Abstract
ATAC-seq has been widely adopted to identify accessible chromatin regions across the genome. However, current data analysis still utilizes approaches initially designed for ChIP-seq or DNase-seq, without considering the transposase digested DNA fragments that contain additional nucleosome positioning information. We present the first dedicated ATAC-seq analysis tool, a semi-supervised machine learning approach named HMMRATAC. HMMRATAC splits a single ATAC-seq dataset into nucleosome-free and nucleosome-enriched signals, learns the unique chromatin structure around accessible regions, and then predicts accessible regions across the entire genome. We show that HMMRATAC outperforms the popular peak-calling algorithms on published human ATAC-seq datasets. We find that single-end sequenced or size-selected ATAC-seq datasets result in a loss of sensitivity compared to paired-end datasets without size-selection.