Pointwise prediction of protein diffusive properties using machine learning

The understanding of cellular mechanisms benefits substantially from accurate determination of protein diffusive properties. Prior work in this field primarily focuses on traditional methods, such as mean square displacements, for calculation of protein diffusion coefficients and biological states....

Full description

Saved in:
Bibliographic Details
Main Authors: Rasched Haidari, Achillefs N Kapanidis
Format: Article
Language:English
Published: IOP Publishing 2025-01-01
Series:JPhys Photonics
Subjects:
Online Access:https://doi.org/10.1088/2515-7647/adede9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849423501871546368
author Rasched Haidari
Achillefs N Kapanidis
author_facet Rasched Haidari
Achillefs N Kapanidis
author_sort Rasched Haidari
collection DOAJ
description The understanding of cellular mechanisms benefits substantially from accurate determination of protein diffusive properties. Prior work in this field primarily focuses on traditional methods, such as mean square displacements, for calculation of protein diffusion coefficients and biological states. This proves difficult and error-prone for proteins undergoing heterogeneous behaviour, particularly in complex environments, limiting the exploration of new biological behaviours. The importance of determining protein diffusion coefficients, anomalous exponents, and biological behaviours led to the Anomalous Diffusion Challenge 2024, exploring machine learning methods to infer these variables in heterogeneous trajectories with time-dependent changepoints. In response to the challenge, we present M3, a machine learning method for pointwise inference of diffusive coefficients, anomalous exponents, and states along noisy heterogenous protein trajectories. M3 makes use of long short-term memory cells to achieve small mean absolute errors for the diffusion coefficient and anomalous exponent alongside high state accuracies (>90%). Subsequently, we implement changepoint detection to determine timepoints at which protein behaviour changes. M3 removes the need for expert fine-tuning required in most conventional statistical methods while being computationally inexpensive to train. The model finished in the Top 5 of the Anomalous Diffusive Challenge 2024, with small improvements made since challenge closure.
format Article
id doaj-art-108f3f62e3b545248b2b8502fcab653d
institution Kabale University
issn 2515-7647
language English
publishDate 2025-01-01
publisher IOP Publishing
record_format Article
series JPhys Photonics
spelling doaj-art-108f3f62e3b545248b2b8502fcab653d2025-08-20T03:30:33ZengIOP PublishingJPhys Photonics2515-76472025-01-017303502510.1088/2515-7647/adede9Pointwise prediction of protein diffusive properties using machine learningRasched Haidari0https://orcid.org/0009-0003-2371-7397Achillefs N Kapanidis1https://orcid.org/0000-0001-6699-136XGene Machines Group, Clarendon Laboratory, Department of Physics, University of Oxford , Oxford, United Kingdom; Kavli Institute of Nanoscience Discovery, Dorothy Crowfoot Hodgkin Building, University of Oxford , Oxford, United KingdomGene Machines Group, Clarendon Laboratory, Department of Physics, University of Oxford , Oxford, United Kingdom; Kavli Institute of Nanoscience Discovery, Dorothy Crowfoot Hodgkin Building, University of Oxford , Oxford, United KingdomThe understanding of cellular mechanisms benefits substantially from accurate determination of protein diffusive properties. Prior work in this field primarily focuses on traditional methods, such as mean square displacements, for calculation of protein diffusion coefficients and biological states. This proves difficult and error-prone for proteins undergoing heterogeneous behaviour, particularly in complex environments, limiting the exploration of new biological behaviours. The importance of determining protein diffusion coefficients, anomalous exponents, and biological behaviours led to the Anomalous Diffusion Challenge 2024, exploring machine learning methods to infer these variables in heterogeneous trajectories with time-dependent changepoints. In response to the challenge, we present M3, a machine learning method for pointwise inference of diffusive coefficients, anomalous exponents, and states along noisy heterogenous protein trajectories. M3 makes use of long short-term memory cells to achieve small mean absolute errors for the diffusion coefficient and anomalous exponent alongside high state accuracies (>90%). Subsequently, we implement changepoint detection to determine timepoints at which protein behaviour changes. M3 removes the need for expert fine-tuning required in most conventional statistical methods while being computationally inexpensive to train. The model finished in the Top 5 of the Anomalous Diffusive Challenge 2024, with small improvements made since challenge closure.https://doi.org/10.1088/2515-7647/adede9anomalous diffusionpointwise inferencediffusionAnDi2 challengemachine learningLSTM
spellingShingle Rasched Haidari
Achillefs N Kapanidis
Pointwise prediction of protein diffusive properties using machine learning
JPhys Photonics
anomalous diffusion
pointwise inference
diffusion
AnDi2 challenge
machine learning
LSTM
title Pointwise prediction of protein diffusive properties using machine learning
title_full Pointwise prediction of protein diffusive properties using machine learning
title_fullStr Pointwise prediction of protein diffusive properties using machine learning
title_full_unstemmed Pointwise prediction of protein diffusive properties using machine learning
title_short Pointwise prediction of protein diffusive properties using machine learning
title_sort pointwise prediction of protein diffusive properties using machine learning
topic anomalous diffusion
pointwise inference
diffusion
AnDi2 challenge
machine learning
LSTM
url https://doi.org/10.1088/2515-7647/adede9
work_keys_str_mv AT raschedhaidari pointwisepredictionofproteindiffusivepropertiesusingmachinelearning
AT achillefsnkapanidis pointwisepredictionofproteindiffusivepropertiesusingmachinelearning