High-throughput technologies have been used to generate a large amount of omics data. In the past, single-level analysis has been extensively conducted where the omics measurements at different levels, including mRNA, microRNA, CNV and DNA methylation, are analyzed separately. As the molecular complexity of disease etiology exists at all different levels, integrative analysis offers an effective way to borrow strength across multi-level omics data and can be more powerful than single level analysis. In this article, we focus on reviewing existing multi-omics integration studies by paying special attention to variable selection methods. We first summarize published reviews on integrating multi-level omics data. Next, after a brief overview on variable selection methods, we review existing supervised, semi-supervised and unsupervised integrative analyses within parallel and hierarchical integration studies, respectively. The strength and limitations of the methods are discussed in detail. No existing integration method can dominate the rest. The computation aspects are also investigated. The review concludes with possible limitations and future directions for multi-level omics data integration.

Lipid species are critical components of eukaryotic membranes. They play key roles in many biological processes such as signal transduction, cell homeostasis, and energy storage. Investigations of lipid–environment interactions, in addition to the lipid and environment main effects, have important implications in understanding the lipid metabolism and related changes in phenotype. In this study, we developed a novel penalized variable selection method to identify important lipid–environment interactions in a longitudinal lipidomics study. An efficient Newton–Raphson based algorithm was proposed within the generalized estimating equation (GEE) framework. We conducted extensive simulation studies to demonstrate the superior performance of our method over alternatives, in terms of both identification accuracy and prediction performance. As weight control via dietary calorie restriction and exercise has been demonstrated to prevent cancer in a variety of studies, analysis of the high-dimensional lipid datasets collected using 60 mice from the skin cancer prevention study identified meaningful markers that provide fresh insight into the underlying mechanism of cancer preventive effects.

We introduce interep, an R package for interaction analysis of repeated measurement data with high-dimensional main and interaction effects. In G × E interaction studies, the forms of environmental factors play a critical role in determining how structured sparsity should be imposed in the high-dimensional scenario to identify important effects. Zhou et al. (2019) (PMID: 31816972) proposed a longitudinal penalization method to select main and interaction effects corresponding to the individual and group structure, respectively, which requires a mixture of individual and group level penalties. The R package interep implements generalized estimating equation (GEE)-based penalization methods with this sparsity assumption. Moreover, alternative methods have also been implemented in the package. These alternative methods merely select effects on an individual level and ignore the group-level interaction structure. In this software article, we first introduce the statistical methodology corresponding to the penalized GEE methods implemented in the package. Next, we present the usage of the core and supporting functions, which is followed by a simulation example with R codes and annotations. The R package interep is available at The Comprehensive R Archive Network (CRAN).

Analysis of longitudinal data in high-dimensional gene–environment interaction studies have been extensively conducted using variable selection methods. Despite their success, these studies have been consistently challenged by the lack of uncertainty quantification procedures to identify main and interaction effects under longitudinal phenotypes that follow heavy-tailed distributions due to disease heterogeneity. In this article, to improve statistical rigor of variable selection-based G × E analysis, we propose to apply the robust Bayesian linear mixed-effect model with a false discovery rate (FDR) control procedure to tackle these challenges. The Bayesian mixed model adopts a robust likelihood function to account for skewness in longitudinal phenotypic measurements, and it imposes spike-and-slab priors to detect important main and interaction effects. Leveraging the parallelism between spike-and-slab priors and the Bayesian approach to hypothesis testing, we perform variable selection and uncertainty quantification through a Bayesian false discovery rate (FDR)-assisted procedure. Numerical analyses have demonstrated the advantage of our proposal over alternative approaches. A case study of a longitudinal cancer prevention study with high-dimensional lipid measures yields main and interaction effects with important biological implications.

Robust variable selection methods have emerged as powerful tools for dissecting high-dimensional gene–environment interactions in longitudinal studies, owing to their ability to accommodate intra-cluster correlations, capture structured sparsity, and handle heavy-tailed repeated measures. Despite these advantages, variable selection-based interaction analysis still suffers from a lack of valid inferential tools to quantify the uncertainty associated with important gene–environment interactions. In this paper, we introduce the R package mixedBayes (version 0.2.5), which implements fully Bayesian robust mixed-effects models proposed in recent work for high-dimensional longitudinal gene–environment interaction analysis. Specifically, the package considers two major classes of mixed models. The first accommodates interactions between omics features and treatment effects arising from repeated-measures one-way ANOVA with high-dimensional genetic factors. The second provides a more general framework for modeling interactions between individual genetic main effects and environmental factors. Both models enable posterior Bayesian inference via Markov chain Monte Carlo (MCMC). We provide detailed numerical examples and accompanying R code to facilitate robust interaction analysis using mixedBayes. In addition, a case study based on longitudinal asthma data with high-dimensional SNP measurements is presented.