Helmholtz Gemeinschaft

Search
Browse
Statistics
Feeds

Simultaneous dimensionality reduction and integration for single-cell ATAC-seq data using deep learning

[img]
Preview
PDF (Preprint) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
5MB
[img]
Preview
PDF (Supplementary Material) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
11MB
Item Type:Preprint
Title:Simultaneous dimensionality reduction and integration for single-cell ATAC-seq data using deep learning
Creators Name:Kopp, W. and Akalin, A. and Ohler, U.
Abstract:Advances in single-cell technologies enable the routine interrogation of chromatin accessibility for tens of thousands of single cells, shedding light on gene regulatory processes at an unprecedented resolution. Meanwhile, size, sparsity and high dimensionality of the resulting data continue to pose challenges for its computational analysis, and specifically the integration of data from different sources. We have developed a dedicated computational approach, a variational auto-encoder using a noise model specifically designed for single-cell ATAC-seq data, which facilitates simultaneous dimensionality reduction and batch correction via an adversarial learning strategy. We showcase both its individual advantages on carefully chosen real and simulated data sets, as well as the benefits for detailed cell type characterization via integrating multiple complex datasets.
Keywords:Deep Learning, Negative Multinomial, Batch-Adversarial, Variational Auto-Encoder, Single-Cell Epigenomics, scATAC-seq
Source:bioRxiv
Publisher:Cold Spring Harbor Laboratory Press
Article Number:2021.05.11.443540
Date:12 May 2021
Official Publication:https://doi.org/10.1101/2021.05.11.443540

Repository Staff Only: item control page

Downloads

Downloads per month over past year

Open Access
MDC Library