Automatic detection of diffusion modes within biological membranes using back-propagation neural network

Dosset, Patrice; Rassam, Patrice; Fernandez, Laurent; Espenel, Cédric; Rubinstein, Eric; Margeat, Emmanuel; Milhiet, Pierre-Emmanuel

doi:10.1186/s12859-016-1064-z

Cited by 64 publications

(58 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…At least ten different fields of view were imaged for each condition. Single particle tracking videos were analysed using PaTrack software and the previously described parameters for trajectory inclusion criteria and determination of motional modes (Brownian, confined or directed) [44]. …”

Section: Methodsmentioning

confidence: 99%

Tetraspanin Tspan9 regulates platelet collagen receptor GPVI lateral diffusion and activation

et al. 2016

Self Cite

View full text Add to dashboard Cite

The tetraspanins are a superfamily of four-transmembrane proteins, which regulate the trafficking, lateral diffusion and clustering of the transmembrane proteins with which they interact. We have previously shown that tetraspanin Tspan9 is expressed on platelets. Here we have characterised gene-trap mice lacking Tspan9. The mice were viable with normal platelet numbers and size. Tspan9-deficient platelets were specifically defective in aggregation and secretion induced by the platelet collagen receptor GPVI, despite normal surface GPVI expression levels. A GPVI activation defect was suggested by partially impaired GPVI-induced protein tyrosine phosphorylation. In mechanistic experiments, Tspan9 and GPVI co-immunoprecipitated and co-localised, but super-resolution imaging revealed no defects in collagen-induced GPVI clustering on Tspan9-deficient platelets. However, single particle tracking using total internal reflection fluorescence microscopy showed that GPVI lateral diffusion was reduced by approximately 50% in the absence of Tspan9. Therefore, Tspan9 plays a fine-tuning role in platelet activation by regulating GPVI membrane dynamics.

show abstract

Section: Methodsmentioning

confidence: 99%

Tetraspanin Tspan9 regulates platelet collagen receptor GPVI lateral diffusion and activation

et al. 2016

Self Cite

View full text Add to dashboard Cite

show abstract

“…The method uses a rolling window to analyze a trajectory and classifies the trajectory segment in each window into different modes of motion based on a set of empirical rules regarding the apparent diffusion coefficient, the mean-squared deviation, and the asymmetry of the displacement distribution. Several other methods based on feature parameter classification were also reported (26)(27)(28). The statistics foundation for such classification schemes, however, is unclear.…”

Section: Introductionmentioning

confidence: 99%

Detection of Velocity and Diffusion Coefficient Change Points in Single-Particle Trajectories

Yin

Song

Yang

2018

Biophysical Journal

View full text Add to dashboard Cite

The position-time trajectory of a biological subject moving in a complex environment contains rich information about how it interacts with the local setting. Whether the subject be an animal or an intracellular endosomal vesicle, the two primary modes of biological locomotion are directional movement and random walk, respectively characterized by velocity and diffusion coefficient. This contribution introduces a method to quantitatively divide a single-particle trajectory into segments that exhibit changes in the diffusion coefficient, velocity, or both. With the determination of these two physical parameters given by the maximum likelihood estimators, the relative precisions are given as explicit functions of the number of data points and total trajectory time. The method is based on rigorous statistical tests and does not require any presumed kinetics scheme. Results of extensive characterizations, extensions to 2D and 3D trajectories, and applications to common scenarios are also discussed.

show abstract

“…The values of exponent provided by the RF algorithm are schematically represented by the dashed lines, and are in good agreement with the ground truth values, which for the CTRW were also calculated by the eMSD (dotted lines). discriminate among confined, anomalous, normal or directed motion [28,29], without extracting quantitative information of classifying with respect to the underlying physical model. This paper presents a machine learning algorithm based on the Random forest (RF) architecture that efficiently and robustly characterizes single trajectories at different levels: first, obtaining the discrimination among several diffusion models; then, providing the estimation of the exponent that characterizes the anomalous diffusion, thus inherently classifying between normal and anomalous (suband super-) diffusion.…”

mentioning

confidence: 99%

Single trajectory characterization via machine learning

et al. 2020

View full text Add to dashboard Cite

In order to study transport in complex environments, it is extremely important to determine the physical mechanism underlying diffusion and precisely characterize its nature and parameters. Often, this task is strongly impacted by data consisting of trajectories with short length (either due to brief recordings or previous trajectory segmentation) and limited localization precision. In this paper, we propose a machine learning method based on a random forest architecture, which is able to associate single trajectories to the underlying diffusion mechanism with high accuracy. In addition, the algorithm is able to determine the anomalous exponent with a small error, thus inherently providing a classification of the motion as normal or anomalous (subor super-diffusion). The method provides highly accurate outputs even when working with very short trajectories and in the presence of experimental noise. We further demonstrate the application of transfer learning to experimental and simulated data not included in the training/test dataset. This allows for a full, high-accuracy characterization of experimental trajectories without the need of any prior information.In the last decades, the research in biophysics has conveyed large efforts toward the development of experimental techniques allowing the visualization of biological processes one molecule at a time [1-4]. These efforts have been mainly driven by the concept that ensemble-averaging hides important features that are relevant for cellular function. Somehow expectedly, experiments performed by means of these techniques have shown a large heterogeneity in the behavior of biological molecules, thus fully justifying the use of these raffinate tools.Besides, experiments performed using single particle tracking [3] have revealed that even chemically-identical molecules in biological media can display very different behaviors, as a consequence of the complex environment where diffusion takes place. By way of example, this heterogeneity is reflected in the broad distribution of dynamic parameters of distinct individual trajectories corresponding to the same molecular species, such as the diffusion coefficient, well above stochastic indetermination. Typically, the trajectories are analyzed by quantifying the (time-averaged) mean square displacement (tMSD) as a function of the time lag τ [5]:The calculation of this quantity-expected to scale linearly for a Brownian walker in a homogeneous environment-has provided a ubiquitous evidence of anomalous behaviors in biological systems, characterized by an asymptotic nonlinear scaling of the tMSD curve d t a 2. More experiments have shown that the anomalous exponent can vary from particle to particle ( figure 1(a)) as a consequence of molecular interactions and that these changes can be experienced by the same particle in space/time [6]. Several methods have been OPEN ACCESS RECEIVED

show abstract

Automatic detection of diffusion modes within biological membranes using back-propagation neural network

Cited by 64 publications

References 38 publications

Tetraspanin Tspan9 regulates platelet collagen receptor GPVI lateral diffusion and activation

Tetraspanin Tspan9 regulates platelet collagen receptor GPVI lateral diffusion and activation

Detection of Velocity and Diffusion Coefficient Change Points in Single-Particle Trajectories

Single trajectory characterization via machine learning

Contact Info

Product

Resources

About