A Systematic Review of the Application of Graph Neural Networks to Extract Candidate Genes and Biological Associations

The development of high throughput technologies has resulted in the collection of large quantities of genomic and transcriptomic data. However, identifying disease-associated genes or networks from these data has remained an ongoing challenge. In recent years, graph neural networks (GNNs) have emerged as a promising analytical tool, but it is not well understood which characteristics of these models result in improved performance. We conducted a systematic search and review of publications that used GNNs to identify disease-associated biological interactions. Information was extracted about model characteristics and performance with the goal of examining the relationship between these factors and performance. Data leakage was found in 31% of these models. For node level tasks, univariate positive associations were identified between model accuracy and use of hyper parameter optimization, data leakage via hyperparameter optimization, test set size, and total dataset size. Among graph level tasks, an increase in AUC was identified in association with testing method and a decrease with optimization reporting. Data leakage may pose an issue for GNN-based approaches; the adoption of best practice guidelines and consistent reporting of model design would be beneficial for future studies.