HoRDA: Learning higher-order structure information for predicting RNA-disease associations

Julong Li, Jianrui Chen, Zhihui Wang, Xiujuan Lei

Abstract: Highlights•Higher-order graph attention networks better process the attention coefficients between nodes.•Higher-order graph convolution networks aggregate more important higher-order neighbor information.•Higher-order negative sampling strategy obtains the desired negative samples.•HoRDA demonstrates superiority in neoplasms case study and comparisons.