% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Zhuang:473658,
author = {Zhuang, Yulong and Awel, Salah and Barty, Anton and Bean,
Richard and Bielecki, Johan and Bergemann, Martin and
Daurer, Benedikt and Ekeberg, Tomas and Estillore, Armando
D. and Fangohr, Hans and Giewekemeyer, Klaus and Hunter,
Mark S. and Karnevskiy, Mikhail and Kirian, Richard and
Kirkwood, Henry and Kim, Yoonhee and Koliyadu, Jayanath and
Lange, Holger and Letrun, Romain and Lübke, Jannik and
Mall, Abhishek and Michelat, Thomas and Morgan, Andrew J.
and Roth, Nils and Samanta, Amit K. and Sato, Tokushi and
Shen, Zhou and Sikorski, Marcin and Schulz, Florian and
Spence, John C. H. and Vagovic, Patrik and Wollweber, Tamme
and Worbs, Lena and Xavier, P. Lourdu and Yefanov, Oleksandr
and Maia, Filipe R. N. C. and Horke, Daniel A. and Küpper,
Jochen and Loh, Duane and Mancuso, Adrian and Chapman, Henry
N. and Ayyer, Kartik},
title = {{U}nsupervised learning approaches to characterizing
heterogeneous samples using {X}-ray single-particle imaging},
journal = {IUCrJ},
volume = {9},
number = {2},
issn = {2052-2525},
address = {Chester},
reportid = {PUBDB-2022-00171},
pages = {204 - 214},
year = {2022},
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.},
cin = {FS-CFEL-1 / XFEL-User / MPSD / FS-CFEL-CMI},
ddc = {530},
cid = {I:(DE-H253)FS-CFEL-1-20120731 /
I:(DE-H253)XFEL-User-20170713 / I:(DE-H253)MPSD-20120731 /
I:(DE-H253)FS-CFEL-CMI-20220405},
pnm = {631 - Matter – Dynamics, Mechanisms and Control
(POF4-631) / DFG project 390715994 - EXC 2056: CUI: Advanced
Imaging of Matter (390715994) / DFG project 194651731 - EXC
1074: Hamburger Zentrum für ultraschnelle Beobachtung
(CUI): Struktur, Dynamik und Kontrolle von Materie auf
atomarer Skala (194651731) / COMOTION - Controlling the
Motion of Complex Molecules and Particles (614507) / IVF -
Impuls- und Vernetzungsfonds (IVF-20140101)},
pid = {G:(DE-HGF)POF4-631 / G:(GEPRIS)390715994 /
G:(GEPRIS)194651731 / G:(EU-Grant)614507 /
G:(DE-HGF)IVF-20140101},
experiment = {EXP:(DE-H253)XFEL-SPB-20150101},
typ = {PUB:(DE-HGF)16},
pubmed = {35371510},
UT = {WOS:000795673400007},
doi = {10.1107/S2052252521012707},
url = {https://bib-pubdb1.desy.de/record/473658},
}