OmicsGBench: A Framework for Evaluating Graph Neural Networks on Omics Data
Louisa Cornelis, Johan Mathe, Louis Van Langendonck, Guillermo Bernárdez, Nina Miolane
原文摘要
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: how do GNNs perform in this low-sample, high-node omics setting? We introduce OmicsGBench (Omics-Graph Bench), the first benchmarking platform for graph-level prediction on omics expression data, a domain whose defining characteristic is the $n \ll p$ regime. 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. Ablation studies show that performance relies primarily on feature selection and whether the readout preserves node identity. Furthermore, graphs built from known biological interactions offer no consistent advantage over co-expression graphs. 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, OmicsGBench 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/OmicsGBench.
cs.LG