LONMF: a non-negative matrix factorization model based on graph Laplacian and optimal transmission for paired single-cell multi-omics data integration
Mengdi Nan, Qing Ren, Yuhan Fu, Xiang Chen, Guanpeng Qi, Liugen Wang, Jie Gao · 2025
Read LONMF: a non-negative matrix factorization model based on graph Laplacian and optimal transmission for paired single-cell multi-omics data integration by Mengdi Nan, Qing Ren, Yuhan Fu, Xiang Chen, Guanpeng Qi, Liugen Wang, Jie Gao (2025) 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-12729160.txt.
Description
Mengdi Nan and co-authors present, in a 2025 methods paper, a model that merges several kinds of single-cell data from the same cells into one view. Modern tools read genes, proteins, and more from each cell, yet noise and format gaps make joint study hard. Their model factors the data into shared parts while respecting cell similarity maps.
An optimal transport step aligns the data types before factoring, which the authors say sharpens clusters and keeps results readable. Tests ran on three paired data sets from known platforms. The model matched top rivals at grouping cells and beat them at explaining what the groups mean in biology. Marker finding and pathway checks followed from its output.
Catalog record
| CREATOR | Mengdi Nan, Qing Ren, Yuhan Fu, Xiang Chen, Guanpeng Qi, Liugen Wang, Jie Gao |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 44 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |