Ver publicación 

Mostrar el registro sencillo de la publicación

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

dc.contributor.authorLópez-Cortés, Xaviera A.
dc.contributor.authorManríquez-Troncoso, José M.
dc.contributor.authorHernández-García, Ruber
dc.contributor.authorPeralta, Daniel
dc.date.accessioned2024-06-05T15:22:16Z
dc.date.available2024-06-05T15:22:16Z
dc.date.issued2024
dc.identifier.urihttp://repositorio.ucm.cl/handle/ucm/5416
dc.description.abstractIntroduction: 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. Methods: This study propose a deep neural network, MSDeepAMR, to learn from raw mass spectra to predict AMR. MSDeepAMR model was implemented for Escherichia coli, Klebsiella pneumoniae, and Staphylococcus aureus under different antibiotic resistance profiles. Additionally, a transfer learning test was performed to study the benefits of adapting the previously trained models to external data. Results: MSDeepAMR models showed a good classification performance to detect antibiotic resistance. The AUROC of the model was above 0.83 in most cases studied, improving the results of previous investigations by over 10%. The adapted models improved the AUROC by up to 20% when compared to a model trained only with external data. Discussion: This study demonstrate the potential of the MSDeepAMR model to predict antibiotic resistance and their use on external MS data. This allow the extrapolation of the MSDeepAMR model to de used in different laboratories that need to study AMR and do not have the capacity for an extensive sample collection.es_CL
dc.language.isoenes_CL
dc.rightsAtribución-NoComercial-SinDerivadas 3.0 Chile*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/cl/*
dc.sourceFrontiers in Microbiology, 15, 1361795es_CL
dc.subjectMALDI-TOFes_CL
dc.subjectDeep learninges_CL
dc.subjectAntibiotic resistancees_CL
dc.subjectEscherichia colies_CL
dc.subjectKlebsiella pneumoniaees_CL
dc.subjectStaphylococcus aureuses_CL
dc.subjectTransfer learninges_CL
dc.titleMSDeepAMR: antimicrobial resistance prediction based on deep neural networks and transfer learninges_CL
dc.typeArticlees_CL
dc.ucm.facultadFacultad de Ciencias de la Ingenieríaes_CL
dc.ucm.indexacionScopuses_CL
dc.ucm.indexacionIsies_CL
dc.ucm.urifrontiersin.org/journals/microbiology/articles/10.3389/fmicb.2024.1361795/full#h1es_CL
dc.ucm.doidoi.org/10.3389/fmicb.2024.1361795es_CL


Ficheros en la publicación

FicherosTamañoFormatoVer

No hay ficheros asociados a esta publicación.

Esta publicación aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo de la publicación

Atribución-NoComercial-SinDerivadas 3.0 Chile
Excepto si se señala otra cosa, la licencia de la publicación se describe como Atribución-NoComercial-SinDerivadas 3.0 Chile