Exploratory Analysis

This ATAC-seq dataset contains accessibility profiles for 142 samples.

Signal has been summarized for the following region sets:

Fragment data IS available.

Read counts are summarized for various region types and the corresponding aggregate count matrices are used for dimension reduction. Counts have been log-normalized (log10(count+1)).

Method	pca umap
Region type	.peaks.cons t10k promoters_gc_protein_coding ERB_BP_distal ERB_BP_dnase ERB_BP_proximal ERB_BP_tfbs ERB_BP_tss
Annotation	.ALL cellType stimulus

Figure 1

Dimension reduction

Samples have been clustered according to the 1000 most variable regions for each region type. Counts have been log-normalized (log2(count+1)).

Region type

.peaks.cons t10k promoters_gc_protein_coding ERB_BP_distal ERB_BP_dnase ERB_BP_proximal ERB_BP_tfbs ERB_BP_tss

Figure 2

Clustered heatmap. The 1000 most variable regions are shown. Counts have been log-normalized (log2(count+1)).

chromVAR [1] analysis. The following motif set(s) were used for the analysis: jaspar_vert. R data files of chromVAR deviation scores have been attached to this report:

• .peaks.cons: RDS file

Region type

.peaks.cons

Figure 3

chromVAR variability. TF motifs are shown ordered according to their variability across the dataset.

Region type

.peaks.cons

Figure 4

chromVAR deviation scores. The heatmap shows the scores for 100 most variable TF motifs across the dataset.

1. Schep, Wu, Buenrostro, & Greenleaf (2017). chromVAR: inferring transcription-factor-associated accessibility from single-cell epigenomic data. Nature Methods, 14(10), 975-978