Deep residual networks for crystallography trained on synthetic data

Mendez, D.; Holton, J.M.; Lyubimov, A.Y.; Hollatz, S.; Mathews, I.I.; Cichosz, A.; Martirosyan, V.; Zeng, T.; Stofer, R.; Liu, R.; Song, J.; McPhillips, S.; Soltis, M.; Cohen, A.E.

doi:10.1107/S2059798323010586

Acta Crystallographica Section D
Acta Crystallographica
Section D STRUCTURAL BIOLOGY

IUCr IT WDC

home archive editors for authors for readers submit subscribe open access

view article

Figure 11
Resonet overlapping lattice detection for fixed-target data collected at LCLS (Artz et al., 2020

). The raw prediction corresponds to the probability that the image contains overlapping lattice diffraction; hence, subtracting this number from 1 computes the probability that the image only contains diffraction from a single lattice. The gray histogram represents all 512 images, whereas the red histogram represents the 122 images that were hand-selected for processing in Artz et al. (2020

). These hand-selected images were chosen because they resembled good-quality, single-lattice diffraction. Only four of these hand-selected images were predicted by Resonet to contain overlapping lattice scattering (with overlapping lattice probability > 50%).

STRUCTURAL
BIOLOGY

ISSN: 2059-7983

Volume 80| Part 1| January 2024| Pages 26-43

https://doi.org/10.1107/S2059798323010586

Open

access

Follow Acta Cryst. D

Search IUCr Journals		doi		Advanced search
Author		volume	page