Please use this identifier to cite or link to this item:
https://repositorio.uca.edu.ar/handle/123456789/14114
Título : | A deep learning-based approach to model anomalous diffusion of membrane proteins: the case of the nicotinic acetylcholine receptor | Autor : | Buena Maizon, Héctor Barrantes, Francisco José |
Palabras clave : | INTELIGENCIA ARTIFICIAL; APRENDIZAJE AUTOMÁTICO; APRENDIZAJE PROFUNDO; PROTEÍNA DE MEMBRANA; RECEPTOR DE NEUROTRANSMISORES; RECEPTOR DE ACETILCOLINA; COLESTEROL; SEGUIMIENTO DE PARTÍCULAS INDIVIDUALES; MICROSCOPÍA DE SUPERRESOLUCIÓN | Fecha de publicación : | 2022 | Editorial : | Oxford University Press | Cita : | Buena Maizon, H., Barrantes, F. J. A deep learning-based approach to model anomalous diffusion of membrane proteins: the case of the nicotinic acetylcholine receptor [en línea]. Briefings in Bioinformatics. 2022, 23 (1). doi: https://doi.org/10.1093/bib/bbab435. Disponible en: https://repositorio.uca.edu.ar/handle/123456789/14114 | Resumen : | Abstract: We present a concatenated deep-learning multiple neural network system for the analysis of single-molecule trajectories. We apply this machine learning-based analysis to characterize the translational diffusion of the nicotinic acetylcholine receptor at the plasma membrane, experimentally interrogated using superresolution optical microscopy. The receptor protein displays a heterogeneous diffusion behavior that goes beyond the ensemble level, with individual trajectories exhibiting more than one diffusive state, requiring the optimization of the neural networks through a hyperparameter analysis for different numbers of steps and durations, especially for short trajectories (<50 steps) where the accuracy of the models is most sensitive to localization errors. We next use the statistical models to test for Brownian, continuous-time random walk and fractional Brownian motion, and introduce and implement an additional, two-state model combining Brownian walks and obstructed diffusion mechanisms, enabling us to partition the two-state trajectories into segments, each of which is independently subjected to multiple analysis. The concatenated multi-network system evaluates and selects those physical models that most accurately describe the receptor’s translational diffusion. We show that the two-state Brownian-obstructed diffusion model can account for the experimentally observed anomalous diffusion (mostly subdiffusive) of the population and the heterogeneous single-molecule behavior, accurately describing the majority (72.5 to 88.7% for α-bungarotoxin-labeled receptor and between 73.5 and 90.3% for antibody-labeled molecules) of the experimentally observed trajectories, with only ~15% of the trajectories fitting to the fractional Brownian motion model. | URI : | https://repositorio.uca.edu.ar/handle/123456789/14114 | ISSN : | 1477-4054 (online) | Disciplina: | MEDICINA | DOI: | 10.1093/bib/bbab435 | Derechos: | Acceso restringido |
Appears in Collections: | Artículos |
Files in This Item:
File | Description | Size | Format | Existent users please Login |
---|---|---|---|---|
deep-learning-based-approach.pdf | 4,6 MB | Adobe PDF | ???org.dspace.app.webui.jsptag.ItemTag.embargo??? Request a copy |
Page view(s)
83
checked on Apr 27, 2024
Download(s)
19
checked on Apr 27, 2024
Google ScholarTM
Check
Altmetric
This item is licensed under a Creative Commons License