A Variational Information Bottleneck Approach to Multi-Omics Data Integration
This work is significant for biomedical researchers who need to integrate multi-omics data, especially when facing incomplete observations and diverse missing patterns, by providing a method that consistently outperforms existing benchmarks.
This paper addresses the challenge of integrating multi-omics data with incomplete observations and various missing patterns. The authors propose a deep variational information bottleneck approach that models joint representations as a product of marginal representations, allowing efficient learning from incomplete data. Experiments on real-world datasets show consistent performance gains over state-of-the-art benchmarks.
Integration of data from multiple omics techniques is becoming increasingly important in biomedical research. Due to non-uniformity and technical limitations in omics platforms, such integrative analyses on multiple omics, which we refer to as views, involve learning from incomplete observations with various view-missing patterns. This is challenging because i) complex interactions within and across observed views need to be properly addressed for optimal predictive power and ii) observations with various view-missing patterns need to be flexibly integrated. To address such challenges, we propose a deep variational information bottleneck (IB) approach for incomplete multi-view observations. Our method applies the IB framework on marginal and joint representations of the observed views to focus on intra-view and inter-view interactions that are relevant for the target. Most importantly, by modeling the joint representations as a product of marginal representations, we can efficiently learn from observed views with various view-missing patterns. Experiments on real-world datasets show that our method consistently achieves gain from data integration and outperforms state-of-the-art benchmarks.