Nuclear Techniques ›› 2019, Vol. 42 ›› Issue (8): 80102-080102.doi: 10.11889/j.0253-3219.2019.hjs.42.080102


Research on serial crystallography data screening algorithm

Yueqi QIAN1,2,Bo LIU3   

  1. 1. Shanghai Institute of Applied Physics, Chinese Academy of Sciences, Shanghai 201800, China
    2. University of Chinese Academy of Sciences, Beijing 100049, China
    3. Shanghai Advanced Research Institute, Chinese Academy of Sciences, Shanghai 201210, China
  • Received:2019-03-15 Revised:2019-05-17 Online:2019-08-10 Published:2019-08-26
  • About author:QIAN Yueqi, male, born in 1991, graduated from University of Science and Technology of China in 2014, master student, focusing on optics
  • Supported by:
    National Key R&D Program of China "Research on XFEL Principle & Key Technologies"(2016YFA0401901)

Abstract: Background

A number of machine learning-based methods have been developed for classification screening of serial femtosecond crystallography (SFX) data.


This study aims to improve the data analysis technique to obtain more effectively screen SFX data from X-ray free electron lasers (XFELS).


First of all, experimental data of different samples were taken for screening and categorizing, Automatic image processing and convolutional neural network were employed for detection of Bragg points in diffraction patterns of crystals, hence, invalid experimental data were filtered out. Then, simulation was performed as the benchmark for many experiments. Finally, the reasons for the different accuracy of experimental prediction results were analyzed.


Among many methods, convolutional neural network can obtain higher prediction accuracy whilst linear method only has better accuracy for some samples, but both of them are superior to traditional point-finding algorithm.


This approach provides an effective and convenient data screening tool for X-ray FEL experiments.

Key words: Free electron laser, Serial crystallography, Machine learning

CLC Number: 

  • TP181,O722