TY - JOUR
T1 - Evaluation of the performance of classification algorithms for XFEL single-particle imaging data
AU - Shi, Yingchen
AU - Yin, Ke
AU - TAI, Xue-Cheng
AU - DeMirci, Hasan
AU - Hosseinizadeh, Ahmad
AU - Hogue, Brenda G.
AU - Li, Haoyuan
AU - Ourmazd, Abbas
AU - Schwander, Peter
AU - Vartanyants, Ivan A.
AU - Yoon, Chun Hong
AU - Aquila, Andrew
AU - Liu, Haiguang
N1 - Funding Information:
Portions of this research were carried out at the Linac Coherent Light Source (LCLS) at the SLAC National Accelerator Laboratory. The LCLS is supported by the US Department of Energy (DOE), Office of Science, Office of Basic Energy Sciences (OBES), under contract DE-AC02-76SF00515.
PY - 2019/3
Y1 - 2019/3
N2 - 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.
AB - 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.
KW - classification algorithms
KW - electron-density map reconstruction
KW - single-particle imaging
KW - X-ray free-electron lasers (XFELs)
UR - http://www.scopus.com/inward/record.url?scp=85062655163&partnerID=8YFLogxK
U2 - 10.1107/S2052252519001854
DO - 10.1107/S2052252519001854
M3 - Article
AN - SCOPUS:85062655163
SN - 2052-2525
VL - 6
SP - 331
EP - 340
JO - IUCrJ
JF - IUCrJ
ER -