AUTHOR=López-Cortés Xaviera A. , Manríquez-Troncoso José M. , Hernández-García Ruber , Peralta Daniel 

TITLE=MSDeepAMR: antimicrobial resistance prediction based on deep neural networks and transfer learning

JOURNAL=Frontiers in Microbiology

VOLUME=Volume 15 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/microbiology/articles/10.3389/fmicb.2024.1361795

DOI=10.3389/fmicb.2024.1361795

ISSN=1664-302X

ABSTRACT=Antimicrobial resistance (AMR) is a global health problem that requires early and effective treatments to prevent the indiscriminate use of antimicrobial drugs and the outcome of infections.Mass Spectrometry (MS), and more particularly MALDI-TOF, have been widely adopted by routine clinical microbiology laboratories to identify bacterial species and detect AMR. The analysis of AMR with deep learning is still recent, and most models depend on filters and preprocessing techniques manually applied on spectra. In this study, we propose a deep neural network, MSDeepAMR, to learn from raw mass spectra to predict AMR. MSDeepAMR models were obtained for Escherichia coli, Klebsiella pneumoniae, and Staphylococcus aureus under different antibiotic resistance profiles, and showed a good classification performance. The AUROC was above 0.83 in most cases studied, improving the results of previous investigations by over 10%. Additionally, a transfer learning test was performed to study the benefits of adapting the previously trained models to external data. The adapted models improved the AUROC by up to 20% when compared to a model trained only with external data, demonstrating the potential of the MSDeepAMR model when it is used on new MS data and enabling the extrapolation of the MSDeepAMR model to different laboratories that need to study AMR and do not have the capacity for an extensive sample collection.