English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Unsupervised learning approaches to characterizing heterogeneous samples using X-ray single-particle imaging

Zhuang, Y., Awel, S., Barty, A., Bean, R., Bielecki, J., Bergemann, M., et al. (2022). Unsupervised learning approaches to characterizing heterogeneous samples using X-ray single-particle imaging. IUCrJ, 9(2), 1-11. doi:10.1107/S2052252521012707.

Item is

Basic

show hide
Genre: Journal Article

Files

show Files
hide Files
:
it5025.pdf (Publisher version), 2MB
Name:
it5025.pdf
Description:
Open Access
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
Copyright Date:
2022
Copyright Info:
© the Author(s) / IUCrJ

Locators

show
hide
Locator:
https://arxiv.org/abs/2109.06179 (Preprint)
Description:
-
Locator:
https://doi.org/10.1107/S2052252521012707 (Publisher version)
Description:
-

Creators

show
hide
 Creators:
Zhuang, Y.1, 2, Author
Awel, S.3, Author
Barty, A.3, Author
Bean, R.3, Author
Bielecki, J.3, Author
Bergemann, M.3, Author
Daurer, B. J.3, Author
Ekeberg, T.3, Author
Estillore, A. D.3, Author
Fangohr, H.2, 4, 5, 6, Author
Giewekemeyer, K.3, Author
Hunter, M. S.3, Author
Karnevskiy, M.3, Author
Kirian, R. A.3, Author
Kirkwood, H.3, Author
Kim, Y.3, Author
Koliyadu, J.3, Author
Lange, H.3, Author
Letrun, R.3, Author
Lübke, J.3, Author
Mall, A.1, 2, 7, Author              Michelat, T.3, AuthorMorgan, A. J.3, AuthorRoth, N.3, AuthorSamanta, A. K.3, AuthorSato, T.3, AuthorShen, Z.3, AuthorSikorski, M.3, AuthorSchulz, F.3, AuthorSpence, J. C. H.3, AuthorVagovic, P.3, AuthorWollweber, T.1, 2, 8, AuthorWorbs, L.3, AuthorXavier, P. L.2, 8, AuthorYefanov, O.3, AuthorMaia, F. R. N. C.3, AuthorHorke, D. A.3, AuthorKüpper, J.3, AuthorLoh, N. D.3, AuthorMancuso, A. P.3, AuthorChapman, H. N.3, AuthorAyyer, K.1, 2, 8, Author more..
Affiliations:
1Computational Nanoscale Imaging, Condensed Matter Dynamics Department, Max Planck Institute for the Structure and Dynamics of Matter, Max Planck Society, ou_3012829              
2Center for Free-Electron Laser Science, ou_persistent22              
3external, ou_persistent22              
4Computational Science, Scientific Service Units, Max Planck Institute for the Structure and Dynamics of Matter, Max Planck Society, ou_3267028              
5European XFEL, ou_persistent22              
6University of Southampton, ou_persistent22              
7International Max Planck Research School for Ultrafast Imaging & Structural Dynamics (IMPRS-UFAST), Max Planck Institute for the Structure and Dynamics of Matter, Max Planck Society, ou_2266714              
8The Hamburg Center for Ultrafast Imaging, Universität Hamburg, ou_persistent22              

Content

show
hide
Free keywords: oherent X-ray diffractive imaging (CXDI); single particles; XFELs
 Abstract: One of the outstanding analytical problems in X-ray single-particle imaging (SPI) is the classification of structural heterogeneity, which is especially difficult given the low signal-to-noise ratios of individual patterns and the fact that even identical objects can yield patterns that vary greatly when orientation is taken into consideration. Proposed here are two methods which explicitly account for this orientation-induced variation and can robustly determine the structural landscape of a sample ensemble. The first, termed common-line principal component analysis (PCA), provides a rough classification which is essentially parameter free and can be run automatically on any SPI dataset. The second method, utilizing variation auto-encoders (VAEs), can generate 3D structures of the objects at any point in the structural landscape. Both these methods are implemented in combination with the noise-tolerant expand–maximize–compress (EMC) algorithm and its utility is demonstrated by applying it to an experimental dataset from gold nanoparticles with only a few thousand photons per pattern. Both discrete structural classes and continuous deformations are recovered. These developments diverge from previous approaches of extracting reproducible subsets of patterns from a dataset and open up the possibility of moving beyond the study of homogeneous sample sets to addressing open questions on topics such as nanocrystal growth and dynamics, as well as phase transitions which have not been externally triggered.

Details

show
hide
Language(s): eng - English
 Dates: 2021-09-152021-11-302022-01
 Publication Status: Published online
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: Peer
 Identifiers: arXiv: 2109.06179
DOI: 10.1107/S2052252521012707
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: IUCrJ
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: Chester CH1 2HU, England : International Union of Crystallography (IUCr)
Pages: - Volume / Issue: 9 (2) Sequence Number: - Start / End Page: 1 - 11 Identifier: ISSN: 2052-2525
CoNE: https://pure.mpg.de/cone/journals/resource/2052-2525