skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.


Title: Intelligent fluorescence image analysis of giant unilamellar vesicles using convolutional neural network
Abstract Background Fluorescence image analysis in biochemical science often involves the complex tasks of identifying samples for analysis and calculating the desired information from the intensity traces. Analyzing giant unilamellar vesicles (GUVs) is one of these tasks. Researchers need to identify many vesicles to statistically analyze the degree of molecular interaction or state of molecular organization on the membranes. This analysis is complicated, requiring a careful manual examination by researchers, so automating the analysis can significantly aid in improving its efficiency and reliability. Results We developed a convolutional neural network (CNN) assisted intelligent analysis routine based on the whole 3D z-stack images. The programs identify the vesicles with desired morphology and analyzes the data automatically. The programs can perform protein binding analysis on the membranes or state decision analysis of domain phase separation. We also show that the method can easily be applied to similar problems, such as intensity analysis of phase-separated protein droplets. CNN-based classification approach enables the identification of vesicles even from relatively complex samples. We demonstrate that the proposed artificial intelligence-assisted classification can further enhance the accuracy of the analysis close to the performance of manual examination in vesicle selection and vesicle state determination analysis. Conclusions We developed a MATLAB based software capable of efficiently analyzing confocal fluorescence image data of giant unilamellar vesicles. The program can automatically identify GUVs with desired morphology and perform intensity-based calculation and state decision for each vesicle. We expect our method of CNN implementation can be expanded and applied to many similar problems in image data analysis.  more » « less
Award ID(s):
2117308
PAR ID:
10332949
Author(s) / Creator(s):
; ; ; ;
Date Published:
Journal Name:
BMC Bioinformatics
Volume:
23
Issue:
1
ISSN:
1471-2105
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. null (Ed.)
    Building upon our previous studies on interactions of amphiphilic Janus nanoparticles with glass-supported lipid bilayers, we study here how these Janus nanoparticles perturb the structural integrity and induce shape instabilities of membranes of giant unilamellar vesicles (GUVs). We show that 100 nm amphiphilic Janus nanoparticles disrupt GUV membranes at a threshold particle concentration similar to that in supported lipid bilayers, but cause drastically different membrane deformations, including membrane wrinkling, protrusion, poration, and even collapse of entire vesicles. By combining experiments with molecular simulations, we reveal how Janus nanoparticles alter local membrane curvature and collectively compress the membrane to induce shape transformation of vesicles. Our study demonstrates that amphiphilic Janus nanoparticles disrupt vesicle membranes differently and more effectively than uniform amphiphilic particles. 
    more » « less
  2. Abstract The cyanobacterial circadian clock maintains remarkable precision and synchrony, even in cells with femtoliter volumes. Here, we reconstitute the KaiABC post-translational oscillator (PTO) in giant unilamellar vesicles (GUVs) to investigate underlying mechanisms of this fidelity. We show that our encapsulation methodology replicates native protein variability. With long-term, single-vesicle tracking of circadian rhythms using fluorescent KaiB and confocal microscopy, we find that oscillator fidelity decreases with lower protein levels and smaller vesicle sizes. KaiB membrane association, observed in cyanobacteria, was recapitulated in GUV membranes. A mathematical model incorporating protein stoichiometry limitations suggests that high expression of PTO components and associated regulators (CikA and SasA) buffers stochastic variations in protein levels. Additionally, while the transcription-translation feedback loop contributes minimally to overall fidelity, it is essential for maintaining phase synchrony. These findings demonstrate synthetic cells capable of autonomous circadian rhythms and highlight a generalizable strategy for dissecting emergent biological behavior using minimal systems. 
    more » « less
  3. Understanding how soft matter deforms in response to mechanical interactions is central to the design of functional synthetic materials as well as elucidation of the behaviors of biological assemblies. Here we explore how cycles of thermally induced transitions between nematic (N) and isotropic (I) phases can be used to exert cyclical elastic stresses on dispersions of giant unilamellar vesicles (GUVs) and thereby evolve GUV shape and properties. The measurements were enabled by the finding that I–N–I phase transitions of the lyotropic chromonic liquid crystal disodium cromoglycate, when conducted via an intermediate columnar (M) phase, minimized transport of GUVs on phase fronts to confining surfaces. Whereas I to N phase transitions strained spherical GUVs into spindle-like shapes, with an efflux of GUV internal volume, subsequent N to I transitions generated a range of complex GUV shapes, including stomatocyte, pear- and dumbbell-like shapes that depended on the extent of strain in the N phase. The highest strained GUVs were observed to form buds (daughter vesicles) that we show, via a cycle of I–N–I–N phase transitions, are connected via a neck to the parent vesicle. Additional experiments established that changes in elasticity of the phase surrounding the GUVs and not thermal expansion of membranes were responsible for the shape transitions, and that I–N–I transformations that generate stomatocytes can be understood from the Bilayer-Coupling model of GUV shapes. Overall, these observations advance our understanding of how LC elastic stresses can be regulated to evolve the shapes of soft biological assemblies as well as provide new approaches for engineering synthetic soft matter. 
    more » « less
  4. A widely used method to measure the bending rigidity of bilayer membranes is fluctuation spectroscopy, which analyses the thermally-driven membrane undulations of giant unilamellar vesicles recorded with either phase-contrast or confocal microscopy. Here, we analyze the fluctuations of the same vesicle using both techniques and obtain consistent values for the bending modulus. We discuss the factors that may lead to discrepancies. 
    more » « less
  5. Motivation Giant unilamellar vesicles (GUVs), cell-like synthetic micrometer size structures, assemble when thin lipid films are hydrated in aqueous solutions. Quantitative measurements of static yields and distribution of sizes of GUVs obtained from thin film hydration methods were recently reported. Dynamic data such as the time evolution of yields and distribution of sizes, however, is not known. Dynamic data can provide insights into the assembly pathway of GUVs and guidelines for choosing conditions to obtain populations with desired size distributions. Approach We develop the ‘stopped-time’ technique to characterize the time evolution of the distribution of sizes and molar yields of populations of free-floating GUVs. We additionally capture high resolution time-lapse images of surface-attached GUV buds on the lipid films. We systematically study the dynamics of assembly of GUVs from three widely used thin film hydration methods, PAPYRUS (Paper-Abetted amPhiphile hYdRation in aqUeous Solutions), gentle hydration, and electroformation. Findings We find that the molar yield versus time curves of GUVs demonstrate a characteristic sigmoidal shape, with an initial yield, a transient, and then a steady state plateau for all three methods. The population of GUVs showed a right-skewed distribution of diameters. The variance of the distributions increased with time. The systems reached steady state within 120 min. We rationalize the dynamics using the thermodynamically motivated budding and merging (BNM) model. These results further the understanding of lipid dynamics and provide for the first-time practical parameters to tailor the production of GUVs of specific sizes for applications. 
    more » « less