A convolutional neural network-based screening tool for X-ray serial crystallography
Journal Article
·
· Journal of Synchrotron Radiation (Online)
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.
- Research Organization:
- Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
- Sponsoring Organization:
- USDOE; USDOE Office of Science (SC)
- Grant/Contract Number:
- AC02-05CH11231; AC02-76SF00515
- OSTI ID:
- 1434392
- Alternate ID(s):
- OSTI ID: 22735907
OSTI ID: 1460313
- Journal Information:
- Journal of Synchrotron Radiation (Online), Journal Name: Journal of Synchrotron Radiation (Online) Journal Issue: 3 Vol. 25; ISSN 1600-5775; ISSN JSYRES
- Publisher:
- International Union of Crystallography (IUCr)Copyright Statement
- Country of Publication:
- Denmark
- Language:
- English
Similar Records
What’s the Difference? The Potential for Convolutional Neural Networks for Transient Detection without Template Subtraction
Deep residual networks for crystallography trained on synthetic data
Journal Article
·
Thu Aug 17 20:00:00 EDT 2023
· The Astronomical Journal
·
OSTI ID:1995913
Deep residual networks for crystallography trained on synthetic data
Journal Article
·
Sun Dec 31 19:00:00 EST 2023
· Acta Crystallographica. Section D. Structural Biology
·
OSTI ID:2274863