Statistical Modeling of MicroRNA Expression with Human Cancers

Abstract

MicroRNAs (miRNAs) are small non-coding RNAs (containing about 22 nucleotides) that regulate gene expression. MiRNAs are involved in many different biological processes such as cell proliferation, differentiation, apoptosis, fat metabolism, and human cancer genes; while miRNAs may function as candidates for diagnostic and prognostic biomarkers and predictors of drug response. This paper emphasizes the statistical methods in the analysis of the associations of miRNA gene expression with human cancers and related clinical phenotypes: 1) simple statistical methods include chi-square test, correlation analysis, t-test and one-way ANOVA; 2) regression models include linear and logistic regression; 3) survival analysis approaches such as non-parametric Kaplan-Meier method and log-rank test as well as semi-parametric Cox proportional hazards models have been used for time to event data; 4) multivariate method such as cluster analysis has been used for clustering samples and principal component analysis (PCA) has been used for data mining; 5) Bayesian statistical methods have recently made great inroads into many areas of science, including the assessment of association between miRNA expression and human cancers; and 6) multiple testing.