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

By T. Wagner, F. Merino, M. Stabrin, T. Moriya, C. Antoni, Amir Apelbaum, Philine Hagel, Oleg Sitsel, T. Raisch, Daniel Prumbaum and 9 more. 2019

986 citations recorded by the source corpus.

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. Thorsten Wagner et al. present SPHIRE-crYOLO, a particle picking software for selecting particles from digital micrographs in cryoEM data. After training, the method automatically recognizes particles with high recall and precision, simplifying data pre-processing.

Subfields: Pediatrics, Perinatology and Child Health, Structural Biology, Surfaces, Coatings and Films

How researchers see this paper

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

In Structural Biology

1. J. M. Carazo
2. Carlos Oscar Sánchez Sorzano
3. Sjors H. W. Scheres

In Surfaces, Coatings and Films

1. Carlos Oscar Sánchez Sorzano
2. Sjors H. W. Scheres

Citations in the corpus

• Isotropic reconstruction for electron tomography with deep learning (2022, methodology): “Deep learning was also applied to cryoET tomograms for denoising 27 – 29 , particle picking 30,31 , classi fi cation 32,33 , and segmentation 34,35 , accelerating the interpretation and analysis of the tomograms.”
• Moyamoya disease factor RNF213 is a giant E3 ligase with a dynein-like core and a distinct ubiquitin-transfer mechanism (2020, methodology): “1 (Wagner et al., 2019) using YOLO architecture with 3 3 patches per micrograph.”
• DeepEMhancer: a deep learning solution for cryo-EM volume post-processing (2020, methodology): “As in most of those methods, our approach relies on a convolutional neural network (CNN) that is trained on massive quantities of data.”