Chuyi Zhang Zhen Zhang ^* Feng Zhang Bin Zeng Xin Liu ^* Lei Wang ^*

• Changsha University, Changsha, China

Accumulating evidence shows that human health and disease are closely related to the microbes in the human body.In this manuscript, a new computational model based on graph attention networks and sparse autoencoders, called GCANCAE, was proposed for inferring possible microbe-disease associations. In GCANCAE, we first constructed a heterogeneous network by combining known microbe-disease relationships, disease similarity, and microbial similarity. And then, we adopted the improved GCN and the CSAE to extract Neighbor relations in the adjacency matrix and novel feature representations in heterogeneous networks. After that, in order to estimate the likelihood of a potential microbe associated with a disease, we integrated these two kinds of representations to create unique eigenmatrices for diseases and microbes respectively, and obtain predicted scores for potential microbe-disease associations by calculating the inner product of these two kinds of eigenmatrices.Results and discussion: Based on the baseline databases such as the HMDAD and the Disbiome, intensive experiments were conducted to evaluate the prediction ability of GCANCAE, and experimental results demonstrated that GCANCAE achieved better performance than state-of-the-art competitive methods under the frameworks of both 2-fold and 5-fold CV. Furthermore, case studies of three categories of common diseases, including Asthma, irritable bowel syndrome (IBS), and Type 2 Diabetes (T2D), confirmed the efficiency of GCANCAE as well.