Multivariate Statistical Methods for High-Dimensional Multiset Omics Data Analysis

Abstract

This chapter covers the state-of-the-art multivariate statistical methods designed for high-dimensional multiset omics data analysis. Recent biotechnological developments have enabled large-scale measurement of various biomolecular data, such as genotypic and phenotypic data, dispersed over various omics domains. An emergent research direction is to analyze these data sources using an integrated approach to better model and understand the underlying biology of complex disease conditions. However, comprehensive analysis techniques that can handle both the size and complexity, and at the same time can account for the hierarchical structure of such data, are lacking. An overview of some of the developments in multivariate techniques for high-dimensional omics data analysis, highlighting two well-known multivariate methods, canonical correlation analysis (CCA) and redundancy analysis (RDA), is provided in this chapter. Penalized versions of CCA are widespread in the omics data analysis field, and there is recent work on multiset penalized RDA that is applicable to multiset omics data. How these methods meet the statistical challenges that come with high-dimensional multiset omics data analysis and help to further our understanding of the human condition in terms of health and disease are presented. Additionally, the current challenges to be resolved in the field of omics data analysis are discussed.

Physical Activity Determinants in Older German Adults at Increased Dementia Risk with Multimorbidity: Baseline Results of the AgeWell.de Study

“…To identify which variables were affected with multicollinearity, we tested the variance inflation factors (VIFs). VIFs were less than two, suggesting a moderate correlation, although not sufficiently strong to justify any remedial action [ 50 ]. Data processing and statistical calculations were conducted using IBM SPSS version 25 (1989–2018 by IBM Corp.©, Armonk, New York, NY, USA).…”

NMR: Unique Strengths That Enhance Modern Metabolomics Research

“…Concatenating matrices will further amplify these differences. The concept of penalized multiblock analysis accompanied with feature selection is suitable for this situation. , It also manages the imbalance of signal scales between platforms. Deng et al reported efficient classification of sample groups in integrated LC-MS and NMR data with feature selection for multiblock PLS-DA .…”

“Omics” in traumatic brain injury: novel approaches to a complex disease

“…To date, omics research in TBI is still in its infancy, and most studies approach different aspects of TBI pathophysiology, leaving little space for consolidation of data from multiple sources. Additionally, the statistical modeling of TBI poses a challenge in view of the heterogeneity of the disease and since data generated by high-throughput technology may be measured in thousands to millions per sample [22]. This high dimensionality carries statistical difficulties such as sparsity, multicollinearity, model complexity, and model overfitting [112].…”

“…Therefore, no single omics modality can completely reflect the complexity of TBI, and a system biology approach is needed. To accomplish this, multiset techniques based on PLS and CCA are available [22]. In addition, network and enrichment analysis is valuable to identify molecules of pathophysiological significance and to understand the downstream flow of information from DNA to physiology [60].…”