iHerd: an integrative hierarchical graph representation learning framework to quantify network changes and prioritize risk genes in disease

Different genes form complex networks within cells to carry out critical cellular functions, while network alterations in this process can potentially introduce downstream transcriptome perturbations and phenotypic variations. Therefore, developing efficient and interpretable methods to quantify network changes and pinpoint driver genes across conditions is crucial. We propose a hierarchical graph representation learning method, called iHerd. Given a set of networks, iHerd first hierarchically generates a series of coarsened sub-graphs in a data-driven manner, representing network modules at different resolutions (e.g., the level of signaling pathways). Then, it sequentially learns low-dimensional node representations at all hierarchical levels via efficient graph embedding. Lastly, iHerd projects separate gene embeddings onto the same latent space in its graph alignment module to calculate a rewiring index for driver gene prioritization. To demonstrate its effectiveness, we applied iHerd on a tumor-to-normal GRN rewiring analysis and cell-type-specific GCN analysis using single-cell multiome data of the brain. We showed that iHerd can effectively pinpoint novel and well-known risk genes in different diseases. Distinct from existing models, iHerd’s graph coarsening for hierarchical learning allows us to successfully classify network driver genes into early and late divergent genes (EDGs and LDGs), emphasizing genes with extensive network changes across and within signaling pathway levels. This unique approach for driver gene classification can provide us with deeper molecular insights. The code is freely available at https://github.com/aicb-ZhangLabs/iHerd. All other relevant data are within the manuscript and supporting information files.Author summary: In our study, we developed a new method called iHerd to better understand how genes work together within cells and how changes in these interactions can lead to various diseases. Our approach allows us to analyze complex gene networks and identify key genes responsible for network changes across different conditions. We applied iHerd to various data sets and found that it could effectively pinpoint genes linked to different diseases. Our method also helps classify these genes based on the extent of network changes they cause, providing deeper insights into the molecular mechanisms involved. Our research aims to improve our understanding of gene interactions and their role in disease development, ultimately contributing to the discovery of new therapeutic targets. The code is freely available for researchers to use and build upon in their work.