End-To-End Deep Learning Explains Antimicrobial Resistance in Peak-Picking-Free MALDI-MS Data

Overview

Journal Anal Chem

Date 2025 Feb 2

PMID 39893590

Authors

Johan K Lassen

Palle Villesen

Affiliations

Soon will be listed here.

Abstract

Mass spectrometry is used to determine infectious microbial species in thousands of clinical laboratories across the world. The vast amount of data allows modern data analysis methods that harvest more information and potentially answer new questions. Here, we present an end-to-end deep learning model for predicting antibiotic resistance using raw matrix assisted laser desorption ionization mass spectrometry (MALDI-MS) data. We used a 1-dimensional convolutional neural network to model (almost) raw data, skipping conventional peak-picking and directly predict resistance. The model's performance is state-of-the-art, having AUCs between 0.93 and 0.99 in all antimicrobial resistance phenotypes and validates across time and location. Feature attribution values highlight important insights into the model and how the end-to-end workflow can be improved further. This study showcases that reliable resistance phenotyping using MALDI-MS data is attainable and highlights the gains of using end-to-end deep learning for spectrometry data.

References

De Waele G, Menschaert G, Vandamme P, Waegeman W . Pre-trained Maldi Transformers improve MALDI-TOF MS-based prediction. Comput Biol Med. 2025; 186:109695. DOI: 10.1016/j.compbiomed.2025.109695. View

Clark A, Kaleta E, Arora A, Wolk D . Matrix-assisted laser desorption ionization-time of flight mass spectrometry: a fundamental shift in the routine practice of clinical microbiology. Clin Microbiol Rev. 2013; 26(3):547-603. PMC: 3719498. DOI: 10.1128/CMR.00072-12. View

Smith C, Want E, OMaille G, Abagyan R, Siuzdak G . XCMS: processing mass spectrometry data for metabolite profiling using nonlinear peak alignment, matching, and identification. Anal Chem. 2006; 78(3):779-87. DOI: 10.1021/ac051437y. View

Wang H, Hsieh T, Chung C, Chang H, Horng J, Lu J . Efficiently Predicting Vancomycin Resistance of From MALDI-TOF MS Spectra Using a Deep Learning-Based Approach. Front Microbiol. 2022; 13:821233. PMC: 9231590. DOI: 10.3389/fmicb.2022.821233. View

Mortier T, Wieme A, Vandamme P, Waegeman W . Bacterial species identification using MALDI-TOF mass spectrometry and machine learning techniques: A large-scale benchmarking study. Comput Struct Biotechnol J. 2021; 19:6157-6168. PMC: 8649224. DOI: 10.1016/j.csbj.2021.11.004. View

Yu J, Tien N, Liu Y, Cho D, Chen J, Tsai Y . Rapid Identification of Methicillin-Resistant Staphylococcus aureus Using MALDI-TOF MS and Machine Learning from over 20,000 Clinical Isolates. Microbiol Spectr. 2022; 10(2):e0048322. PMC: 9045122. DOI: 10.1128/spectrum.00483-22. View

Gloaguen Y, Kirwan J, Beule D . Deep Learning-Assisted Peak Curation for Large-Scale LC-MS Metabolomics. Anal Chem. 2022; 94(12):4930-4937. PMC: 8969107. DOI: 10.1021/acs.analchem.1c02220. View

Zhang X, Lin T, Xu J, Luo X, Ying Y . DeepSpectra: An end-to-end deep learning approach for quantitative spectral analysis. Anal Chim Acta. 2019; 1058:48-57. DOI: 10.1016/j.aca.2019.01.002. View

Lapuschkin S, Waldchen S, Binder A, Montavon G, Samek W, Muller K . Unmasking Clever Hans predictors and assessing what machines really learn. Nat Commun. 2019; 10(1):1096. PMC: 6411769. DOI: 10.1038/s41467-019-08987-4. View

10.

Lundberg S, Nair B, Vavilala M, Horibe M, Eisses M, Adams T . Explainable machine-learning predictions for the prevention of hypoxaemia during surgery. Nat Biomed Eng. 2019; 2(10):749-760. PMC: 6467492. DOI: 10.1038/s41551-018-0304-0. View

11.

Gibb S, Strimmer K . MALDIquant: a versatile R package for the analysis of mass spectrometry data. Bioinformatics. 2012; 28(17):2270-1. DOI: 10.1093/bioinformatics/bts447. View

12.

Kantz E, Tiwari S, Watrous J, Cheng S, Jain M . Deep Neural Networks for Classification of LC-MS Spectral Peaks. Anal Chem. 2019; 91(19):12407-12413. PMC: 7089603. DOI: 10.1021/acs.analchem.9b02983. View

13.

Kelley D, Snoek J, Rinn J . Basset: learning the regulatory code of the accessible genome with deep convolutional neural networks. Genome Res. 2016; 26(7):990-9. PMC: 4937568. DOI: 10.1101/gr.200535.115. View

14.

Alzubaidi L, Zhang J, Humaidi A, Al-Dujaili A, Duan Y, Al-Shamma O . Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. J Big Data. 2021; 8(1):53. PMC: 8010506. DOI: 10.1186/s40537-021-00444-8. View

15.

Angeletti S . Matrix assisted laser desorption time of flight mass spectrometry (MALDI-TOF MS) in clinical microbiology. J Microbiol Methods. 2016; 138:20-29. DOI: 10.1016/j.mimet.2016.09.003. View

16.

Weis C, Cuenod A, Rieck B, Dubuis O, Graf S, Lang C . Direct antimicrobial resistance prediction from clinical MALDI-TOF mass spectra using machine learning. Nat Med. 2022; 28(1):164-174. DOI: 10.1038/s41591-021-01619-9. View

17.

Melnikov A, Tsentalovich Y, Yanshole V . Deep Learning for the Precise Peak Detection in High-Resolution LC-MS Data. Anal Chem. 2019; 92(1):588-592. DOI: 10.1021/acs.analchem.9b04811. View