SPHIRE-crYOLO is a fast and accurate fully automated particle picker for cryo-EM

Thorsten Wagner(Max Planck Institute of Molecular Physiology), Felipe Merino(Max Planck Institute of Molecular Physiology), Markus Stabrin(Max Planck Institute of Molecular Physiology), Toshio Moriya(Max Planck Institute of Molecular Physiology), Claudia Antoni(Max Planck Institute of Molecular Physiology), Amir Apelbaum(Max Planck Institute of Molecular Physiology), Philine Hagel(Max Planck Institute of Molecular Physiology), Oleg Sitsel(Max Planck Institute of Molecular Physiology), Tobias Raisch(Max Planck Institute of Molecular Physiology), Daniel Prumbaum(Max Planck Institute of Molecular Physiology), Dennis Quentin(Max Planck Institute of Molecular Physiology), Daniel Roderer(Max Planck Institute of Molecular Physiology), Sebastian Tacke(Max Planck Institute of Molecular Physiology), Birte Siebolds(Max Planck Institute of Molecular Physiology), Evelyn Schubert(Max Planck Institute of Molecular Physiology), Tanvir R. Shaikh(Max Planck Institute of Molecular Physiology), Pascal Lill(Max Planck Institute of Molecular Physiology), Christos Gatsogiannis(Max Planck Institute of Molecular Physiology), Stefan Raunser(Max Planck Institute of Molecular Physiology)
Communications Biology
June 19, 2019
10.1038/s42003-019-0437-z
Cited by 1,444Open Access
Full Text

Abstract

Selecting particles from digital micrographs is an essential step in single-particle electron cryomicroscopy (cryo-EM). As manual selection of complete datasets-typically comprising thousands of particles-is a tedious and time-consuming process, numerous automatic particle pickers have been developed. However, non-ideal datasets pose a challenge to particle picking. Here we present the particle picking software crYOLO which is based on the deep-learning object detection system You Only Look Once (YOLO). After training the network with 200-2500 particles per dataset it automatically recognizes particles with high recall and precision while reaching a speed of up to five micrographs per second. Further, we present a general crYOLO network able to pick from previously unseen datasets, allowing for completely automated on-the-fly cryo-EM data preprocessing during data acquisition. crYOLO is available as a standalone program under http://sphire.mpg.de/ and is distributed as part of the image processing workflow in SPHIRE.

Related Papers

No related papers found

Powered by citation graph analysis