NetActivity enhances transcriptional signals by combining gene expression into robust gene set activity scores through interpretable autoencoders

Abstract

Grouping gene expression into gene set activity scores (GSAS) provides better biological insights than studying individual genes. However, existing gene set projection methods cannot return representative, robust, and interpretable GSAS. We developed NetActivity, a framework based on a sparsely-connected autoencoder and a three-tier training that yields robust and interpretable GSAS. NetActivity was trained with 1,518 well-known gene sets and all GTEx samples, returning GSAS representative of the original transcriptome and assigning higher importance to more biologically relevant genes. Moreover, NetActivity returns GSAS with a more consistent definition than GSVA and hipathia, state-of-the-art gene set projection methods. Finally, NetActivity enables combining bulk RNA-seq and microarray datasets in a meta-analysis of prostate cancer progression, highlighting gene sets related to cell division. When applied to metastatic prostate cancer, gene sets associated with cancer progression were also altered due to drug resistance, while a classical enrichment analysis identified gene sets irrelevant to the phenotype.