Inferring spatial transcriptomics markers from whole slide images to characterize metastasis-related spatial heterogeneity of colorectal tumors: A pilot study

We assess the ability for machine learning models to infer gene expression levels across tissue samples. We prototyped and compared several convolutional, transformer, and graph convolutional neural networks to predict spatial RNA patterns at the Visium spots under the hypothesis that the transformer- and graph-based approaches better capture relevant spatial tissue architecture. We further analyzed the model’s ability to recapitulate spatial autocorrelation statistics using SPARK and SpatialDE.