Outcome-Guided Disease Subtyping for High-Dimensional Omics Data

TL;DR

This paper introduces a unified outcome-guided disease subtyping method for high-dimensional omics data, integrating feature selection, subtype discovery, and outcome prediction to identify clinically relevant disease subtypes.

Contribution

It proposes a novel latent generative model with embedded feature selection and robust estimation, improving disease subtype identification over existing methods.

Findings

Successfully identifies clinically relevant subtypes in lung disease data

Performs feature selection and outcome prediction simultaneously

Demonstrates robustness to outliers and model violations

Abstract

High-throughput microarray and sequencing technology have been used to identify disease subtypes that could not be observed otherwise by using clinical variables alone. The classical unsupervised clustering strategy concerns primarily the identification of subpopulations that have similar patterns in gene features. However, as the features corresponding to irrelevant confounders (e.g. gender or age) may dominate the clustering process, the resulting clusters may or may not capture clinically meaningful disease subtypes. This gives rise to a fundamental problem: can we find a subtyping procedure guided by a pre-specified disease outcome? Existing methods, such as supervised clustering, apply a two-stage approach and depend on an arbitrary number of selected features associated with outcome. In this paper, we propose a unified latent generative model to perform outcome-guided disease subtyping constructed from omics data, which improves the resulting subtypes concerning the disease of interest. Feature selection is embedded in a regularization regression. A modified EM algorithm is applied for numerical computation and parameter estimation. The proposed method performs feature selection, latent subtype characterization and outcome prediction simultaneously. To account for possible outliers or violation of mixture Gaussian assumption, we incorporate robust estimation using adaptive Huber or median-truncated loss function. Extensive simulations and an application to complex lung diseases with transcriptomic and clinical data demonstrate the ability of the proposed method to identify clinically relevant disease subtypes and signature genes suitable to explore toward precision medicine.