Enhancing spatial transcriptomics data using self supervised learning and transfer learning

Abstract

Spatially resolved transcriptomics technologies enable comprehensive measurement of gene expression patterns in the context of intact tissues. Existing technologies suffer from either low resolution or shallow sequencing depth. We present DIST, a deep learning-based method that imputes the gene expression by self-supervised learning and transfer learning. We evaluate the performance of DIST for imputation, clustering, differential expression analysis and functional enrichment analysis. The results show that DIST can impute the gene expression accurately, enhance the gene expression for low-quality data, help detect more biological meaningful differentially expressed genes and pathways, therefore allow for deeper insights into the biological processes.