AUTHOR=Lei Xiujuan , Wang Yueyue 

TITLE=Predicting Microbe-Disease Association by Learning Graph Representations and Rule-Based Inference on the Heterogeneous Network

JOURNAL=Frontiers in Microbiology

VOLUME=Volume 11 - 2020

YEAR=2020

URL=https://www.frontiersin.org/journals/microbiology/articles/10.3389/fmicb.2020.00579

DOI=10.3389/fmicb.2020.00579

ISSN=1664-302X

ABSTRACT=More and more clinical observations have indicated that microbes have great impacts on human diseases. Understanding the relationships between microbes and diseases are of profound significance for prevention, early diagnosis and prognosis of diseases. In this paper, based on the known microbe-disease associations, we propose a predictive model to predict potential microbe-disease associations by integrating Learning Graph Representations and a modified Scoring mechanism on the Heterogeneous network (called LGRSH). Firstly, the microbe similarity network and the disease similarity network are obtained based on the Gaussian interaction profile kernel similarity. Then, we construct a heterogeneous network by integrating the microbe similarity network, the disease similarity network and microbe-disease associations’ network. After that, the embedding algorithm Node2vec is implemented to learn the representation for every node in the heterogeneous network. Finally, according to these low-dimensional vector representations, we calculate the relevance for each microbe and disease pair by utilizing a modified rule-based inference method. By comparison with three other methods including LRLSHMDA, KATZHMDA and BiRWHMDA, LGRSH performs better than others. Moreover, in case studies of asthma, Chronic Obstructive Pulmonary Disease (COPD) and Inflammatory Bowel Disease (IBD), there are 8, 8 and 10 out of the top-10 predicted disease-related microbes having been validated respectively, demonstrating that LGRSH performs well in predicting potential microbe-disease associations.