Graph neural networks can capture complex object relationships. For instance, they can identify cancer genes based on omic features and protein-protein interactions. Prof. Qin Cao, Prof. Stephen K.W. Tsui of the School of Biomedical Sciences, CUHK and their collaborator Prof. Kevin Y. Yip at Sanford Burnham Prebys Medical Discovery Institute have used graph neural networks in finding cancer genes, predicting essential genes and beyond. This paper is part of the reusability report collection of Nature Machine Intelligence, which seriously evaluates the reproducibility of published work and reusability of methods in novel applications.

The findings have been published in Nature Machine Intelligence: https://www.nature.com/articles/s42256-022-00454-y