Impact of matched samples on domain harmonization in cross-cohort NMR metabolomics
A Ottas, L Goldoni, A Armirotti, S Decherchi · 2026
Read Impact of matched samples on domain harmonization in cross-cohort NMR metabolomics by A Ottas, L Goldoni, A Armirotti, S Decherchi (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-13675295.txt.
Description
Ottas, Goldoni, Armirotti and Decherchi wrote a 2026 study on lining up metabolomics data across study groups. Learning models often drop in skill when data come from a distinct lab or platform. Matched samples, measured in both data sets, may help bridge that gap. The team tested several harmonization methods on NMR data.
Their task was to spot heart failure in plasma data from a large biobank. Models trained on one platform were tested on another with far fewer samples. Most alignment methods beat raw data on cross-group scores. Matched samples, up to about a hundred pairs, were weighed for their added value. Extra data sets on diabetes gave further checks.
Catalog record
| CREATOR | A Ottas, L Goldoni, A Armirotti, S Decherchi |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 63 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |