OgBench: A Framework for Evaluating Graph Neural Networks on Omics Data

TL;DR

OgBench is a benchmarking framework designed to evaluate graph neural networks on omics data, focusing on the low-sample, high-node regime typical in biological applications, revealing that GNNs often do not outperform simpler models.

Contribution

This work introduces OgBench, the first standardized platform for benchmarking GNNs on omics data in the challenging $n \\ll p$ regime, and provides insights into their limited advantages.

Findings

Widely used GNNs often do not outperform MLPs and classical baselines.

The structure of biological graphs may not inherently improve predictive performance.

OgBench enables development and validation of models tailored for biological graph data.

Abstract

Graph Neural Networks (GNNs) have become the dominant framework for inductive graph-level learning. Yet most benchmarks focus on the regime $n \gg p$, where the number of graphs $n$ greatly exceeds the number of nodes per graph $p$. This overlooks biological domains such as omics, which operate in the opposite $n \ll p$ regime, characterized by large graphs of genes, transcripts, or proteins across few patient samples. This raises the question: \textit{how do GNNs perform in this low-sample, high-node omics setting?} We introduce \texttt{OgBench} (Omics-Graph Bench), the first benchmarking platform for graph-level prediction in the $n \ll p$ regime characteristic of omics data. We provide a standardized, end-to-end modular infrastructure from raw omics data to families of featured graphs with varied structural properties. We benchmark classical GNNs, as well as GNNs designed for large graphs and omics applications, alongside MLPs and machine learning baselines to establish reference performances. Our results show that widely used GNNs often do not outperform simple MLPs and classical baselines. These findings challenge the prevailing assumption that graph structure inherently adds value in this domain, fostering a critical reassessment of current learning paradigms. Ultimately, by exposing these limitations, OgBench provides the open-source ecosystem necessary for the community to develop and validate novel architectures explicitly tailored for biological graphs. The code is available at https://github.com/geometric-intelligence/ogbench.