skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

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

Abstract

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:
; ; ; ; ;
Publication Date:
Sponsoring Org.:
USDOE
OSTI Identifier:
1434392
Grant/Contract Number:
AC02-05CH11231; AC02-76SF00515
Resource Type:
Journal Article: Published Article
Journal Name:
Journal of Synchrotron Radiation
Additional Journal Information:
Journal Volume: 25; Journal Issue: 3; Related Information: CHORUS Timestamp: 2018-05-18 12:57:24; Journal ID: ISSN 1600-5775
Publisher:
International Union of Crystallography (IUCr)
Country of Publication:
Denmark
Language:
English

Citation Formats

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. Denmark: N. p., 2018. 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. Denmark. doi:10.1107/S1600577518004873.
Ke, Tsung-Wei, Brewster, Aaron S., Yu, Stella X., Ushizima, Daniela, Yang, Chao, and Sauter, Nicholas K. Tue . "A convolutional neural network-based screening tool for X-ray serial crystallography". Denmark. 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},
number = 3,
volume = 25,
place = {Denmark},
year = {Tue Apr 24 00:00:00 EDT 2018},
month = {Tue Apr 24 00:00:00 EDT 2018}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record at 10.1107/S1600577518004873

Save / Share: