AtacWorks Quick Start Guide

Using AtacWorks toolkit, one can either train a custom AtacWorks model with their own data or use one of already pre-trained AtacWorks models and run denoising on the data directly.

Training an AtacWorks Model

To train an AtacWorks model, you need a pair of ATAC-Seq datasets from the same cell type, where one dataset has lower coverage or lower quality than the other. You can also use multiple such pairs of datasets. For each such pair of datasets, AtacWorks requires three input files:

1. A coverage track representing the number of sequencing reads mapped to each position on the genome in the low-coverage or low-quality dataset. This may be smoothed or processed. Format: bigWig

2. A coverage track representing the number of sequencing reads mapped to each position on the genome in the high-coverage or high-quality dataset. This may be smoothed or processed in the same way as the previous track. Format: bigWig

3. The genomic positions of peaks called on the high-coverage or high-quality dataset. These can be obtained by using MACS2 or any other peak caller. Format: either BED or the narrowPeak format produced by MACS2.

The model learns a mapping from (1) to both (2) and (3); in other words, from the noisy coverage track, it learns to predict both the clean coverage track, and the positions of peaks in the clean dataset.

The step by step guide for how to load and pre-process the data, run training commands and the expected outputs is described in a tutorial notebook. More information about training an atacworks model can be found here.

Denoising and Peak Calling using Pre-trained AtacWorks Model

To denoise and call peaks from low-coverage, low cell count, or low quality ATAC-seq data, you need three input files:

1. A trained AtacWorks model file with extension .pth.tar.

2. A coverage track representing the number of sequencing reads mapped to each position on the genome in the low-coverage or low-quality dataset. This track should be processed in the same way as the files used for training the model. Format: bigWig

3. Chromosome sizes file - a tab-separated text file containing the names and sizes of chromosomes in the genome.

The step-by-step guide for how to pass the appropriate inputs, what outputs to expect from AtacWorks and how to interpret the results are discussed in a tutorial notebook. More information about denoising using pre-trained atacworks model can be found here.