Abstract Multi-omic data can better characterize complex cellular signaling pathways from multiple views compared to individual omic data. However, integrating multi-omic data to rank key disease biomarkers and infer core signaling pathways remains an open problem. Compared to other AI models, graph AI can integrate multi-omic data with large-scale signaling networks and rank biomarkers and signaling interactions using attention mechanisms. In this study, we present a novel graph AI model, mosGraphFlow , and apply it on multi-omic datasets of Alzheimer’s disease (AD). The comparison results show that the proposed model not only achieves the best classification accuracy but also identifies important AD disease biomarkers and signaling interactions. Moreover, the signaling sources are highlighted at specific omic levels to facilitate the understanding of the pathogenesis of AD. The proposed model can also be applied and expanded for other studies using multi-omic data. And the model code are uploaded via GitHub with link: https://github.com/mosGraph/mosGraphFlow

mosGraphFlow: a novel integrative graph AI model mining disease targets from multi-omic data