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

Ana R. Baião, Zhaoxiang Cai외 6명|arXiv (Cornell University)|2025. 01. 29.

Bioinformatics and Genomic Networks인용 수 5

한 줄 요약

다중-omics 데이터 통합 방법에 대한 포괄적 리뷰로, imputation, joint embedding, 및 batch correction를 위한 심층 생성 모델(특히 variational autoencoders)에 중점을 두고, 손실 함수, regularisation, 및 미래 방향에 대한 논의가 포함된다.

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.

연구 동기 및 목표

• 정밀의학을 위한 고차원이고 이질적인 multi-omics 데이터를 통합하는 데 직면한 도전과제를 동기 부여한다.
• imputation, augmentation, 및 joint embedding에 대한 강조를 두고 최첨단 방법들을 조사한다.
• 손실 함수, regularisation 기법, 및 학습 전략과 같은 기술적 측면을 논의한다.
• 생의학 통합을 위한 foundation models 및 새로운 데이터 모달리티의 최근 발전을 조명한다.
• 다중 모달 생물의학 데이터 통합의 현재 한계 식별 및 향후 연구 방향 제안한다.

제안 방법

• multi-omics 통합을 위한 고전적 통계 및 머신러닝 접근법에 대한 검토.
• imputation, augmentation, 및 joint embedding을 위한 심층 생성 모델, 특히 variational autoencoders (VAEs)에 중점.
• 손실 함수 및 regularisation 기법의 논의... 포함하여 adversarial training, disentanglement, 및 contrastive learning.
• 교차 모달 데이터 통합에 사용된 학습 전략 및 모델 아키텍처의 분석.
• 다중-omics에서의 foundation models 및 신흥 데이터 모달리티에 대한 고려.
• 한계에 대한 비판적 평가 및 향후 방향.

실험 결과

연구 질문

• RQ1 What are the key methodological advancements in multi-omics data integration across classical statistics, ML, and deep generative approaches?
• RQ2 How have VAEs and related generative models been applied to imputation, augmentation, and joint embedding in multi-omics data?
• RQ3 What loss functions, regularisation strategies, and training paradigms best address high dimensionality and heterogeneity in multi-omics data?
• RQ4 What are the limitations of current methods, and what future directions are promising for integrating new data modalities in biomedicine?
• RQ5 How do foundation models and emerging modalities impact multi-omics data integration?

주요 결과

• Deep generative models, notably VAEs, are widely used for data imputation, augmentation, and joint embedding in multi-omics integration.
• Adversarial training, disentanglement, and contrastive learning are important regularisation techniques discussed in the context of multi-omics VAEs.
• Recent advances include foundations models and integration of emerging data modalities.
• The review synthesizes technical aspects of loss functions and regularisation, highlighting their role in addressing high dimensionality and data heterogeneity.
• Limitations of current approaches and gaps point to future directions for more robust, scalable, and interpretable multi-modal methods.