkably, a C-terminally oriented CTCF accelerates DNA compaction by cohesin. DNA-bound Cas9 and Cas12a ribonucleoproteins are also polar cohesin barriers, indicating that stalling is intrinsic to cohesin itself, and other proteins can substitute for CTCF in fruit flies and other eukaryotes. Finally, we show that RNA-DNA hybrids (R-loops) block cohesin-mediated DNA compaction in vitro and are enriched with cohesin subunits in vivo, likely forming TAD boundaries. Our results provide direct evidence that CTCF orientation and R-loops shape the 3D genome by directly regulating cohesin.

CTCF is a DNA-tension-dependent barrier to cohesin-mediated loop extrusion

“…Once bound to their binding sites, the mean residence time of CTCF molecules was around 29 min (Extended Data Fig. 1f,g), which is longer than most [37][38][39][40][41][42] but not all 40 in vivo estimates, and longer than an in vitro measurement described in a recent preprint 43 . It is possible that additional factors, such as the action of other chromatin-bound proteins, might promote CTCF unbinding in cells.…”

Cohesin and CTCF control the dynamics of chromosome folding

“…Chromosome conformation capture (3C) methods, which measure physical proximity between genomic sequences in fixed cells, revealed that chromosomal contacts are organized into submegabase domains of preferential interactions known as topologically associating domains (TADs) 4,5 whose boundaries can functionally insulate regulatory sequences 3 . TADs mainly arise from nested interactions between convergently oriented binding sites of the DNA-binding protein CTCF, which are established as chromatin-bound CTCF arrests the loop extrusion activity of the cohesin complex [6][7][8][9][10] .…”

“…Determining the timing and duration of chromosomal interactions within TADs and their relationship with CTCF and cohesin is key to understanding how enhancers communicate with promoters 11,12 . Single-cell analyses of chromosome structure in fixed cells 4,[13][14][15] , chromosome tracing experiments [16][17][18][19] , in vitro 9,10,20 and live-cell 21 measurements of CTCF and cohesin dynamics, and polymer simulations 6,15,22 , as well as live-cell imaging of chromosomal locations and nascent RNA 23,24 , all suggested that TADs and CTCF loops are dynamic structures whose temporal evolution might be governed by the kinetics of loop extrusion 25 . Recent live-cell measurements of a CTCF loop connecting two opposite TAD boundaries in mouse embryonic stem cells (mESCs) provided direct evidence that this is the case, and revealed that cohesin-mediated loops between CTCF sites located 500 kilobases (kb) away last 10-30 min (ref.…”

Extruding transcription elongation loops observed in high-resolution single-cell 3D genomes

“…S16, B and C), thus CTCF is not the universal TSS barrier. Besides CTCF, other chromatin-bound proteins (e.g., dCas9 (42), minichromosome maintenance (MCM) complex (47), transcription factors (48)) and specific non-canonical DNA structures (e.g., R-loops (49), replication folks (50))…”

“…S16, B and C), thus CTCF is not the universal TSS barrier. Besides CTCF, other chromatin-bound proteins (e.g., dCas9 ( 42 ), minichromosome maintenance (MCM) complex ( 47 ), transcription factors ( 48 )) and specific non-canonical DNA structures (e.g., R-loops ( 49 ), replication folks ( 50 )) have been implied as potential cohesin barriers, demonstrating that the barrier doesn’t have to be a DNA-binding protein. In this study, we showed that inactivation of RNAPII (fig.…”