spMosaic: multi-sample integration for scalable spatial domain discovery based on spatial transcriptomics
Shiwei Fu, Han Li, Wei Vivian Li · 2026
Read spMosaic: multi-sample integration for scalable spatial domain discovery based on spatial transcriptomics by Shiwei Fu, Han Li, Wei Vivian Li (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/pmc-13625658.txt.
Description
Shiwei Fu, Han Li, and Wei Vivian Li present a tool for finding tissue regions across many samples at once in a 2026 paper. Spatial transcriptomics reads gene activity in place, inside intact tissue slices. Comparing regions across slices and people is hard: batch effects, personal variation, and mismatched coordinates all interfere. Their framework, spMosaic, attacks the problem in three stages.
A statistical smoother first finds genes that vary in space in every sample. A dual-encoder network then learns compact sample descriptions while pushing batch noise into its own corner, and a clustering step tightens the region assignments. Against nine rival methods it clustered as well or better, and it alone scaled to a test of nearly 380,000 spots from mouse cortex samples. The authors pitch it for cohort-scale tissue atlases.
Catalog record
| CREATOR | Shiwei Fu, Han Li, Wei Vivian Li |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 103 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |