AUTHOR=Liu Haijie , Guan Jiaojiao , Li He , Bao Zhijie , Wang Qingmei , Luo Xun , Xue Hansheng TITLE=Predicting the Disease Genes of Multiple Sclerosis Based on Network Representation Learning JOURNAL=Frontiers in Genetics VOLUME=Volume 11 - 2020 YEAR=2020 URL=https://www.frontiersin.org/journals/genetics/articles/10.3389/fgene.2020.00328 DOI=10.3389/fgene.2020.00328 ISSN=1664-8021 ABSTRACT=Multiple sclerosis (MS) is a kind of autoimmune disease that difficult to find exact disease-related genes. Effectively identifying disease-related genes contributes to improving the treatment and diagnosis of multiple sclerosis. Current identifying disease-related genes methods mainly focus on the hypothesis of guilt-by-association and pay little attention to the global topological information of the whole protein-protein-interaction (PPI) network. Besides, network representation learning (NRL) has attracted huge attention in the area of network analysis because of its promising performance on node representation and many downstream tasks. In this paper, we try to introduce network representation learning into the task of disease-related genes prediction and propose a novel framework to identify multiple sclerosis's disease-related genes. The proposed framework mainly contains three steps: capturing the topology structure of the PPI network using NRL-based methods, encoding learned features into low-dimensional space using a stacked autoencoder, and training a support vector machine classifier to predict disease-related genes. Compared with three state-of-the-art algorithms, our proposed framework shows superior performance on the task of predicting multiple sclerosis's disease-related genes.