Handling highly correlated genes of Single-Cell RNA sequencing data in prediction models

Motivation: Selecting feature genes and predicting cells' phenotype are typical tasks in the analysis of scRNA-seq data. Many algorithms were developed for these tasks, but high correlations among genes create challenges specifically in scRNA-seq analysis, which are not well addressed. Highly correlated genes lead to collinearity and unreliable model fitting. Highly correlated genes compete with each other in feature selection, which causes underestimation of their importance. Most importantly, when a causal gene is highly correlated other genes, most algorithms select one of them in a data driven manner. The correlation structure among genes could change substantially. Hence, it is critical to build a prediction model based on causal genes but not their highly correlated genes. Results: To address the issues discussed above, we propose a grouping algorithm which can be integrated in prediction models. Using real benchmark scRNA-seq data sets and simulated cell phenotypes, we show our novel method significantly outperform standard prediction models in the performance of both prediction and feature selection. Our algorithm report the whole group of correlated genes, which allow researchers to conduct additional studies to identify the causal genes from the group. Availability: An R package is being developed and will be made available on the Comprehensive R Archive Network (CRAN). In the meantime, R code can be requested by email.