X2Graph for Cancer Subtyping Prediction on Biological Tabular Data

TL;DR

X2Graph is a novel deep learning approach that transforms biological tabular data into graph structures using external knowledge, enabling effective cancer subtyping with superior performance on small datasets.

Contribution

The paper introduces X2Graph, a new method that leverages external knowledge to convert tabular data into graphs for improved cancer subtyping accuracy.

Findings

X2Graph outperforms existing methods on three cancer datasets.

The graph transformation improves modeling of biological relationships.

X2Graph is effective on small, scarce datasets.

Abstract

Despite the transformative impact of deep learning on text, audio, and image datasets, its dominance in tabular data, especially in the medical domain where data are often scarce, remains less clear. In this paper, we propose X2Graph, a novel deep learning method that achieves strong performance on small biological tabular datasets. X2Graph leverages external knowledge about the relationships between table columns, such as gene interactions, to convert each sample into a graph structure. This transformation enables the application of standard message passing algorithms for graph modeling. Our X2Graph method demonstrates superior performance compared to existing tree-based and deep learning methods across three cancer subtyping datasets.