geneDRAGNN - gene Disease PRioritizAtion using Graph Neural Networks

Anonymous

Abstract: Most human diseases exhibit a complex genetic etiology impacted by many genes and proteins in a large network of interactions. The process of evaluating gene-disease association through in-vivo experiments is both time-consuming and expensive. Thus, network-based computational methods capable of modeling the complex interplay between molecular components can lead to more targeted evaluation. In this paper, we propose and validate geneDRAGNN: a general data processing and machine learning methodology for exploiting information about gene-gene interaction networks for predicting gene-disease association. We demonstrate that information about the gene-gene interaction network can significantly improve the performance of gene-disease association prediction models. We apply this methodology to predicting gene-disease association for lung adenocarcinoma, a histological subtype of lung cancer, and perform genomic analysis on genes flagged as potential associations.