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

Publication Date: 9/16/2024

Event: 2024 European Conference on Computational Biology (ECCB)

Reference: pp. 1-9, 2024

Authors: Tianci Song, University of Minnesota, NEC Laboratories America, Inc.; Eric Cosatto, NEC Laboratories America, Inc.; Gaoyuan Wang, Yale University; Rui Kuang, University of Minnesota; Mark Gerstein, Yale University; Martin Renqiang Min, NEC Laboratories America, Inc.; Jonathan Warrell, NEC Laboratories America, Inc.

Abstract: 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.

Publication Link: