Published April 14, 2022 | Version v1
Journal article Open

Data repository for the article: "Classification of diffraction patterns using a convolutional neural network in single-particle-imaging experiments performed at X-ray free-electron lasers"

  • 1. Deutsches Elektronen-Synchrotron DESY
  • 2. Applied Computer Vision Lab, Helmholtz Imaging, German Cancer Research Center (DKFZ), Division of Medical Image Computing, German Cancer Research Center (DKFZ)

Description

Data "data_corrected.zip" used in the paper (Assalauova, Ignatenko, Isensee et al., 2022) were described in (Li et al., 2020) and raw files were published on CXDI platform (https://www.cxidb.org/id-156.html). These data were preprocessed (background correction, center estimation) by S. Bobkov using SPI data analysis platform available in GitLab (https://gitlab.com/spi_xfel), the section “spi_processing” and described in (Bobkov et al., 2020). Procedures described in (Assalauova, Ignatenko, Isensee et al., 2022) are publicly available https://gitlab.hzdr.de/hi-dkfz/applied-computer-vision-lab/collaborations/desy_2021_singleparticleimaging_cnn.

File "final_200k_split_191183.pkl" contains the train:test split and file "PaperConfigMaxF1.zip" contains pretrained weights. These two files are used with the code repository https://gitlab.hzdr.de/hi-dkfz/applied-computer-vision-lab/collaborations/desy_2021_singleparticleimaging_cnn.

 

Assalauova, D., Ignatenko, A., Isensee, F., et al. “Classification of diffraction patterns using a convolutional neural network in single particle imaging experiments performed at X-ray free-electron lasers.” arXiv preprint arXiv:2112.09020.
Haoyuan, L., et al. ”Diffraction data from aerosolized Coliphage PR772 virus particles imaged with the Linac Coherent Light Source.” Scientific data 7.1 (2020): 1-12.
Bobkov, S. A., et al. “Advances in Modern Information Technologies for Data Analysis in CRYO-EM and XFEL Experiments.” Crystallography Reports 65.6 (2020): 1081-1092.
 

Files

data_corrected.zip

Files (4.0 GB)

Name Size Download all
md5:8cf0d65c91c51c84b018d6125fa23427
3.6 GB Preview Download
md5:e99a81a9410e4a56bdffbfab10acb039
16.3 MB Download
md5:2bd3bfbc4c4a58526029bbc2b185a470
362.0 MB Preview Download