ResSAT: enhancing spatial transcriptomics prediction from H&E-stained histology images with an interactive spot transformer
Anqi Liu, Yue Zhao, Woong-Ki Kim, Hui Shen, Zhengming Ding, Hong-Wen Deng · 2026
Read ResSAT: enhancing spatial transcriptomics prediction from H&E-stained histology images with an interactive spot transformer by Anqi Liu, Yue Zhao, Woong-Ki Kim, Hui Shen, Zhengming Ding, Hong-Wen Deng (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13576212.txt.
Description
Anqi Liu leads a 2026 study presenting ResSAT, a model that predicts gene activity maps of tissue from ordinary stained microscope images. Spatial transcriptomics measures which genes are active at each spot in a tissue slice, yet the process is slow and costly. Standard H&E stained images are cheap and routine, and tissue structure in them tracks gene patterns.
ResSAT blends image features, spot locations, and a transformer step that lets spots attend to each other, with residual network parts carrying the image reading. Benchmark tests on ten public Visium datasets put it ahead of rival methods. The predicted maps kept the spatial patterns that matter for biology, according to the authors. They present the model as a cheaper, faster route to many gene activity profiles.
Catalog record
| CREATOR | Anqi Liu, Yue Zhao, Woong-Ki Kim, Hui Shen, Zhengming Ding, Hong-Wen Deng |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 63168 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |