Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Exemplar Guided Deep Neural Network for Spatial Transcriptomics Analysis of Gene Expression Prediction

About

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.

Yan Yang, Md Zakir Hossain, Eric A Stone, Shafin Rahman• 2022

Related benchmarks

TaskDatasetResultRank
gene expression predictionHHK
MSE1.321
16
gene expression predictionPSC
MSE0.345
16
gene expression predictionHER2+
MSE1.112
16
gene expression predictionHER2
MSE0.8916
8
gene expression prediction10xProteomic (test)
PCC@F6.78
8
gene expression predictionKidney
MSE0.7574
8
gene expression predictionSTNet (test)
PCC@F1.51
8
gene expression predictionBreast cancer
MSE0.6662
8
Spatially resolved gene expression predictionSTNet dataset
MSE0.192
7
Spatially resolved gene expression predictionSkin
MSE0.281
7
Showing 10 of 10 rows

Other info

Follow for update