MGREL: A multi-graph representation learning-based ensemble learning method for gene-disease association prediction

Ziyang Wang, Yaowen Gu, Si Zheng, Lin Yang, Jiao Li

Abstract: Highlights•A gene-disease association prediction model (MGREL) is proposed based on multiple graph representation learning and ensemble learning.•MGREL simultaneously utilizes the genetic, therapeutic, and topological features for gene and disease high-order representations.•MGREL outperforms 5 baselines both in the general association prediction and challengeable unseen tasks.