A technical review of multi-omics data integration methods: from classical statistical to deep generative approaches

TL;DR

This review discusses recent advances in multi-omics data integration, emphasizing deep generative models like VAEs, and highlights technical challenges, new methodologies, and future research directions in biomedical data analysis.

Contribution

It provides a comprehensive overview of state-of-the-art multi-omics integration methods, focusing on deep generative models and recent technological advancements.

Findings

Deep generative models effectively handle data imputation and augmentation.

Recent methods improve joint embedding and batch effect correction.

Emerging foundation models expand multi-modal data integration capabilities.

Abstract

The rapid advancement of high-throughput sequencing and other assay technologies has resulted in the generation of large and complex multi-omics datasets, offering unprecedented opportunities for advancing precision medicine strategies. However, multi-omics data integration presents significant challenges due to the high dimensionality, heterogeneity, experimental gaps, and frequency of missing values across data types. Computational methods have been developed to address these issues, employing statistical and machine learning approaches to uncover complex biological patterns and provide deeper insights into our understanding of disease mechanisms. Here, we comprehensively review state-of-the-art multi-omics data integration methods with a focus on deep generative models, particularly variational autoencoders (VAEs) that have been widely used for data imputation and augmentation, joint embedding creation, and batch effect correction. We explore the technical aspects of loss functions and regularisation techniques including adversarial training, disentanglement and contrastive learning. Moreover, we discuss recent advancements in foundation models and the integration of emerging data modalities, while describing the current limitations and outlining future directions for enhancing multi-modal methodologies in biomedical research.