UMMAN: Unsupervised Multi-graph Merge Adversarial Network for Disease Prediction Based on Intestinal Flora

The abundance of intestinal flora is closely related to human diseases, but diseases are not caused by a single gut microbe. Instead, they result from the complex interplay of numerous microbial entities. This intricate and implicit connection among gut microbes poses a significant challenge for disease prediction using abundance information from OTU data. Recently, several methods have shown potential in predicting corresponding diseases. However, these methods fail to learn the inner association among gut microbes from different hosts, leading to unsatisfactory performance. In this paper, we propose a novel architecture, Unsupervised Multi-graph Merge Adversarial Network (UMMAN). UMMAN can obtain the embeddings of nodes in the Multi-Graph with an unsupervised scenario, which helps learn the multiplex and implicit association. Our method is the first to combine Graph Neural Networks with the task of intestinal flora disease prediction. We construct the Original-Graph using multiple relation types and generate the Shuffled-Graph by disrupting the nodes. We introduce the Node Feature Global Integration (NFGI) module to represent the global features of the graph. Furthermore, we design a joint loss comprising adversarial loss and hybrid attention loss to ensure that the real graph embedding aligns closely with the Original-Graph and diverges from the Shuffled-Graph. Comprehensive experiments on five benchmark OTU gut microbiome datasets demonstrate the effectiveness and stability of our method.