Preprint
Sep 2026
Preserving DEG Rankings for Gene Discovery in Histology-Based Spatial Gene Expression Prediction
Predicting spatial gene expression from histology images could scale spatial transcriptomics (ST) to image-only cohorts, but conventional histology-based ST prediction is trained and evaluated mainly by per-gene spatial-profile reconstruction. This objective is misaligned with a key downstream use of ST: differentially...
Kaito Shiku, Kazuya Nishimura, Yasuhiro Kojima et al.
· 0 citations