Early antifungal resistance prediction based on MALDI-TOF mass spectrometry and machine learning
Diane Duroux, Yiqi Yang, Janko Sattler, Michael Krauthammer, Adrian Egli · 2026
Read Early antifungal resistance prediction based on MALDI-TOF mass spectrometry and machine learning by Diane Duroux, Yiqi Yang, Janko Sattler, Michael Krauthammer, Adrian Egli (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-13470391.txt.
Description
Diane Duroux built a machine-learning tool in 2026 to predict anti-fungus fight-back early from MALDI-TOF mass spectra. Fungal cases kill an estimated 1.5 million people yearly, yet fight-back guessing work has focused on bacteria. The DRIAMS dataset supplied 658 germ spectra linked to 3,046 lab-measured results across three drug groups and seven yeast types.
Main part analysis plus a multi-layer net gave the most stable scores under nested cross-testing, reaching area under the hit-miss curve 0.77 across the ten best species-drug pairs. Best pairs held Candida albicans with micafungin and Candida parapsilosis with fluconazole. Rule-book-based orders could avoid likely tough drugs in about 3 of 10 patients, pending future testing.
Catalog record
| CREATOR | Diane Duroux, Yiqi Yang, Janko Sattler, Michael Krauthammer, Adrian Egli |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 56 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |