Temporal convolutional networks work as general feature extractors for single-particle diffusion analysis

The application of deep learning (DL) approaches to the study of particle diffusion is becoming increasingly widespread, achieving highly accurate predictive performance that is often challenging to attain with traditional analytical tools. DL has made successful incursions in the field of single-pa...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Saavedra, Lucas A., Barrantes, Francisco J.
Formato: Artículo
Lenguaje:Español
Publicado: IOP Publishing 2025
Materias:
APRENDIZAJE PROFUNDO
DIFUSION DE PARTICULAS
MODELOS DE SIMULACION
Acceso en línea:https://repositorio.uca.edu.ar/handle/123456789/20082
Aporte de:
Repositorio Institucional de la Universidad Católica Argentina (UCA) de Universidad Católica Argentina
id I33-R139-123456789-20082
record_format dspace
spelling I33-R139-123456789-200822025-07-11T05:02:38Z Temporal convolutional networks work as general feature extractors for single-particle diffusion analysis Saavedra, Lucas A. Barrantes, Francisco J. APRENDIZAJE PROFUNDO DIFUSION DE PARTICULAS MODELOS DE SIMULACION The application of deep learning (DL) approaches to the study of particle diffusion is becoming increasingly widespread, achieving highly accurate predictive performance that is often challenging to attain with traditional analytical tools. DL has made successful incursions in the field of single-particle tracking of biological molecules in 2- and 3-dimensional spaces. In this work, we introduce a WaveNet-based deep neural network (WadNet)- and convolution-based DL network coined Wad temporal convolutional networks (WadTCN) and its transformer-based variant to decode single-value or pointwise prediction of dynamic properties of bidimensional trajectories. We trained WadTCN to be tested in all 1st and 2nd Andi Challenge tasks with bidimensional trajectories, examined how WadTCN performed when learning is transferred from one network to another to accelerate training, and evaluated its capacity to segment trajectories with a data-driven approach, at variance with other works that rely on mean changes or parameter thresholding to determine change points. WadTCN was further compared to a pure temporal convolutional network and RANDI, a top-performing recurrent neural network in the 1st Andi Challenge. We also assessed the ability of WadTCN to classify and segment single-particle trajectories of a membrane-associated protein, the nicotinic acetylcholine receptor, in the plane of a live cell plasma membrane. WadTCN outperformed similar analytical tools in predicting anomalous diffusion exponents and demonstrated notable robustness in more challenging tasks like the segmentation of trajectories into two states and prediction of the diffusion coefficient of diffusing molecules. Furthermore, most layers of WadTCN perform as general feature extractors, suggesting its applicability in other tasks requiring training acceleration. 2025-07-10T17:38:52Z 2025-07-10T17:38:52Z 2025 Artículo 2515-7647 https://repositorio.uca.edu.ar/handle/123456789/20082 10.1088/2515-7647/adbec8 spa Atribución-NoComercial-CompartirIgual 4.0 Internacional http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf IOP Publishing JPhys Photonics. 7, 2025.
institution Universidad Católica Argentina
institution_str I-33
repository_str R-139
collection Repositorio Institucional de la Universidad Católica Argentina (UCA)
language Español
topic APRENDIZAJE PROFUNDO
DIFUSION DE PARTICULAS
MODELOS DE SIMULACION
spellingShingle APRENDIZAJE PROFUNDO
DIFUSION DE PARTICULAS
MODELOS DE SIMULACION
Saavedra, Lucas A.
Barrantes, Francisco J.
Temporal convolutional networks work as general feature extractors for single-particle diffusion analysis
topic_facet APRENDIZAJE PROFUNDO
DIFUSION DE PARTICULAS
MODELOS DE SIMULACION
description The application of deep learning (DL) approaches to the study of particle diffusion is becoming increasingly widespread, achieving highly accurate predictive performance that is often challenging to attain with traditional analytical tools. DL has made successful incursions in the field of single-particle tracking of biological molecules in 2- and 3-dimensional spaces. In this work, we introduce a WaveNet-based deep neural network (WadNet)- and convolution-based DL network coined Wad temporal convolutional networks (WadTCN) and its transformer-based variant to decode single-value or pointwise prediction of dynamic properties of bidimensional trajectories. We trained WadTCN to be tested in all 1st and 2nd Andi Challenge tasks with bidimensional trajectories, examined how WadTCN performed when learning is transferred from one network to another to accelerate training, and evaluated its capacity to segment trajectories with a data-driven approach, at variance with other works that rely on mean changes or parameter thresholding to determine change points. WadTCN was further compared to a pure temporal convolutional network and RANDI, a top-performing recurrent neural network in the 1st Andi Challenge. We also assessed the ability of WadTCN to classify and segment single-particle trajectories of a membrane-associated protein, the nicotinic acetylcholine receptor, in the plane of a live cell plasma membrane. WadTCN outperformed similar analytical tools in predicting anomalous diffusion exponents and demonstrated notable robustness in more challenging tasks like the segmentation of trajectories into two states and prediction of the diffusion coefficient of diffusing molecules. Furthermore, most layers of WadTCN perform as general feature extractors, suggesting its applicability in other tasks requiring training acceleration.
format Artículo
author Saavedra, Lucas A.
Barrantes, Francisco J.
author_facet Saavedra, Lucas A.
Barrantes, Francisco J.
author_sort Saavedra, Lucas A.
title Temporal convolutional networks work as general feature extractors for single-particle diffusion analysis
title_short Temporal convolutional networks work as general feature extractors for single-particle diffusion analysis
title_full Temporal convolutional networks work as general feature extractors for single-particle diffusion analysis
title_fullStr Temporal convolutional networks work as general feature extractors for single-particle diffusion analysis
title_full_unstemmed Temporal convolutional networks work as general feature extractors for single-particle diffusion analysis
title_sort temporal convolutional networks work as general feature extractors for single-particle diffusion analysis
publisher IOP Publishing
publishDate 2025
url https://repositorio.uca.edu.ar/handle/123456789/20082
work_keys_str_mv AT saavedralucasa temporalconvolutionalnetworksworkasgeneralfeatureextractorsforsingleparticlediffusionanalysis
AT barrantesfranciscoj temporalconvolutionalnetworksworkasgeneralfeatureextractorsforsingleparticlediffusionanalysis
_version_ 1845297959323828224

Ejemplares similares