A pathway-based kernel boosting method for sample classification using genomic data

TL;DR

This paper introduces a novel pathway-based kernel boosting method that leverages biological pathway information for improved sample classification in cancer genomic data, outperforming existing methods.

Contribution

The paper proposes a new PKB method that integrates pathway knowledge into a boosting framework for predictive modeling of cancer outcomes.

Findings

PKB outperforms competing methods in cancer classification tasks.

PKB identifies biologically relevant pathways associated with clinical outcomes.

The method effectively handles high-dimensional genomic data with limited samples.

Abstract

The analysis of cancer genomic data has long suffered "the curse of dimensionality". Sample sizes for most cancer genomic studies are a few hundreds at most while there are tens of thousands of genomic features studied. Various methods have been proposed to leverage prior biological knowledge, such as pathways, to more effectively analyze cancer genomic data. Most of the methods focus on testing marginal significance of the associations between pathways and clinical phenotypes. They can identify relevant pathways, but do not involve predictive modeling. In this article, we propose a Pathway-based Kernel Boosting (PKB) method for integrating gene pathway information for sample classification, where we use kernel functions calculated from each pathway as base learners and learn the weights through iterative optimization of the classification loss function. We apply PKB and several competing methods to three cancer studies with pathological and clinical information, including tumor grade, stage, tumor sites, and metastasis status. Our results show that PKB outperforms other methods, and identifies pathways relevant to the outcome variables.