SeATAC: a tool for exploring the chromatin landscape and the role of pioneer factors
Dsouza, N.; Gong, W.; Garry, D.
Show abstract
The position of the nucleosome and chromatin packaging in eukaryotic genomes govern gene regulation and cellular functions. Assay for Transposase-Accessible Chromatin using sequencing (ATAC-seq) is an efficient and precise method for revealing chromatin accessibility across the genome. However, there is no method that is specifically designed for detecting differential chromatin accessibility using ATAC-seq datasets. In this study, we developed a bioinformatics tool called SeATAC, that used a conditional variational autoencoder (CVAE) model to learn the latent representation of ATAC-seq V-plots, and to estimate the statistically differential chromatin accessibility. We demonstrated that SeATAC outperformed MACS2 and NucleoATAC on four separate tasks including: (1) detection of differential V-plots; (2) definition of nucleosome positions; (3) detection of nucleosome changes and (4) designation of transcriptional factor binding sites (TFBS) with differential chromatin accessibility. By applying SeATAC to several pioneer factor induced differentiation or reprogramming ATAC-seq datasets, we found that induction of these pioneer factors not only relaxed the closed chromatin but also decreased the chromatin accessibility of 20% - 30% of their target sites. These two groups of TF binding sites were characterized by different genomic distribution and histone marks. Here, we present SeATAC as a novel tool to accurately reveal the genomic regions with differential chromatin accessibility from ATAC-seq data.
Matching journals
The top 3 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- Functional classification of noncoding RNAs associated with distinct histone modifications by PIRCh-seq 96%
- Chromatin Interaction Neural Network (ChINN): A machine learning-based method for predicting chromatin interactions from DNA sequences 96%
- Harmonizing single cell 3D genome data with STARK and scNucleome 96%
Similar papers in this journal
- Predicting gene expression from histone marks using chromatin deep learning models depends on histone mark function, regulatory distance and cellular states 96%
- Assessing base-resolution DNA mechanics on the genome scale 96%
- Extensive long-range polycomb interactions and weak compartmentalization are hallmarks of human neuronal 3D genome 96%
Similar papers in this journal
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.