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

Title: Unsupervised learning approaches to characterizing heterogeneous samples using X-ray single-particle imaging

Journal Article · · IUCrJ
 [1]; ORCiD logo [2];  [2];  [3]; ORCiD logo [3];  [3]; ORCiD logo [4]; ORCiD logo [5]; ORCiD logo [2];  [6];  [3];  [7]; ORCiD logo [3]; ORCiD logo [8];  [3]; ORCiD logo [3];  [3]; ORCiD logo [9];  [3];  [10] more »;  [1];  [3];  [11];  [12];  [2]; ORCiD logo [3];  [4];  [2]; ORCiD logo [9];  [8];  [13];  [10];  [12];  [10]; ORCiD logo [2];  [14]; ORCiD logo [15];  [12]; ORCiD logo [4]; ORCiD logo [16]; ORCiD logo [12];  [10] « less
  1. Max Planck Institute for the Structure and Dynamics of Matter, Hamburg (Germany); Deutsches Elektronen-Synchrotron (DESY), Hamburg (Germany). Center for Free-Electron Laser Science
  2. Deutsches Elektronen-Synchrotron (DESY), Hamburg (Germany). Center for Free-Electron Laser Science
  3. European XFEL, Schenefeld (Germany)
  4. National Univ. of Singapore (Singapore)
  5. Uppsala Univ. (Sweden)
  6. Max Planck Institute for the Structure and Dynamics of Matter, Hamburg (Germany); Deutsches Elektronen-Synchrotron (DESY), Hamburg (Germany). Center for Free-Electron Laser Science; European XFEL, Schenefeld (Germany); Univ. of Southampton (United Kingdom)
  7. SLAC National Accelerator Lab., Menlo Park, CA (United States). Linac Coherent Light Source (LCLS)
  8. Arizona State Univ., Tempe, AZ (United States)
  9. Univ. of Hamburg (Germany)
  10. Max Planck Institute for the Structure and Dynamics of Matter, Hamburg (Germany); Deutsches Elektronen-Synchrotron (DESY), Hamburg (Germany). Center for Free-Electron Laser Science; Univ. of Hamburg (Germany)
  11. Univ. of Melbourne, VIC (Australia)
  12. Deutsches Elektronen-Synchrotron (DESY), Hamburg (Germany). Center for Free-Electron Laser Science; Univ. of Hamburg (Germany)
  13. Deutsches Elektronen-Synchrotron (DESY), Hamburg (Germany). Center for Free-Electron Laser Science; European XFEL, Schenefeld (Germany)
  14. Uppsala Univ. (Sweden); Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States). National Energy Research Scientific Computing Center (NERSC)
  15. Deutsches Elektronen-Synchrotron (DESY), Hamburg (Germany). Center for Free-Electron Laser Science; Univ. of Hamburg (Germany); Radboud Univ., Nijmegen (Netherlands)
  16. European XFEL, Schenefeld (Germany); La Trobe Univ., Melbourne, VIC (Australia)
+ Show Author Affiliations

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.

Research Organization:
SLAC National Accelerator Lab., Menlo Park, CA (United States)
Sponsoring Organization:
USDOE Office of Science (SC), Basic Energy Sciences (BES); German Research Foundation (DFG); European Research Council (ERC); National Science Foundation (NSF); Swedish Research Council (SRC); Human Frontiers Science Program, France
Grant/Contract Number:
AC02-76SF00515; 194651731; 390715994; ERC-614507-Küpper; STC-1231306; RGP0010/2017
OSTI ID:
1871648
Journal Information:
IUCrJ, Vol. 9, Issue 2; ISSN 2052-2525
Publisher:
International Union of CrystallographyCopyright Statement
Country of Publication:
United States
Language:
English

References (24)

Low-signal limit of X-ray single particle diffractive imaging journal January 2019
Orientation determination in single-particle x-ray coherent diffraction imaging experiments journal August 2013
Interior Melting of Rapidly Heated Gold Nanoparticles journal August 2021
High-Throughput 3D Ensemble Characterization of Individual Core–Shell Nanoparticles with X-ray Free Electron Laser Single-Particle Imaging journal January 2021
Deep neural networks for classifying complex features in diffraction images journal June 2019
Crystallography without crystals. I. The common-line method for assembling a three-dimensional diffraction volume from single-particle scattering journal February 2008
Unsupervised classification of single-particle X-ray diffraction snapshots by spectral clustering journal January 2011
Dragonfly : an implementation of the expand–maximize–compress algorithm for single-particle imaging journal June 2016
The Single Particles, Clusters and Biomolecules and Serial Femtosecond Crystallography instrument of the European XFEL: initial installation journal April 2019
Three-Dimensional Structure Determination from Common Lines in Cryo-EM by Eigenvectors and Semidefinite Programming journal January 2011
CryoDRGN: reconstruction of heterogeneous cryo-EM structures using neural networks journal February 2021
A MHz-repetition-rate hard X-ray free-electron laser driven by a superconducting linear accelerator journal May 2020
Observation of an environmentally insensitive solid-state spin defect in diamond journal July 2018
Materials science: Melting and the surface journal October 1986
Correlations in Scattered X-Ray Laser Pulses Reveal Nanoscale Structural Features of Viruses journal October 2017
Reconstruction algorithm for single-particle diffraction imaging experiments journal August 2009
Accelerated imaging of metallic implants using model‐based nonlinear reconstruction journal November 2018
Structure determination from single molecule X-ray scattering with three photons per image journal June 2018
Potential for biomolecular imaging with femtosecond X-ray pulses journal August 2000
The Adaptive Gain Integrating Pixel Detector at the European XFEL journal January 2019
An Introduction to Variational Autoencoders journal January 2019
Classification of diffraction patterns in single particle imaging experiments performed at x-ray free-electron lasers using a convolutional neural network journal February 2021
Sorting algorithms for single-particle imaging experiments at X-ray free-electron lasers journal October 2015
3D diffractive imaging of nanoparticle ensembles using an x-ray laser journal December 2020

Similar Records

Low-signal limit of X-ray single particle diffractive imaging
Journal Article · Thu Dec 12 00:00:00 EST 2019 · Optics Express · OSTI ID:1871648
+7 more
Diffraction data from aerosolized Coliphage PR772 virus particles imaged with the Linac Coherent Light Source
Journal Article · Thu Nov 19 00:00:00 EST 2020 · Scientific Data · OSTI ID:1871648
+47 more
Finding simplicity: unsupervised discovery of features, patterns, and order parameters via shift-invariant variational autoencoders *
Journal Article · Mon Nov 20 00:00:00 EST 2023 · Machine Learning: Science and Technology · OSTI ID:1871648

Related Subjects

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND TECHNOLOGY