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

By Tristan Bepler, Andrew Morin, M. Rapp, J. Brasch, L. Shapiro, A. Noble, Bonnie Berger. 2018

1,282 citations recorded by the source corpus.

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). The challenge of accurate particle picking in cryo-EM analysis is addressed with Topaz, a neural-network-based algorithm that shows advantages over other tools, especially in picking unusually shaped particles.

Subfields: Computational Theory and Mathematics, Molecular Biology, Structural Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

  1. Andrew Zisserman

In Molecular Biology

  1. Andrew Zisserman
  2. Xueming Li
  3. Li Fei-Fei
  4. Maria-Elena Nilsback

In Structural Biology

  1. Xueming Li

Citations in the corpus