POEMS：基于稀疏解码的可解释多组学整合专家乘积模型
POEMS: Product of Experts for Interpretable Multi-omic Integration using Sparse Decoding
AI总结：
POEMS通过稀疏解码、专家乘积模型和门控网络，在不牺牲非线性表达能力的前提下实现可解释的多组学整合，并在癌症亚型分型中同时取得有竞争力的预测性能和可解释的生物标志物发现。
摘要：
整合不同分子层面（即多组学数据）对于揭示疾病的复杂性至关重要；然而，大多数深度生成模型要么以牺牲可解释性为代价优先考虑预测性能，要么通过将解码器线性化来强制实现可解释性，从而削弱了网络的非线性表达能力。为了克服这一权衡，我们提出了POEMS：基于稀疏解码的可解释多组学整合专家乘积模型，这是一个无监督概率框架，在保持预测性能的同时提供可解释性。POEMS在不将网络任何部分线性化的情况下提供可解释性，具体方式为：1）使用稀疏连接将特征映射到潜在因子，这直接转化为生物标志物发现；2）通过专家乘积模型利用共享潜在空间实现跨组学关联；3）通过门控网络报告每个组学的贡献，该网络自适应地计算它们在表示学习中的影响。此外，我们提出了一种高效的稀疏解码器。在一项癌症亚型分型案例研究中，POEMS实现了具有竞争力的聚类和分类性能，同时提供了我们新颖的一组解释，证明了基于生物标志物的洞察与预测准确性可以在多组学表示学习中共存。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
