skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Evaluation of the performance of classification algorithms for XFEL single-particle imaging data

Abstract

Using X-ray free-electron lasers (XFELs), it is possible to determine three-dimensional structures of nanoscale particles using single-particle imaging methods. Classification algorithms are needed to sort out the single-particle diffraction patterns from the large amount of XFEL experimental data. However, different methods often yield inconsistent results. This study compared the performance of three classification algorithms: convolutional neural network, graph cut and diffusion map manifold embedding methods. The identified single-particle diffraction data of the PR772 virus particles were assembled in the three-dimensional Fourier space for real-space model reconstruction. The comparison showed that these three classification methods lead to different datasets and subsequently result in different electron density maps of the reconstructed models. Interestingly, the common dataset selected by these three methods improved the quality of the merged diffraction volume, as well as the resolutions of the reconstructed maps.

Authors:
ORCiD logo [1];  [2];  [3];  [4];  [5];  [6];  [7];  [5];  [5];  [8];  [4];  [4]; ORCiD logo [9]
  1. Tsinghua Univ., Beijing (People's Republic of China); Beijing Computational Science Research Centre, Beijing (People's Republic of China)
  2. Huazhong Univ. of Science and Technology, Hubei (People's Republic of China)
  3. Univ. of Bergen, Bergen (Norway)
  4. SLAC National Accelerator Lab., Menlo Park, CA (United States)
  5. Univ. of Wisconsin-Milwaukee, Milwaukee, WI (United States)
  6. Arizona State Univ., Tempe, AZ (United States)
  7. SLAC National Accelerator Lab., Menlo Park, CA (United States); Stanford Univ., Stanford, CA (United States)
  8. Deutsches Elektronen-Synchrotron (DESY), Hamburg (Germany); National Research Nuclear Univ. MEPhI (Moscow Engineering Physics Institute), Moscow (Russian Federation)
  9. Beijing Computational Science Research Centre, Beijing (People's Republic of China)
Publication Date:
Research Org.:
SLAC National Accelerator Lab., Menlo Park, CA (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1505431
Grant/Contract Number:  
11575021; U1530401; U1430237; 1231306; SC002164; AC02-76SF00515; 18-41-06001
Resource Type:
Journal Article: Accepted Manuscript
Journal Name:
IUCrJ
Additional Journal Information:
Journal Volume: 6; Journal Issue: 2; Journal ID: ISSN 2052-2525
Publisher:
International Union of Crystallography
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING; X-ray free-electron lasers (XFELs); single-particle imaging; classification algorithms; electron-density map reconstruction

Citation Formats

Shi, Yingchen, Yin, Ke, Tai, Xuecheng, DeMirci, Hasan, Hosseinizadeh, Ahmad, Hogue, Brenda G., Li, Haoyuan, Ourmazd, Abbas, Schwander, Peter, Vartanyants, Ivan A., Yoon, Chun Hong, Aquila, Andrew, and Liu, Haiguang. Evaluation of the performance of classification algorithms for XFEL single-particle imaging data. United States: N. p., 2019. Web. doi:10.1107/s2052252519001854.
Shi, Yingchen, Yin, Ke, Tai, Xuecheng, DeMirci, Hasan, Hosseinizadeh, Ahmad, Hogue, Brenda G., Li, Haoyuan, Ourmazd, Abbas, Schwander, Peter, Vartanyants, Ivan A., Yoon, Chun Hong, Aquila, Andrew, & Liu, Haiguang. Evaluation of the performance of classification algorithms for XFEL single-particle imaging data. United States. doi:10.1107/s2052252519001854.
Shi, Yingchen, Yin, Ke, Tai, Xuecheng, DeMirci, Hasan, Hosseinizadeh, Ahmad, Hogue, Brenda G., Li, Haoyuan, Ourmazd, Abbas, Schwander, Peter, Vartanyants, Ivan A., Yoon, Chun Hong, Aquila, Andrew, and Liu, Haiguang. Thu . "Evaluation of the performance of classification algorithms for XFEL single-particle imaging data". United States. doi:10.1107/s2052252519001854. https://www.osti.gov/servlets/purl/1505431.
@article{osti_1505431,
title = {Evaluation of the performance of classification algorithms for XFEL single-particle imaging data},
author = {Shi, Yingchen and Yin, Ke and Tai, Xuecheng and DeMirci, Hasan and Hosseinizadeh, Ahmad and Hogue, Brenda G. and Li, Haoyuan and Ourmazd, Abbas and Schwander, Peter and Vartanyants, Ivan A. and Yoon, Chun Hong and Aquila, Andrew and Liu, Haiguang},
abstractNote = {Using X-ray free-electron lasers (XFELs), it is possible to determine three-dimensional structures of nanoscale particles using single-particle imaging methods. Classification algorithms are needed to sort out the single-particle diffraction patterns from the large amount of XFEL experimental data. However, different methods often yield inconsistent results. This study compared the performance of three classification algorithms: convolutional neural network, graph cut and diffusion map manifold embedding methods. The identified single-particle diffraction data of the PR772 virus particles were assembled in the three-dimensional Fourier space for real-space model reconstruction. The comparison showed that these three classification methods lead to different datasets and subsequently result in different electron density maps of the reconstructed models. Interestingly, the common dataset selected by these three methods improved the quality of the merged diffraction volume, as well as the resolutions of the reconstructed maps.},
doi = {10.1107/s2052252519001854},
journal = {IUCrJ},
issn = {2052-2525},
number = 2,
volume = 6,
place = {United States},
year = {2019},
month = {2}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Save / Share:

Works referenced in this record:

Single-particle imaging without symmetry constraints at an X-ray free-electron laser
journal, September 2018


Correlations in Scattered X-Ray Laser Pulses Reveal Nanoscale Structural Features of Viruses
journal, October 2017

  • Kurta, Ruslan P.; Donatelli, Jeffrey J.; Yoon, Chun Hong
  • Physical Review Letters, Vol. 119, Issue 15, Article No. 158102
  • DOI: 10.1103/PhysRevLett.119.158102