Format

Send to

Choose Destination
Nat Methods. 2019 Nov;16(11):1153-1160. doi: 10.1038/s41592-019-0575-8. Epub 2019 Oct 7.

Positive-unlabeled convolutional neural networks for particle picking in cryo-electron micrographs.

Author information

1
Computational and Systems Biology, MIT, Cambridge, MA, USA.
2
Computer Science and Artificial Intelligence Laboratory, MIT, Cambridge, MA, USA.
3
Department of Mathematics, MIT, Cambridge, MA, USA.
4
Department of Biochemistry and Molecular Biophysics, Mortimer B. Zuckerman Mind Brain Behavior Institute, Columbia University, New York, NY, USA.
5
National Resource for Automated Molecular Microscopy, Simons Electron Microscopy Center, New York Structural Biology Center, New York, NY, USA.
6
National Resource for Automated Molecular Microscopy, Simons Electron Microscopy Center, New York Structural Biology Center, New York, NY, USA. anoble@nysbc.org.
7
Computer Science and Artificial Intelligence Laboratory, MIT, Cambridge, MA, USA. bab@mit.edu.
8
Department of Mathematics, MIT, Cambridge, MA, USA. bab@mit.edu.

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 ).

PMID:
31591578
PMCID:
PMC6858545
[Available on 2020-04-07]
DOI:
10.1038/s41592-019-0575-8

Supplemental Content

Full text links

Icon for Nature Publishing Group
Loading ...
Support Center