A deep generative model of single-cell methylomic data

Ethan Weinberger, Su-In Lee

Keywords: single-cell, methylation, variational autoencoders, bisulfite sequencing

TL;DR: We propose a latent variable model for analyzing single-cell methylomic data generated from bisulfite sequencing experiments.

Abstract: Single-cell DNA methyolme profiling platforms based on bisulfite sequencing techniques promise to enable the exploration of epigenomic heterogeneity at an unprecedented resolution. However, substantial noise resulting from technical limitations of these platforms can impede downstream analyses of the data. Here we present methylVI, a deep generative model that learns probabilistic representations of single-cell methylation data which explicitly account for the unique characeteristics of bisulfite-sequencing-derived methylomic data. After initially validating the quality of our model's fit, we proceed to demonstrate how methylVI can facilitate common downstream analysis tasks, including integrating data collected using different sequencing platforms and producing denoised methylome profiles. Our implementation of methylVI is publicly available at https://github.com/suinleelab/methylVI.

Submission Number: 4