Identifying Ovarian Cancer-Associated EV mRNA Expression Profiles Using Unsupervised Machine Learning and Non-Negative Matrix Factorization
Rama Krishna Thelagathoti, Chao Jiang, Dinesh S. Chandel, Wesley A. Tom, Cleo Sarmiento, Appolinaire Olou, Gary Krzyzanowski, M. Rohan Fernando · 2026
Read Identifying Ovarian Cancer-Associated EV mRNA Expression Profiles Using Unsupervised Machine Learning and Non-Negative Matrix Factorization by Rama Krishna Thelagathoti, Chao Jiang, Dinesh S. Chandel, Wesley A. Tom, Cleo Sarmiento, Appolinaire Olou, Gary Krzyzanowski, M. Rohan Fernando (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-13295405.txt.
Description
Rama Krishna Thelagathoti and colleagues use unsupervised machine learning to find ovarian cancer signals in the parcels tumors shed into body fluids, in a 2026 study. Those parcels, extracellular vesicles, carry messenger RNA from their parent cells, giving a blood-based window on cancer. The data are noisy and the sample sizes small, so group contrasts can miss hidden structure.
The team applied non-negative matrix factorization, which splits expression data into a few gene programs and shows how strongly each sample uses them. A strict cleaning pipeline came first. Judged by rebuilding error and steadiness across runs, the model settled on a compact picture and a shortlist of telling genes. The authors present the method as a low-bias way to rank features in small, wide datasets.
Catalog record
| CREATOR | Rama Krishna Thelagathoti, Chao Jiang, Dinesh S. Chandel, Wesley A. Tom, Cleo Sarmiento, Appolinaire Olou, Gary Krzyzanowski, M. Rohan Fernando |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 39 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |