skip to main content

DOE PAGESDOE PAGES

Title: A convolutional neural network-based screening tool for X-ray serial crystallography

A new tool is introduced for screening macromolecular X-ray crystallography diffraction images produced at an X-ray free-electron laser light source. Based on a data-driven deep learning approach, the proposed tool executes a convolutional neural network to detect Bragg spots. Automatic image processing algorithms described can enable the classification of large data sets, acquired under realistic conditions consisting of noisy data with experimental artifacts. Outcomes are compared for different data regimes, including samples from multiple instruments and differing amounts of training data for neural network optimization.
Authors:
 [1] ;  [2] ;  [1] ;  [3] ;  [4] ;  [2]
  1. Univ. of California, Berkeley, CA (United States). International Computer Science Inst.
  2. Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States). Molecular Biophysics and Integrated Bioimaging Division
  3. Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States). Computational Research Division; Univ. of California, Berkeley, CA (United States). Berkeley Inst. for Data Science
  4. Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States). Computational Research Division
Publication Date:
Grant/Contract Number:
AC02-05CH11231; AC02-76SF00515
Type:
Published Article
Journal Name:
Journal of Synchrotron Radiation (Online)
Additional Journal Information:
Journal Name: Journal of Synchrotron Radiation (Online); Journal Volume: 25; Journal Issue: 3; Journal ID: ISSN 1600-5775
Publisher:
International Union of Crystallography
Research Org:
Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
Sponsoring Org:
USDOE Office of Science (SC)
Country of Publication:
United States
Language:
English
Subject:
74 ATOMIC AND MOLECULAR PHYSICS; 46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND TECHNOLOGY; convolutional neural networks; deep learning; serial crystallography; X-ray free-electron laser; macromolecular structure
OSTI Identifier:
1434392
Alternate Identifier(s):
OSTI ID: 1460313

Ke, Tsung-Wei, Brewster, Aaron S., Yu, Stella X., Ushizima, Daniela, Yang, Chao, and Sauter, Nicholas K.. A convolutional neural network-based screening tool for X-ray serial crystallography. United States: N. p., Web. doi:10.1107/S1600577518004873.
Ke, Tsung-Wei, Brewster, Aaron S., Yu, Stella X., Ushizima, Daniela, Yang, Chao, & Sauter, Nicholas K.. A convolutional neural network-based screening tool for X-ray serial crystallography. United States. doi:10.1107/S1600577518004873.
Ke, Tsung-Wei, Brewster, Aaron S., Yu, Stella X., Ushizima, Daniela, Yang, Chao, and Sauter, Nicholas K.. 2018. "A convolutional neural network-based screening tool for X-ray serial crystallography". United States. doi:10.1107/S1600577518004873.
@article{osti_1434392,
title = {A convolutional neural network-based screening tool for X-ray serial crystallography},
author = {Ke, Tsung-Wei and Brewster, Aaron S. and Yu, Stella X. and Ushizima, Daniela and Yang, Chao and Sauter, Nicholas K.},
abstractNote = {A new tool is introduced for screening macromolecular X-ray crystallography diffraction images produced at an X-ray free-electron laser light source. Based on a data-driven deep learning approach, the proposed tool executes a convolutional neural network to detect Bragg spots. Automatic image processing algorithms described can enable the classification of large data sets, acquired under realistic conditions consisting of noisy data with experimental artifacts. Outcomes are compared for different data regimes, including samples from multiple instruments and differing amounts of training data for neural network optimization.},
doi = {10.1107/S1600577518004873},
journal = {Journal of Synchrotron Radiation (Online)},
number = 3,
volume = 25,
place = {United States},
year = {2018},
month = {4}
}