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:
; ; ; ; ;
Publication Date:
Grant/Contract Number:
AC02-05CH11231; AC02-76SF00515
Type:
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)
Sponsoring Org:
USDOE
Country of Publication:
Denmark
Language:
English
OSTI Identifier:
1434392