DeepCpG: accurate prediction of single-cell DNA methylation states using deep learning.
Published version
Peer-reviewed
Repository URI
Repository DOI
Change log
Authors
Angermueller, Christof
Lee, Heather J
Reik, Wolf
Stegle, Oliver https://orcid.org/0000-0003-0507-1839
Abstract
Recent technological advances have enabled DNA methylation to be assayed at single-cell resolution. However, current protocols are limited by incomplete CpG coverage and hence methods to predict missing methylation states are critical to enable genome-wide analyses. We report DeepCpG, a computational approach based on deep neural networks to predict methylation states in single cells. We evaluate DeepCpG on single-cell methylation data from five cell types generated using alternative sequencing protocols. DeepCpG yields substantially more accurate predictions than previous methods. Additionally, we show that the model parameters can be interpreted, thereby providing insights into how sequence composition affects methylation variability.
Description
Keywords
Artificial neural network, DNA methylation, Deep learning, Epigenetics, Machine learning, Single-cell genomics
Journal Title
Genome Biol
Conference Name
Journal ISSN
1474-7596
1474-760X
1474-760X
Volume Title
18
Publisher
Springer Science and Business Media LLC