MO-GCN: A multi-omics graph convolutional network for discriminative analysis of schizophrenia

The methodology of machine learning with multi-omics data has been widely adopted in the discriminative analyses of schizophrenia, but most of these studies ignored the cooperative interactions and topological attributes of multi-omics networks. In this study, we constructed three types of brain graphs (BGs), three types of gut graphs (GGs), and nine types of brain-gut combined graphs (BGCGs) for each individual. We proposed a novel methodology of multi-omics graph convolutional network (MO-GCN) with an attention mechanism to construct a classification model by integrating all BGCGs. We also identified important brain and gut features using the Topk pooling layer and analyzed their correlations with the Positive and Negative Syndrome Scale (PANSS) and MATRICS Consensus Cognitive Battery (MCCB) scores. The results showed that the novel MO-GCN model using BGCGs outperformed the GCN models using either BGs or GGs. In particular, the accuracy of the best model by 5-fold cross-validation reached 84.0 %. Interpretability analysis revealed that the top 10 important brain features were primarily from the hippocampus, olfactory, fusiform and pallidum, which were involved in the brain systems of memory, learning and emotion. The top 10 important gut features were primarily from Dorea, Ruminococcus, Subdoligranulum and Clostridium, etc. Moreover, the important brain and gut features were significantly correlated with the PANSS and MCCB scores, respectively. In conclusion, the MO-GCN can effectively improve the classification performance and provide a potential gut microbiota-brain perspective for the understanding of schizophrenia.