m6Aexpress-enet: Predicting the regulatory expression m6A sites by an enet-regularization negative binomial regression model

Abstract

As the most abundant mRNA modification, m⁶A controls and influences many aspects of mRNA metabolism including the mRNA stability and degradation. However, the role of specific m⁶A sites in regulating gene expression still remains unclear. In additional, the multicollinearity problem caused by the correlation of methylation level of multiple m⁶A sites in each gene could influence the prediction performance. To address the above challenges, we propose an elastic-net regularized negative binomial regression model (called m⁶Aexpress-enet) to predict which m⁶A site could potentially regulate its gene expression. Comprehensive evaluations on simulated datasets demonstrate that m⁶Aexpress-enet could achieve the top prediction performance. Applying m⁶Aexpress-enet on real MeRIP-seq data from human lymphoblastoid cell lines, we have uncovered the complex regulatory pattern of predicted m⁶A sites and their unique enrichment pathway of the constructed co-methylation modules. m⁶Aexpress-enet proves itself as a powerful tool to enable biologists to discover the mechanism of m⁶A regulatory gene expression. Furthermore, the source code and the step-by-step implementation of m⁶Aexpress-enet is freely accessed at https://github.com/tengzhangs/m6Aexpress-enet.

Keywords: Elastic-net regularization; Gene expression; M(6)A methylation; Negative binomial regression; Regulation.