Enrichment analysis on regulatory subspaces: a novel direction for the superior description of cellular responses to SARS-CoV-2

Abstract

StatementThe enrichment analysis of discriminative cell transcriptional responses to SARS-CoV-2 infection using biclustering produces a broader set of superiorly enriched GO terms and KEGG pathways against alternative state-of-the-art machine learning approaches, unraveling novel knowledge. Motivation and methodsThe comprehensive understanding of the impacts of the SARS-CoV-2 virus on infected cells is still incomplete. This work identifies and analyses the main cell regulatory processes affected and induced by SARS-CoV-2, using transcriptomic data from several infectable cell lines available in public databases and in vivo samples. We propose a new class of statistical models to handle three major challenges, namely the scarcity of observations, the high dimensionality of the data, and the complexity of the interactions between genes. Additionally, we analyse the function of these genes and their interactions within cells to compare them to ones affected by IAV (H1N1), RSV and HPIV3 in the target cell lines. ResultsGathered results show that, although clustering and predictive algorithms aid classic functional enrichment analysis, recent pattern-based biclustering algorithms significantly improve the number and quality of the detected biological processes. Additionally, a comparative analysis of these processes is performed to identify potential pathophysiological characteristics of COVID-19. These are further compared to those identified by other authors for the same virus as well as related ones such as SARS-CoV-1. This approach is particularly relevant due to a lack of other works utilizing more complex machine learning tools within this context.