Available online 30 August 2022, 104187

Spectral clustering is widely used to handle complexity in omics data for disease subtyping. It organises observations into coherent groups utilising patient similarity graphs.

Skewed distribution and data variability in the measurements of omics data complicate the identification of molecular disease subtypes defined by clinical diferences, such as survival.

There is a need of robust distance functions that consider extreme values and synthesize the structurally relevant observations in a way that minimize the influence of extreme values in distance functions.

This paper proposes a robust distance function called ROMDEX on the ground to handle extreme values and data variability in omics data for disease subtyping.

The proposed ROMDEX function is embedded into a gaussian kernel to generate fully connected similarity graph for disease subtyping. It is validated on multiple TCGA cancer datasets, and the results are compared with multiple baseline disease subtyping methods.

The evaluaton of results is based on Kaplan–Meier survival time analysis, which is validated using statistical tests e.g., Cox-proportional hazard (Cox p-value).

Molecular disease subtype discovery from omics data is an important research problem in precision medicine.The biggest challenges are the skewed distribution and data variability in the measurements of omics data. These challenges complicate the efficient identification of molecular disease subtypes defined by clinical differences, such as survival. Existing approaches adopt kernels to construct patient similarity graphs from each view through pairwise matching. However, the distance functions used in kernels are unable to utilize the potentially critical information of extreme values and data variability which leads to the lack of robustness. In this paper, a novel robust distance metric (ROMDEX) is proposed to construct similarity graphs for molecular disease subtypes from omics data, which is able to address the data variability and extreme values challenges. The proposed approach is validated on multiple TCGA cancer datasets, and the results are compared with multiple baseline disease subtyping methods. The evaluation of results is based on Kaplan–Meier survival time analysis, which is validated using statistical tests e.g, Cox-proportional hazard (Cox p-value). We reject the null hypothesis that the cohorts have the same hazard, for the P-values less than 0.05. The proposed approach achieved best P-values of 0.00181, 0.00171, and 0.00758 for Gene Expression, DNA Methylation, and MicroRNA data respectively, which shows significant difference in survival between the cohorts. In the results, the proposed approach outperformed the existing state-of-the-art (MRGC, PINS, SNF, Consensus Clustering and Icluster+) disease subtyping approaches on various individual disease views of multiple TCGA datasets.

Disease subtyping

Patient similarity

Graph modeling

Clustering analysis

Robust statistics

Similarity kernels

© 2022 Elsevier Inc. All rights reserved.