Adversarial regularized autoencoder graph neural network for microbe-disease associations prediction

Abstract

Background: Microorganisms inhabit various regions of the human body and significantly contribute to numerous diseases. Predicting the associations between microbes and diseases is crucial for understanding pathogenic mechanisms and informing prevention and treatment strategies. Biological experiments to determine these associations are time-consuming and costly. Therefore, integrating deep learning with biological networks can efficiently identify potential microbe-disease associations on a large scale.

Methods: We propose an adversarial regularized autoencoder graph neural network algorithm, named Stacked Adversarial Regularization for Microbe-Disease Associations Prediction (SARMDA), for predicting associations between microbes and diseases. First, we integrate topological structural similarity and functional similarity metrics of microbes and diseases to construct a heterogeneous network. Then, utilizing an autoencoder based on GraphSAGE, we learn both the topological and attribute representations of nodes within the constructed network. Finally, we introduce an adversarial regularized autoencoder graph neural network embedding model to address the inherent limitations of traditional GraphSAGE autoencoders in capturing global information.

Results: Under the five-fold cross-validation on microbe-disease pairs, SARMDA was compared with eight advanced methods using the Human Microbe-Disease Association Database (HMDAD) and Disbiome databases. The best area under the ROC curve (AUC) achieved by SARMDA on HMDAD was 0.9891$\pm$0.0057, and the best area under the precision-recall curve (AUPR) was 0.9902$\pm$0.0128. On the Disbiome dataset, the AUC was 0.9328$\pm$0.0072, and the best AUPR was 0.9233$\pm$0.0089, outperforming the other eight MDAs prediction methods. Furthermore, the effectiveness of our model was demonstrated through a detailed analysis of asthma and inflammatory bowel disease cases.

Keywords: autoencoders; generative adversarial learning; graph neural networks; microbe-disease associations prediction.

Figure 1

Adversarial regularized autoencoder graph neural network framework.

Figure 2

ROC and PR curves of the model with WGAN-GP on the HMDAD and Disbiome datasets. (A) and (B) denote the ROC and PR curves on the HMDAD database, respectively. (C) and (D) represent the ROC and PR curves on the Disbiome database, respectively.

Figure 3

(A) Denote the F1, MCC, Accurracy, Precision, and recall on the HMDAD database, respectively. (B) Denote the F1, MCC, Accurracy, Precision, and recall on the Disbiome database, respectively.

Figure 4

Sensitivity of SARMDA to weight factors β, size of encoder dimension, and number of neural network layers.

Figure 5

ROC and PR curves of different graph neural networks in the HMDAD and Disbiome dataset. (A) and (B) denote the ROC and PR curves on the HMDAD database, respectively. (C) and (D) represent the ROC and PR curves on the Disbiome database, respectively.