Exemplar Guided Deep Neural Network for Spatial Transcriptomics Analysis of Gene Expression Prediction
This work addresses the challenge of low-throughput gene expression measurement in spatial transcriptomics, which is crucial for disease understanding and treatment development, by providing a more accurate prediction method, though it appears incremental as it builds on existing techniques like vision transformers.
The paper tackled the problem of predicting gene expression from tissue slide images in spatial transcriptomics by proposing an Exemplar Guided Network (EGN), which uses exemplar learning to boost prediction accuracy and efficiency, achieving superior results compared to past state-of-the-art methods on standard benchmark datasets.
Spatial transcriptomics (ST) is essential for understanding diseases and developing novel treatments. It measures gene expression of each fine-grained area (i.e., different windows) in the tissue slide with low throughput. This paper proposes an Exemplar Guided Network (EGN) to accurately and efficiently predict gene expression directly from each window of a tissue slide image. We apply exemplar learning to dynamically boost gene expression prediction from nearest/similar exemplars of a given tissue slide image window. Our EGN framework composes of three main components: 1) an extractor to structure a representation space for unsupervised exemplar retrievals; 2) a vision transformer (ViT) backbone to progressively extract representations of the input window; and 3) an Exemplar Bridging (EB) block to adaptively revise the intermediate ViT representations by using the nearest exemplars. Finally, we complete the gene expression prediction task with a simple attention-based prediction block. Experiments on standard benchmark datasets indicate the superiority of our approach when comparing with the past state-of-the-art (SOTA) methods.