Integrating Autoencoder and Multi-View Graph Convolutional Networks for Spatial Domains Identification

Spatial transcriptomics technology provides high-resolution gene expression profiles and spatial location information, offering a revolutionary approach to identify tissue regions and cell types. However, due to the characteristics of gene expression data such as high dimension and high noise, some information may be lost when performing feature extraction. Therefore, we propose a framework that integrates an autoencoder and a multi-view graph convolutional network, IAMGCN, to reduce information loss and capture more comprehensive information. Specifically, we use the autoencoder to extract the deep representation of the gene expression matrix. The middle layer of the autoencoder is integrated into the middle layer of the graph convolutional network. This integration aims to reduce the information loss during the information aggregation process of the graph convolutional network. In order to learn the specificity and common information of multiple views, we introduce a contrastive learning strategy, which takes the output of the autoencoder as a positive sample, and reduce the distance between the two views and the autoencoder output, respectively. We test IAMGCN on two datasets and compare it with five other methods, and the experimental results show that IAMGCN achieves the highest accuracy on all datasets.