Abstract
Particle identification and selection, which is a prerequisite for high-resolution structure determination of biological macromolecules via single-particle cryo-electron microscopy poses a major bottleneck for automating the steps of structure determination. Here, we present a generalized deep learning tool, CASSPER, for the automated detection and isolation of protein particles in transmission microscope images. This deep learning tool uses Semantic Segmentation and a collection of visually prepared training samples to capture the differences in the transmission intensities of protein, ice, carbon, and other impurities found in the micrograph. CASSPER is a semantic segmentation based method that does pixel-level classification and completely eliminates the need for manual particle picking. Integration of Contrast Limited Adaptive Histogram Equalization (CLAHE) in CASSPER enables high-fidelity particle detection in micrographs with variable ice thickness and contrast. A generalized CASSPER model works with high efficiency on unseen datasets and can potentially pick particles on-the-fly, enabling data processing automation.
Highlights
Particle identification and selection, which is a prerequisite for high-resolution structure determination of biological macromolecules via single-particle cryo-electron microscopy poses a major bottleneck for automating the steps of structure determination
Multiple Artificial intelligence/machine learning (AI/ML)-based methods have already been proposed, such as XMIPP21, APPLE picker[22], DeepPicker[23], DeepEM24, FastParticle Picker[25], crYOLO26, PIXER27, PARSED28, WARP29, Topaz[30], AutoCryoPicker[31], etc. that are based on Convolutional Neural Networks (CNN), region-based Convolutional Neural Networks (R-CNN), cross-correlation, and segmentation
In this study, we present a tool named CASSPER that can be used for automated particle picking from cryo-electron microscopy (cryo-EM) images
Summary
Particle identification and selection, which is a prerequisite for high-resolution structure determination of biological macromolecules via single-particle cryo-electron microscopy poses a major bottleneck for automating the steps of structure determination. DoGpicker[14] uses mathematically derived Gaussian functions as templates to recognize and select particles from the micrographs These tools are prone to pick huge amounts of contaminants, background, and ice, and do not work optimally for datasets with poor SNR or small particle sizes. These problems are resolved to a certain extent in template (reference)-based particle picking tools implemented in SIGNATURE15, RELION11, cryoSPARC12, EMAN8, SPHIRE16, cisTEM17, FindEM18, gEMpicker[19], SPIDER20, etc. In all these methods, templates are generated by manually picking a few hundred to several thousand particles from multiple micrographs. The exposure difference, noise level, and the variable ice thickness in micrographs limit the performance of automated particle picking tools
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.
