The Deep Generative Decoder: MAP estimation of representations improves modelling of single-cell RNA data.

Journal: Bioinformatics (Oxford, England)
PMID: 37572301

Abstract

MOTIVATION: Learning low-dimensional representations of single-cell transcriptomics has become instrumental to its downstream analysis. The state of the art is currently represented by neural network models, such as variational autoencoders, which use a variational approximation of the likelihood for inference.

Authors

  • Viktoria Schuster
    Department of Health Technology, Section for Bioinformatics, Technical University of Denmark, DTU, 2800 Kgs, Lyngby, Denmark.
  • Anders Krogh
    Department of Computer Science, University of Copenhagen, Copenhagen, Denmark.

Keywords

External Resources

Popular Topics
Recent Journals