Single-molecule chromatin configurations link transcription factor binding to expression in human cells [ATAC-seq]

The binding of multiple transcription factors (TFs) to genomic enhancers activates gene expression in mammalian cells. However, the molecular details that link enhancer sequence to TF binding, promoter state, and gene expression levels remain opaque. We applied single-molecule footprinting (SMF) to measure the simultaneous occupancy of TFs, nucleosomes, and components of the transcription machinery on engineered enhancer/promoter constructs with variable numbers of TF binding sites for both a synthetic and an endogenous TF. We find that activation domains enhance a TF’s capacity to compete with nucleosomes for binding to DNA in a BAF-dependent manner, TF binding on nucleosome-free DNA is consistent with independent binding between TFs, and average TF occupancy linearly contributes to promoter activation rates. We also decompose TF strength into separable binding and activation terms, which can be tuned and perturbed independently. Finally, we develop thermodynamic and kinetic models that quantitatively predict both the binding microstates observed at the enhancer and subsequent time-dependent gene expression. This work provides a template for quantitative dissection of distinct contributors to gene activation, including the activity of chromatin remodelers, TF activation domains, chromatin acetylation, TF concentration, TF binding affinity, and TF binding site configuration. Bulk omni-ATAC was performed as in69 with 50,000 cells and two biological replicates per sample. Libraries were sequenced 2x36 with an NextSeq 500/550 High Output v2.5 75 cycles kit (Illumina, 20024906) on a NextSeq 550. Bulk ATAC-seq data processing of fastq files was performed with snakeATAC (https://github.com/GreenleafLab/snakeATAC_singularity) and alignment to hg38. To compare SMF and ATAC data, ATAC peaks were first standardized to 200 bp wide and grouped by signal into 100 quantile bins. Average ATAC coverage was computed per bin. Methylation signal from SMF was computed by averaging over all GpCs in all reads overlapping the ATAC peaks and averaged by quantile. Visualization of ATAC peaks at ISGs was performed by loading BigWig files with 100 bp windows into the Integrative Genomics Viewer70. BAM files were then further processed with ChrAccR (https://github.com/GreenleafLab/ChrAccR) to perform chromVar71 (IFN_ATAC_chraccr.rmd) and ATAC footprinting analyses. ATAC footprinting of ISREs was performed on genome-wide matches to Vierstra Non-redundant TF motif clustering (V2.1 BETA-HUMAN)1 cluster AC0188 IRF/STAT|IRF using ChrAccR function getMotifFootprints and RPM and Tn5 bias normalization (IFN_ATAC_footprinting.R). Computing average ATAC signal around IFN promoters, a list of hg38 TSS was extended by 250 bp in either direction, and average ATAC-seq coverage was computed over these peaks using bedtools coverage (vX). Signal was RPM normalized and averaged across all ISGs, which were defined as genes with >2-fold increase in expression 24 hours after IFN-β stimulation (as measured by bulk RNA-seq, see below) and which contained ≥3 ISRE motifs in the promoter. A null set of genes was selected by choosing the expressed gene with the closest TPM to each ISG pre-stimulation.