MichiGAN: sampling from disentangled representations of single-cell data using generative adversarial networks

MichiGAN: sampling from disentangled representations of single-cell data using generative adversarial networks

Abstract Deep generative models such as variational autoencoders (VAEs) and generative adversarial networks (GANs) generate and manipulate high-dimensional images. We systematically assess the complementary strengths and weaknesses of these models on single-cell gene expression data. We also develop...

Full description

Bibliographic Details
Main Authors: Hengshi Yu, Joshua D. Welch
Format: Article
Language:English
Published: BMC 2021-05-01
Series:Genome Biology
Subjects:
Cellular identity
Disentangled representations
Generative adversarial networks
Representation learning
Single-cell genomics
Online Access:https://doi.org/10.1186/s13059-021-02373-4

Internet

https://doi.org/10.1186/s13059-021-02373-4

Similar Items