AUTHOR=Li Jianwei , Kong Mengfan , Wang Duanyang , Yang Zhenwu , Hao Xiaoke 

TITLE=Prediction of lncRNA–Disease Associations via Closest Node Weight Graphs of the Spatial Neighborhood Based on the Edge Attention Graph Convolutional Network

JOURNAL=Frontiers in Genetics

VOLUME=Volume 12 - 2021

YEAR=2022

URL=https://www.frontiersin.org/journals/genetics/articles/10.3389/fgene.2021.808962

DOI=10.3389/fgene.2021.808962

ISSN=1664-8021

ABSTRACT=Accumulated evidences of biological clinical trials have shown that long non-coding RNAs (lncRNAs) are closely related to the occurrence and development of various complex human diseases. Researches on lncRNA-disease relations will benefit to further understand the pathogenesis of human complex diseases at the molecular level, but only a small proportion of lncRNA-disease associations have been confirmed. Considering the high cost of biological experiments, exploring potential lncRNA-disease associations with computational approaches has become very urgent.
In this study, the model of LDA-EAGCN based on Closest Node Weight Graph of the Spatial Neighborhood (CNWGSN) and Edge Attention Graph Convolutional Network (EAGCN) was developed to uncover potential lncRNA-disease associations by integrating disease semantic similarity, lncRNA functional similarity and known lncRNA-disease associations. Inspired by the great success of EAGCN method on the chemical molecule property recognition problem, the prediction of lncRNA-disease associations could be regarded as the component recognition problem of lncRNA-disease characteristic graphs. The CNWGSN features of lncRNA-disease associations combined with known lncRNA-disease associations were been introduced to train EAGCN, and correlation scores of input data were predicted with EAGCN for judging whether the input lncRNAs would be associated to the input diseases.
LDA-EAGCN achieved reliable AUC value of 0.9853 in the ten-fold cross-over experiments, which was the highest in the current five state-of-the-art methods. Furthermore, case studies of renal cancer, laryngeal carcinoma and liver cancer were implemented and most of the top-ranking lncRNA-disease associations have been proved by recently published experimental literatures. It can be seen that LDA-EAGCN is an effective model for predicting potential lncRNA-disease associations. Its source code and all data are available at https://github.com/HGDKMF/LDA-EAGCN.