A convolutional neural network‐based screening tool for X‐ray serial crystallography. (24th April 2018)

• Record Type: Journal Article
• Authors: Ke, Tsung-Wei; Brewster, Aaron S.; Yu, Stella X.; Ushizima, Daniela; Yang, Chao; Sauter, Nicholas K.
• Is Part Of: Journal of synchrotron radiation. Volume 25:Part 3(2018)
• Page Start: 655
• Page End: 670
• Publication Date: 2018-04-24
• Subjects: convolutional neural networks -- deep learning -- serial crystallography -- X‐ray free‐electron laser -- macromolecular structure; Synchrotron radiation -- Periodicals; Free electron lasers -- Periodicals; 539.73505
• DOI: 10.1107/S1600577518004873
• Languages: English
• ISSNs: 0909-0495

Abstract

Abstract : Deep learning provides one possible avenue to reduce the data stream generated by serial macromolecular X‐ray crystallography. Convolutional neural networks can be trained to recognize the presence or absence of Bragg spots, forming a criterion to veto events prior to downstream data processing. 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.