NMFGOT: a multi-view learning framework for the microbiome and metabolome integrative analysis with optimal transport plan
Yuanyuan Ma, Lifang Liu · 2024
Read NMFGOT: a multi-view learning framework for the microbiome and metabolome integrative analysis with optimal transport plan by Yuanyuan Ma, Lifang Liu (2024) 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-11586431.txt.
Description
Yuanyuan Ma and Lifang Liu (2024) present NMFGOT, a toolkit that analyzes gut microbe and metabolite data together. Modern sequencing makes it cheap to profile the microbes in a sample and the small molecules they produce. The hard part is that microbes, metabolites, and the human environment interact in tangled, nonlinear ways. Single-dataset methods miss those links. NMFGOT is an unsupervised learning framework, so it needs no labeled examples.
Its engine is nonnegative matrix factorization, a method breaking big data tables into simpler parts. A graph-regularized optimal transport plan measures distance between samples as a shifting of mass, which handles curved, high-order links between microbes and metabolites better than plain distances. A spatial term keeps samples near each other in one data type near each other in the shared map. The authors show it at work on joint microbiome and metabolome datasets.
Catalog record
| CREATOR | Yuanyuan Ma, Lifang Liu |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 34 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |