A supervised graph-based deep learning algorithm to detect and quantify clustered particles
Considerable 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...
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Artículo |
| Lenguaje: | Inglés |
| Publicado: |
Royal Society of Chemistry
2025
|
| Materias: | |
| Acceso en línea: | https://repositorio.uca.edu.ar/handle/123456789/20070 |
| Aporte de: |
| id |
I33-R139-123456789-20070 |
|---|---|
| record_format |
dspace |
| spelling |
I33-R139-123456789-200702025-07-11T05:02:26Z A supervised graph-based deep learning algorithm to detect and quantify clustered particles Saavedra, Lucas A. Mosqueira, Alejo Barrantes, Francisco J. MEMBRANAS CELULARES TOPOGRAFIA PROTEINAS APRENDIZAJE PROFUNDO ALGORITMOS Considerable 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. 2025-07-10T15:14:22Z 2025-07-10T15:14:22Z 2024 Artículo 2040-3372 https://repositorio.uca.edu.ar/handle/123456789/20070 10.1039/d4nr01944j eng Atribución-NoComercial-CompartirIgual 4.0 Internacional http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Royal Society of Chemistry Nanoscale. 32, 2024. |
| institution |
Universidad Católica Argentina |
| institution_str |
I-33 |
| repository_str |
R-139 |
| collection |
Repositorio Institucional de la Universidad Católica Argentina (UCA) |
| language |
Inglés |
| topic |
MEMBRANAS CELULARES TOPOGRAFIA PROTEINAS APRENDIZAJE PROFUNDO ALGORITMOS |
| spellingShingle |
MEMBRANAS CELULARES TOPOGRAFIA PROTEINAS APRENDIZAJE PROFUNDO ALGORITMOS Saavedra, Lucas A. Mosqueira, Alejo Barrantes, Francisco J. A supervised graph-based deep learning algorithm to detect and quantify clustered particles |
| topic_facet |
MEMBRANAS CELULARES TOPOGRAFIA PROTEINAS APRENDIZAJE PROFUNDO ALGORITMOS |
| description |
Considerable 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. |
| format |
Artículo |
| author |
Saavedra, Lucas A. Mosqueira, Alejo Barrantes, Francisco J. |
| author_facet |
Saavedra, Lucas A. Mosqueira, Alejo Barrantes, Francisco J. |
| author_sort |
Saavedra, Lucas A. |
| title |
A supervised graph-based deep learning algorithm to detect and quantify clustered particles |
| title_short |
A supervised graph-based deep learning algorithm to detect and quantify clustered particles |
| title_full |
A supervised graph-based deep learning algorithm to detect and quantify clustered particles |
| title_fullStr |
A supervised graph-based deep learning algorithm to detect and quantify clustered particles |
| title_full_unstemmed |
A supervised graph-based deep learning algorithm to detect and quantify clustered particles |
| title_sort |
supervised graph-based deep learning algorithm to detect and quantify clustered particles |
| publisher |
Royal Society of Chemistry |
| publishDate |
2025 |
| url |
https://repositorio.uca.edu.ar/handle/123456789/20070 |
| work_keys_str_mv |
AT saavedralucasa asupervisedgraphbaseddeeplearningalgorithmtodetectandquantifyclusteredparticles AT mosqueiraalejo asupervisedgraphbaseddeeplearningalgorithmtodetectandquantifyclusteredparticles AT barrantesfranciscoj asupervisedgraphbaseddeeplearningalgorithmtodetectandquantifyclusteredparticles AT saavedralucasa supervisedgraphbaseddeeplearningalgorithmtodetectandquantifyclusteredparticles AT mosqueiraalejo supervisedgraphbaseddeeplearningalgorithmtodetectandquantifyclusteredparticles AT barrantesfranciscoj supervisedgraphbaseddeeplearningalgorithmtodetectandquantifyclusteredparticles |
| _version_ |
1845297956810391552 |