Damodar, P. | Search bioRxiv

bioRxiv2025

CryoSift - An accessible and automated CNN-driven tool for cryo-EM 2D class selection

Single-particle cryo-electron microscopy (cryo-EM) has become an essential tool in structural biology. However, automating repetitive tasks remains an ongoing challenge in cryo-EM dataset processing. Here, we present a platform-independent convolutional neural network (CNN) tool for assessing the quality of 2D averages to enable automatic selection of suitable particles for high-resolution reconstructions, termed CryoSift. We integrate CryoSift into a fully automated processing pipeline using the existing cryosparc-tools library. Our integrated and customizable 2D assessment workflow enables high-throughput processing that accommodates experienced to novice cryo-EM users. O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=183 SRC="FIGDIR/small/667259v2_ufig1.gif" ALT="Figure 1"> View larger version (57K): org.highwire.dtl.DTLVardef@1fdac98org.highwire.dtl.DTLVardef@14e3c7corg.highwire.dtl.DTLVardef@16520bforg.highwire.dtl.DTLVardef@48fa0f_HPS_FORMAT_FIGEXP M_FIG C_FIG

bioinformatics↗

bioRxiv2025

Magellon - an extensible platform for cryo-EM data visualization, management, and processing

Single particle cryo-electron microscopy (cryo-EM) has revolutionized structural biology by enabling high-resolution determination of macromolecular structures. However, the field faces challenges in data management, processing workflow integration, and software extensibility. We present Magellon, an innovative cryo-EM software platform that addresses these challenges through a modern microservices architecture. Magellon consists of an extensible backend with a web-based front end that we call Magellon Viewer. Together, these combine high-performance computing capabilities with an intuitive user interface, enabling researchers to efficiently process and analyze cryo-EM data. The platforms distinguishing features include a plugin-based architecture, distributed processing capabilities, comprehensive monitoring systems, and a novel approach to data organization and visualization. A key philosophy of the approach is that the Magellon backend provides a platform that uses robust industry-standard libraries to orchestrate computational tasks while offering users and developers flexibility in selecting the computational resources for performing calculations. Magellon represents a significant advancement in cryo-EM software infrastructure, offering flexibility, scalability, and extensibility while maintaining ease of use.

biophysics↗