High-throughput single-cell chromatin accessibility CRISPR screens enable unbiased identification of regulatory networks in cancer

Abstract

Chromatin accessibility profiling can identify putative regulatory regions genome wide; however, pooled single-cell methods for assessing the effects of regulatory perturbations on accessibility are limited. Here, we report a modified droplet-based single-cell ATAC-seq protocol for perturbing and evaluating dynamic single-cell epigenetic states. This method (Spear-ATAC) enables simultaneous read-out of chromatin accessibility profiles and integrated sgRNA spacer sequences from thousands of individual cells at once. Spear-ATAC profiling of 104,592 cells representing 414 sgRNA knock-down populations reveals the temporal dynamics of epigenetic responses to regulatory perturbations in cancer cells and the associations between transcription factor binding profiles.

Fig. 1. Spear-ATAC enables high-throughput CRISPR screening with a chromatin accessibility read-out.

a Schematic of the Spear-ATAC method. Modifications to traditional CRISPR screening methods and scATAC-seq approaches are outlined on the right. b Heatmap of the percent of sgRNA reads assigned to 3045 individual cells with corresponding chromatin accessibility information via scATAC-seq. c UMAP of Spear-ATAC chromatin accessibility profiles for the pilot K562 screen colored by sgRNA assignments. d Rank ordered plot of sgRNA:TF perturbations to identify top hits in the pilot K562 screen. e UMAP of Spear-ATAC chromatin accessibility profiles for the pilot K562 screen colored by chromVAR deviations for GATA1 ENCODE ChIP-seq. f (Top) Bias-Normalized footprint of the local accessibility for each scATAC-seq cluster for genomic regions containing GATA motifs. (Bottom) Modeled hexamer insertion bias of Tn5 around sites containing each motif. g Pseudo-bulk ATAC-seq track at the GATA1 locus for sgGATA1 and sgNT cells. Light grey box indicates the region targeted by sgGATA1-1, sgGATA1-2, and sgGATA1-2 CRISPRi sgRNAs. h Differential accessibility between sgGATA1 and sgNT cells. The x axis represents the log2 mean accessibility per peak and the y axis represents the log2 fold change in sgGATA1 cells compared to sgNT cells. Colored points are significant (|log₂ fold change | >0.5, FDR < 0.05).

Fig. 2. Assessing trans regulatory perturbations over time using Spear-ATAC.

a Schematic of Spear-ATAC time-course experiment with a 21-sgRNA pool analyzed at 4 time-points (3, 6, 9, and 21 days post-transduction). b Change in sgGATA1 representation over time, represented by the number of cells analyzed per time-point (red) and the % of cells in the total pool (black). c Rank ordered plot of sgRNA:TF perturbations to identify top hits in the K562 time-course screen at the indicated time points. d (Left) Heatmap of chromatin peak accessibility for each scATAC-seq sub-population using the top differential scATAC-seq peaks. Each row represents a z score of log₂ normalized accessibility within each group using scATAC-seq. Day 21 was excluded due to low representation of sgGATA1 cells at this time point. (Right) Transcription factor hypergeometric motif enrichment with FDR indicated in parentheses. e Pseudo-bulk ATAC-seq track at the IRF1 locus for sgGATA1 (day 3, day 6, day 9, and day 21) and sgNT cells (day3). Light grey box indicates peak regions that increased in accessibility in the sgGATA1 vs sgNT cells. Day 21 was excluded due to low representation of sgGATA1 cells at this time point.

Fig. 3. High throughput chromatin accessibility screening of CRISPR perturbations using Spear-ATAC.

a Schematic of Spear-ATAC large screens with a 132-sgRNA pool analyzed for three different cell lines (K562, MCF7, and GM12878). b Rank ordered plot of sgRNA:TF perturbations to identify top hits in the K562 large screen. c Motif enrichment in differentially accessible peaks across 6 perturbed transcription factors in the K562 large screen. Color indicates whether the motif enrichment corresponds to up-regulated (red) or down-regulated (blue) peaks. d Schematic of inferring regulatory relations with Spear-ATAC. Briefly, the correlation for each TF–TF motif is determined in both the targeting (sgT) and non-targeting (sgNT) cells. Next the correlation in the non-targeting cells is subtracted from targeting cells. These TF–TF motif pairs are then assessed for different regulatory relationships. e (Left) Heatmap of the differences between sgGATA1 targeting and non-targeting cells for all TF–TF motif accessibility correlations grouped into five different modules in the K562 large screen. (Right) Zoomed-in heatmap of modules 1 and 2 highlighting transcription factors with largely perturbed TF–TF motif accessibility relationships.