POEMS: Product of Experts for Interpretable Multi-omic Integration using Sparse Decoding

TL;DR

POEMS is an unsupervised probabilistic framework that integrates multi-omics data, balancing interpretability and predictive accuracy through sparse decoding and a product of experts model, aiding biomarker discovery and disease subtyping.

Contribution

It introduces POEMS, a novel multi-omics integration method that maintains nonlinear expressiveness and interpretability without linearizing the network, enabling biomarker discovery and cross-omic analysis.

Findings

Achieves competitive clustering and classification in cancer subtyping

Provides interpretable biomarkers and cross-omic associations

Balances predictive performance with interpretability

Abstract

Integrating different molecular layers, i.e., multiomics data, is crucial for unraveling the complexity of diseases; yet, most deep generative models either prioritize predictive performance at the expense of interpretability or enforce interpretability by linearizing the decoder, thereby weakening the network's nonlinear expressiveness. To overcome this tradeoff, we introduce POEMS: Product Of Experts for Interpretable Multiomics Integration using Sparse Decoding, an unsupervised probabilistic framework that preserves predictive performance while providing interpretability. POEMS provides interpretability without linearizing any part of the network by 1) mapping features to latent factors using sparse connections, which directly translates to biomarker discovery, 2) allowing for cross-omic associations through a shared latent space using product of experts model, and 3) reporting contributions of each omic by a gating network that adaptively computes their influence in the representation learning. Additionally, we present an efficient sparse decoder. In a cancer subtyping case study, POEMS achieves competitive clustering and classification performance while offering our novel set of interpretations, demonstrating that biomarker based insight and predictive accuracy can coexist in multiomics representation learning.