MultiGATE: integrative analysis and regulatory inference in spatial multi-omics data via graph representation learning
Jianhua Miao, Jinzhao Li, Jingxue Xin, Jia-Juan Tu, Muyang Ge, Ji Qi, Xiaocheng Zhou, Ying Zhu, Can Yang, Zhixiang Lin
Abstract
New spatial multi-omics technologies, which jointly profile transcriptome and epigenome/protein markers for the same tissue section, expand the frontiers of spatial techniques. Here, we introduce MultiGATE, which utilizes a two-level graph attention auto-encoder to integrate the multi-modality and spatial information in spatial multi-omics data. The key feature of MultiGATE is that it simultaneously performs embedding of the spatial pixels and infers the cross-modality regulatory relationship, which allows deeper data integration and provides insights on transcriptional regulation. We evaluate the performance of MultiGATE on spatial multi-omics datasets obtained from different tissues and platforms. Through effectively integrating spatial multi-omics data, MultiGATE both enhances the extraction of latent embeddings of the pixels and boosts the inference of transcriptional regulation for cross-modality genomic features.