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

Genome Biology

Hengshi Yu¹  Joshua D. Welch² 

[1] Department of Biostatistics, University of Michigan, Ann Arbor, USA;Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, USA;Department of Computer Science and Engineering, University of Michigan, Ann Arbor, USA;

关键词: Cellular identity;    Disentangled representations;    Generative adversarial networks;    Representation learning;    Single-cell genomics;   

DOI  :  10.1186/s13059-021-02373-4

来源: Springer

【 摘 要 】

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.

【 授权许可】

CC BY