Abstract
Quantifying the extent to which points are clustered in single-molecule localization microscopy data is vital to understanding the spatial relationships between molecules in the underlying sample. Many existing computational approaches are limited in their ability to process large-scale data sets, to deal effectively with sample heterogeneity, or require subjective user-defined analysis parameters. Here, we develop a supervised machine-learning approach to cluster analysis which is fast and accurate. Trained on a variety of simulated clustered data, the neural network can classify millions of points from a typical single-molecule localization microscopy data set, with the potential to include additional classifiers to describe different subtypes of clusters. The output can be further refined for the measurement of cluster area, shape, and point-density. We demonstrate this approach on simulated data and experimental data of the kinase Csk and the adaptor PAG in primary human T cell immunological synapses.
Highlights
Quantifying the extent to which points are clustered in single-molecule localization microscopy data is vital to understanding the spatial relationships between molecules in the underlying sample
Whereas images from wide-field or confocal microscopes are composed of arrays of pixels, the data from SMLM1,2 are fundamentally a list of coordinates, each representing the spatial location of a point-emitter
Common among many of these approaches is the selection of analysis parameters, which can lead to a suboptimal interpretation of the data, for example, when points are clustered at a different spatial scale to the one used for assessment or when points are not homogeneously clustered
Summary
Quantifying the extent to which points are clustered in single-molecule localization microscopy data is vital to understanding the spatial relationships between molecules in the underlying sample. Whereas images from wide-field or confocal microscopes are composed of arrays of pixels, the data from SMLM1,2 are fundamentally a list of coordinates, each representing the spatial location of a point-emitter This list can be plotted and rasterized for examination with conventional image analysis tools, but an ideal method would operate on the original coordinate data without requiring its transformation. Common among many of these approaches is the selection of analysis parameters, which can lead to a suboptimal interpretation of the data, for example, when points are clustered at a different spatial scale to the one used for assessment or when points are not homogeneously clustered These situations are common in the case of complex data from biological specimens. These artifacts should be corrected for beforehand, or the results interpreted in their context
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
