Por favor, use este identificador para citar o enlazar este ítem: https://repositorio.uca.edu.ar/handle/123456789/20070
Campo DC Valor Lengua/Idioma
dc.contributor.authorSaavedra, Lucas A.es
dc.contributor.authorMosqueira, Alejoes
dc.contributor.authorBarrantes, Francisco J.es
dc.date.accessioned2025-07-10T15:14:22Z-
dc.date.available2025-07-10T15:14:22Z-
dc.date.issued2024-
dc.identifier.issn2040-3372-
dc.identifier.urihttps://repositorio.uca.edu.ar/handle/123456789/20070-
dc.description.abstractConsiderable efforts are currently being devoted to characterizing the topography of membraneembedded proteins using combinations of biophysical and numerical analytical approaches. In this work, we present an end-to-end (i.e., human intervention-independent) algorithm consisting of two concatenated binary Graph Neural Network (GNNs) classifiers with the aim of detecting and quantifying dynamic clustering of particles. As the algorithm only needs simulated data to train the GNNs, it is parameter-independent. The GNN-based algorithm is first tested on datasets based on simulated, albeit biologically realistic data, and validated on actual fluorescence microscopy experimental data. Application of the new GNN method is shown to be faster than other currently used approaches for high-dimensional SMLM datasets, with the additional advantage that it can be implemented on standard desktop computers. Furthermore, GNN models obtained via training procedures are reusable. To the best of our knowledge, this is the first application of GNN-based approaches to the analysis of particle aggregation, with potential applications to the study of nanoscopic particles like the nanoclusters of membrane-associated proteins in live cells.es
dc.formatapplication/pdfes
dc.language.isoenges
dc.publisherRoyal Society of Chemistryes
dc.rightsAtribución-NoComercial-CompartirIgual 4.0 Internacional*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/4.0/*
dc.sourceNanoscale. 32, 2024.es
dc.subjectMEMBRANAS CELULARESes
dc.subjectTOPOGRAFIAes
dc.subjectPROTEINASes
dc.subjectAPRENDIZAJE PROFUNDOes
dc.subjectALGORITMOSes
dc.titleA supervised graph-based deep learning algorithm to detect and quantify clustered particleses
dc.typeArtículoes
dc.identifier.doi10.1039/d4nr01944j-
uca.issnrd0es
uca.affiliationFil: Saavedra, Lucas A. Pontificia Universidad Católica Argentina. Facultad de Ciencias Médicas; Argentinaes
uca.affiliationFil: Mosqueira, Alejo. Pontificia Universidad Católica Argentina. Facultad de Ciencias Médicas; Argentinaes
uca.affiliationFil: Barrantes, Francisco J. Pontificia Universidad Católica Argentina. Facultad de Ciencias Médicas; Argentinaes
uca.versionpublishedVersiones
item.fulltextWith Fulltext-
item.languageiso639-1en-
item.grantfulltextmixedopen-
crisitem.author.deptInstituto de Investigaciones Biomédicas - BIOMED-
crisitem.author.deptLaboratorio de Neurobiología Molecular-
crisitem.author.deptFacultad de Ciencias Médicas-
crisitem.author.deptInstituto de Investigaciones Biomédicas - BIOMED-
crisitem.author.deptLaboratorio de Neurobiología Molecular-
crisitem.author.deptFacultad de Ciencias Médicas-
crisitem.author.orcid0000-0002-5693-5302-
crisitem.author.orcid0000-0002-4745-681X-
crisitem.author.parentorgFacultad de Ciencias Médicas-
crisitem.author.parentorgInstituto de Investigaciones Biomédicas - BIOMED-
crisitem.author.parentorgPontificia Universidad Católica Argentina-
crisitem.author.parentorgFacultad de Ciencias Médicas-
crisitem.author.parentorgInstituto de Investigaciones Biomédicas - BIOMED-
crisitem.author.parentorgPontificia Universidad Católica Argentina-
Aparece en las colecciones: Artículos
Ficheros en este ítem:
Fichero Descripción Tamaño Formato   Login
supervised-graph-based.pdf2,46 MBAdobe PDF   SOLICITAR ACCESO
supervised-graph-based.jpg906,16 kBJPEGVisualizar/Abrir
Mostrar el registro sencillo del ítem

Google ScholarTM

Ver en Google Scholar


Altmetric

Altmetric


Este ítem está sujeto a una Licencia Creative Commons Creative Commons