DISSECT: deep semi-supervised consistency regularization for accurate cell type fraction and gene expression estimation

Genome Biol. 2024 Apr 30;25(1):112. doi: 10.1186/s13059-024-03251-5.

Abstract

Cell deconvolution is the estimation of cell type fractions and cell type-specific gene expression from mixed data. An unmet challenge in cell deconvolution is the scarcity of realistic training data and the domain shift often observed in synthetic training data. Here, we show that two novel deep neural networks with simultaneous consistency regularization of the target and training domains significantly improve deconvolution performance. Our algorithm, DISSECT, outperforms competing algorithms in cell fraction and gene expression estimation by up to 14 percentage points. DISSECT can be easily adapted to other biomedical data types, as exemplified by our proteomic deconvolution experiments.

Keywords: Cell deconvolution; Deep learning; Semi-supervised learning.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Algorithms*
  • Deep Learning
  • Gene Expression Profiling / methods
  • Humans
  • Neural Networks, Computer
  • Proteomics / methods