Positive-unlabeled convolutional neural networks for particle picking in cryo-electron micrographs
Top Cited Papers
- 7 October 2019
- journal article
- research article
- Published by Springer Science and Business Media LLC in Nature Methods
- Vol. 16 (11), 1153-1160
- https://doi.org/10.1038/s41592-019-0575-8
Abstract
Cryo-electron microscopy is a popular method for the determination of protein structures; however, identifying a sufficient number of particles for analysis can take months of manual effort. Current computational approaches find many false positives and require ad hoc postprocessing, especially for unusually shaped particles. To address these shortcomings, we develop Topaz, an efficient and accurate particle-picking pipeline using neural networks trained with a general-purpose positive-unlabeled learning method. This framework enables particle detection models to be trained with few sparsely labeled particles and no labeled negatives. Topaz retrieves many more real particles than conventional picking methods while maintaining low false-positive rates, is capable of picking challenging unusually shaped proteins (for example, small, non-globular and asymmetric particles), produces more representative particle sets and does not require post hoc curation. We demonstrate the performance of Topaz on two difficult datasets and three conventional datasets. Topaz is modular, standalone, free and open source (http://topaz.csail.mit.edu).Keywords
Funding Information
- U.S. Department of Health & Human Services | National Institutes of Health (GM081871, R01-GM081871, MH114817, GM128303)
This publication has 38 references indexed in Scilit:
- Collaboration gets the most out of softwareeLife, 2013
- RELION: Implementation of a Bayesian approach to cryo-EM structure determinationJournal of Structural Biology, 2012
- DoG Picker and TiltPicker: Software tools to facilitate particle selection in single particle electron microscopyJournal of Structural Biology, 2009
- Appion: An integrated, database-driven pipeline to facilitate EM image processingJournal of Structural Biology, 2009
- EMAN2: An extensible image processing suite for electron microscopyJournal of Structural Biology, 2006
- Learning from Positive and Unlabeled Examples with Different Data DistributionsLecture Notes in Computer Science, 2005
- UCSF Chimera?A visualization system for exploratory research and analysisJournal of Computational Chemistry, 2004
- FindEM—a fast, efficient program for automatic selection of particles from electron micrographsJournal of Structural Biology, 2004
- Particle finding in electron micrographs using a fast local correlation algorithmUltramicroscopy, 2003
- Leginon: An Automated System for Acquisition of Images from Vitreous Ice SpecimensJournal of Structural Biology, 2000