National Institutes of Health/National Institute of General Medical Sciences (NIH/NIGMS)
R01-GM081871
米国
National Institutes of Health/National Institute of Mental Health (NIH/NIMH)
R01-MH114817
米国
National Science Foundation (NSF, United States)
DGE-1644869
米国
Other private
Simons Foundation / SF349247
米国
National Institutes of Health/National Institute of General Medical Sciences (NIH/NIGMS)
F32GM128303
米国
National Institutes of Health/National Institute of General Medical Sciences (NIH/NIGMS)
GM103310
米国
Other government
New York State Office of Science, Technology and Academic Research (NYSTAR)
米国
National Institutes of Health/Office of the Director
OD019994
米国
Other private
Agouron Institute / F00316
米国
引用
ジャーナル: Nat Methods / 年: 2019 タイトル: Positive-unlabeled convolutional neural networks for particle picking in cryo-electron micrographs. 著者: Tristan Bepler / Andrew Morin / Micah Rapp / Julia Brasch / Lawrence Shapiro / Alex J Noble / Bonnie Berger / 要旨: 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 ...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 ).
EMPIAR-10215 (タイトル: Rabbit muscle aldolase single particle cryoEM / Data size: 1.4 TB Data #1: Micrographs along with all other magnification images from the collection [micrographs - single frame] Data #2: Micrograph frames [micrographs - multiframe] Data #3: CryoEM structures in the paper [picked particles - single frame - unprocessed])