Benchmarking deep learning architectures for MALDI-TOF mass spectrometry in infectious disease diagnostics and vector-borne disease surveillance

Noshine Mohammad, Alexandre Godmer, Renaud Piarroux, Cécile Nabet, Xavier Tannier · 2026

Read Benchmarking deep learning architectures for MALDI-TOF mass spectrometry in infectious disease diagnostics and vector-borne disease surveillance by Noshine Mohammad, Alexandre Godmer, Renaud Piarroux, Cécile Nabet, Xavier Tannier (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/PMC13597518.txt.

Description

Noshine Mohammad and colleagues tested deep learning systems that read MALDI-TOF mass spectra, the tool that names microbes in minutes, across three public health jobs. Their 2026 study used 7,424 spectra to test naming of a difficult mycobacterium's subspecies and its drug resistance, plus mosquito species naming and age guessing from body parts.

Balanced scores ran from the mid-eighties to mid-nineties percent for species tasks, and resistance calls scored higher still. Mosquito age estimates landed within roughly two to four days of the truth. Prep choices and tweaks for machine and sample spread proved key. The team also weighed computing cost and energy use against the score gained. The authors argue the pairing of the device with tuned AI could carry high-end testing into field and low-resource settings.

Catalog record

CREATORNoshine Mohammad, Alexandre Godmer, Renaud Piarroux, Cécile Nabet, Xavier Tannier
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE63278
LICENSEhttps://creativecommons.org/licenses/by/4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/article/MED/PMC13597518

Browse the full library · About the Tower of Babel