EMMA-STRAT: a multi-omics based machine learning framework for stratification of endometrial carcinoma molecular subtypes and MSI status
Naisarg Patel, Andres Salumets, Vijayachitra Modhukur · 2026
Read EMMA-STRAT: a multi-omics based machine learning framework for stratification of endometrial carcinoma molecular subtypes and MSI status by Naisarg Patel, Andres Salumets, Vijayachitra Modhukur (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/PMC13474893.txt.
Description
Naisarg Patel, Andres Salumets, and Vijayachitra Modhukur build a learning framework in 2026 to sort womb cancer types from layered gene data. The framework, named EMMA-STRAT, blends gene activity, small RNA, and gene marking data. It was trained on a public cohort of 433 cases and checked on two outside cohorts. Six learning methods were benchmarked before final picks.
Layered data beat any single layer on both tasks: sorting four gene types and flagging an unstable DNA repair state. Balanced accuracy stayed high on outside data, near the mid-eighties for type sorting and mid-nineties for the repair flag. One model type won each task after feature cuts. Outside checks make the tool a candidate for lab triage.
Catalog record
| CREATOR | Naisarg Patel, Andres Salumets, Vijayachitra Modhukur |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 89280 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |