mFLIP: metabolic flux interval prediction
Baris Can, Sadi Celik, Ali Cakmak · 2026
Read mFLIP: metabolic flux interval prediction by Baris Can, Sadi Celik, Ali Cakmak (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-13474969.txt.
Description
Can and co-authors built a machine learning tool in 2026 that predicts metabolic flux ranges. These ranges give the speeds at which cells convert chemicals along their pathways, without the slow math the standard method needs. The standard approach, flux variability analysis, solves many optimization problems per network and can take hours on large studies. Their tool, mFLIP, learned from flux results computed the slow way across more than 22,000 metabolomics samples drawn from repositories.
Once trained, mFLIP returns flux intervals in under a second, down from minutes per sample with the classical computation it replaces. Random forest and gradient boosting models scored best, with the lowest errors and classification results among the six model families tried. The team validated the approach on six cancer datasets, covering breast, colon, pancreatic, and prostate tumors, and says it beat the prior state-of-the-art method on both speed and accuracy.
Catalog record
| CREATOR | Baris Can, Sadi Celik, Ali Cakmak |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 56 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |