Cargando…

DeepCentering: fully automated crystal centering using deep learning for macromolecular crystallography

High-throughput protein crystallography using a synchrotron light source is an important method used in drug discovery. Beamline components for automated experiments including automatic sample changers have been utilized to accelerate the measurement of a number of macromolecular crystals. However,...

Descripción completa

Detalles Bibliográficos
Autores principales: Ito, Sho, Ueno, Go, Yamamoto, Masaki
Formato: Online Artículo Texto
Lenguaje:English
Publicado: International Union of Crystallography 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6613109/
https://www.ncbi.nlm.nih.gov/pubmed/31274465
http://dx.doi.org/10.1107/S160057751900434X
_version_ 1783432996259364864
author Ito, Sho
Ueno, Go
Yamamoto, Masaki
author_facet Ito, Sho
Ueno, Go
Yamamoto, Masaki
author_sort Ito, Sho
collection PubMed
description High-throughput protein crystallography using a synchrotron light source is an important method used in drug discovery. Beamline components for automated experiments including automatic sample changers have been utilized to accelerate the measurement of a number of macromolecular crystals. However, unlike cryo-loop centering, crystal centering involving automated crystal detection is a difficult process to automate fully. Here, DeepCentering, a new automated crystal centering system, is presented. DeepCentering works using a convolutional neural network, which is a deep learning operation. This system achieves fully automated accurate crystal centering without using X-ray irradiation of crystals, and can be used for fully automated data collection in high-throughput macromolecular crystallography.
format Online
Article
Text
id pubmed-6613109
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher International Union of Crystallography
record_format MEDLINE/PubMed
spelling pubmed-66131092019-07-17 DeepCentering: fully automated crystal centering using deep learning for macromolecular crystallography Ito, Sho Ueno, Go Yamamoto, Masaki J Synchrotron Radiat Short Communications High-throughput protein crystallography using a synchrotron light source is an important method used in drug discovery. Beamline components for automated experiments including automatic sample changers have been utilized to accelerate the measurement of a number of macromolecular crystals. However, unlike cryo-loop centering, crystal centering involving automated crystal detection is a difficult process to automate fully. Here, DeepCentering, a new automated crystal centering system, is presented. DeepCentering works using a convolutional neural network, which is a deep learning operation. This system achieves fully automated accurate crystal centering without using X-ray irradiation of crystals, and can be used for fully automated data collection in high-throughput macromolecular crystallography. International Union of Crystallography 2019-06-03 /pmc/articles/PMC6613109/ /pubmed/31274465 http://dx.doi.org/10.1107/S160057751900434X Text en © Ito, Ueno and Yamamoto 2019 http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution (CC-BY) Licence, which permits unrestricted use, distribution, and reproduction in any medium, provided the original authors and source are cited.http://creativecommons.org/licenses/by/4.0/
spellingShingle Short Communications
Ito, Sho
Ueno, Go
Yamamoto, Masaki
DeepCentering: fully automated crystal centering using deep learning for macromolecular crystallography
title DeepCentering: fully automated crystal centering using deep learning for macromolecular crystallography
title_full DeepCentering: fully automated crystal centering using deep learning for macromolecular crystallography
title_fullStr DeepCentering: fully automated crystal centering using deep learning for macromolecular crystallography
title_full_unstemmed DeepCentering: fully automated crystal centering using deep learning for macromolecular crystallography
title_short DeepCentering: fully automated crystal centering using deep learning for macromolecular crystallography
title_sort deepcentering: fully automated crystal centering using deep learning for macromolecular crystallography
topic Short Communications
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6613109/
https://www.ncbi.nlm.nih.gov/pubmed/31274465
http://dx.doi.org/10.1107/S160057751900434X
work_keys_str_mv AT itosho deepcenteringfullyautomatedcrystalcenteringusingdeeplearningformacromolecularcrystallography
AT uenogo deepcenteringfullyautomatedcrystalcenteringusingdeeplearningformacromolecularcrystallography
AT yamamotomasaki deepcenteringfullyautomatedcrystalcenteringusingdeeplearningformacromolecularcrystallography