Spatially Resolved Gene Expression Prediction from Histology via Multi-view Graph Contrastive Learning with HSIC-bottleneck Regularization
This work addresses the high cost of spatial transcriptomics data for researchers in computational biology by enabling gene expression prediction from more accessible histology images.
The paper tackles the problem of predicting spatially resolved gene expression from histology images by addressing the neglect of spatial dependencies and the challenge of aligning image and expression representations, resulting in a proposed multi-view graph contrastive learning framework with HSIC-bottleneck regularization.
The rapid development of spatial transcriptomics(ST) enables the measurement of gene expression at spatial resolution, making it possible to simultaneously profile the gene expression, spatial locations of spots, and the matched histopathological images. However, the cost for collecting ST data is much higher than acquiring histopathological images, and thus several studies attempt to predict the gene expression on ST by leveraging their corresponding histopathological images. Most of the existing image-based gene prediction models treat the prediction task on each spot of ST data independently, which ignores the spatial dependency among spots. In addition, while the histology images share phenotypic characteristics with the ST data, it is still challenge to extract such common information to help align paired image and expression representations. To address the above issues, we propose a Multi-view Graph Contrastive Learning framework with HSIC-bottleneck Regularization(ST-GCHB) aiming at learning shared representation to help impute the gene expression of the queried imagingspots by considering their spatial dependency.