Cargando…

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

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 MichiGAN...

Descripción completa

Detalles Bibliográficos
Autores principales: Yu, Hengshi, Welch, Joshua D.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: BioMed Central 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8139054/
https://www.ncbi.nlm.nih.gov/pubmed/34016135
http://dx.doi.org/10.1186/s13059-021-02373-4
Descripción
Sumario: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 MichiGAN, a novel neural network that combines the strengths of VAEs and GANs to sample from disentangled representations without sacrificing data generation quality. We learn disentangled representations of three large single-cell RNA-seq datasets and use MichiGAN to sample from these representations. MichiGAN allows us to manipulate semantically distinct aspects of cellular identity and predict single-cell gene expression response to drug treatment. SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at (10.1186/s13059-021-02373-4).