AUTHOR=Liu Gan , Liu Xiuqin , Ma Liang 

TITLE=DecOT: Bulk Deconvolution With Optimal Transport Loss Using a Single-Cell Reference

JOURNAL=Frontiers in Genetics

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/genetics/articles/10.3389/fgene.2022.825896

DOI=10.3389/fgene.2022.825896

ISSN=1664-8021

ABSTRACT=Tissues are constitute of heterogeneous cell types. Although single-cell RNA sequencing have paved the way to a deeper understanding of organismal cellular composition. The high cost and technique noise have prevent is widely application.  Alternatively computational deconvolution of bulk tissues can be a cost effective solution. Here, we propose DecOT, a deconvolution method that uses the Wasserstein distance as loss and applies scRNA-seq data as references to characterize the cell type composition from bulk tissue RNA-seq data. The Wasserstein loss in DecOT is able to utilize additional information from gene space. DecOT also applies an ensemble framework to integrate deconvolution results for multiple individuals reference which mitigate the individual/batch effect. By benchmarking DecOT with four recently proposed square loss based methods on pseudo-bulk data from four different single-cell datasets and a real pancreatic islet bulk samples, we show DecOT outperforms other methods and the ensemble framework is robust to the choice of references.