Predicting disease-associated microbes based on similarity fusion and deep learning

Abstract

Increasing studies have revealed the critical roles of human microbiome in a wide variety of disorders. Identification of disease-associated microbes might improve our knowledge and understanding of disease pathogenesis and treatment. Computational prediction of microbe-disease associations would provide helpful guidance for further biomedical screening, which has received lots of research interest in bioinformatics. In this study, a deep learning-based computational approach entitled SGJMDA is presented for predicting microbe-disease associations. Specifically, SGJMDA first fuses multiple similarities of microbes and diseases using a nonlinear strategy, and extracts feature information from homogeneous networks composed of the fused similarities via a graph convolution network. Second, a heterogeneous microbe-disease network is built to further capture the structural information of microbes and diseases by employing multi-neighborhood graph convolution network and jumping knowledge network. Finally, potential microbe-disease associations are inferred through computing the linear correlation coefficients of their embeddings. Results from cross-validation experiments show that SGJMDA outperforms 6 state-of-the-art computational methods. Furthermore, we carry out case studies on three important diseases using SGJMDA, in which 19, 20, and 11 predictions out of their top 20 results are successfully checked by the latest databases, respectively. The excellent performance of SGJMDA suggests that it could be a valuable and promising tool for inferring disease-associated microbes.

Keywords: graph convolution networks; jumping knowledge networks; microbe-disease association; similarity fusion.

Figure 1

The workflow of SGJMDA in microbe-disease association inference.

Figure 2

Performance analysis on the proportion coefficient .

Figure 3

Performance analysis on the dimension of layer_size.

Figure 4

Performance analysis on the number of layers in multi-neighborhood.

Figure 5

Performance analysis on the number of head nodes in multi-neighborhood.

Figure 6

ROC and PR curves of different methods in association prediction based on 5-CV.

Figure 7

ROC and PR curves of different methods in association prediction based on 10-CV.

Figure 8

Performance comparison between SGJMDA and DSAE_RF when using the same k-means clustering for negative sample selection.