Search for: All records

Abstract While critical to biological processes, molecular diffusion is difficult to quantify, and spatial mapping of local diffusivity is even more challenging. Here we report a machine-learning-enabled approach, pixels-to-diffusivity (Pix2D), to directly extract the diffusion coefficientDfrom single-molecule images, and consequently enable super-resolvedDspatial mapping. Working with single-molecule images recorded at a fixed framerate under typical single-molecule localization microscopy (SMLM) conditions, Pix2D exploits the often undesired yet evident motion blur,i.e., the convolution of single-molecule motion trajectory during the frame recording time with the diffraction-limited point spread function (PSF) of the microscope. Whereas the stochastic nature of diffusion imprints diverse diffusion trajectories to different molecules diffusing at the same givenD, we construct a convolutional neural network (CNN) model that takes a stack of single-molecule images as the input and evaluates aD-value as the output. We thus validate robustDevaluation and spatial mapping with simulated data, and with experimental data successfully characterizeDdifferences for supported lipid bilayers of different compositions and resolve gel and fluidic phases at the nanoscale.