Loss-Function Learning for Digital Tissue Deconvolution

J Comput Biol. 2020 Mar;27(3):342-355. doi: 10.1089/cmb.2019.0462. Epub 2020 Jan 29.

Abstract

The gene expression profile of a tissue averages the expression profiles of all cells in this tissue. Digital tissue deconvolution addresses the following inverse problem: given the expression profileyof a tissue, what is the cellular compositioncof that tissue? IfXis a matrix whose columns are reference profiles of individual cell types, the compositionccan be computed by minimizing(y-Xc)for a given loss function. Current methods use predefined all-purpose loss functions. They successfully quantify the dominating cells of a tissue, while often falling short in detecting small cell populations. In this study we use training data to learn the loss functionalong with the compositionc. This allows us to adapt to application-specific requirements such as focusing on small cell populations or distinguishing phenotypically similar cell populations. Our method quantifies large cell fractions as accurately as existing methods and significantly improves the detection of small cell populations and the distinction of similar cell types.

Keywords: cellular composition; digital tissue deconvolution; loss-function learning; machine learning; model adaptation.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Algorithms
  • Computational Biology / methods*
  • Gene Expression
  • Humans
  • Loss of Function Mutation
  • Machine Learning
  • Melanoma / genetics*