Spatial Gene Expression Prediction is the process of estimating gene activity across tissue regions by analyzing visual features from histological images, providing a scalable alternative to costly spatial transcriptomics technologies. Spatial gene expression prediction utilizes morphological clues—such as tissue structure and cell arrangement—captured in these images to infer the distribution of gene expression across the tissue. This approach provides a scalable way to study tissue complexity and its molecular functions in both health and disease.

Posts

Predicting Spatially Resolved Gene Expression via Tissue Morphology using Adaptive Spatial GNNs (ECCB)

/in /by

Spatial transcriptomics technologies, which generate a spatial map of gene activity, can deepen the understanding of tissue architecture and its molecular underpinnings in health and disease. However, the high cost makes these technologies difficult to use in practice. Histological images co-registered with targeted tissues are more affordable and routinely generated in many research and clinical studies. Hence, predicting spatial gene expression from the morphological clues embedded in tissue histological images provides a scalable alternative approach to decoding tissue complexity.

Read more