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 9
Maximum composite images of sequential groups of SSRL diffraction patterns. The resolution labels 3.20, 2.56 and 1.28 Å correspond to the SSRL data sets that are shown in Fig. 8

(subplots W, S and A, respectively). The shot ranges over which the maximum composite images were computed are shown in the subplots in Fig. 8

(W, S and A). Regions labeled `I' correspond to relatively high-resolution estimates and regions labeled `II' correspond to low-resolution estimates from the same data set. The black circles indicate the nominal resolutions of the data sets (taken from the AIMLESS logs), and the red circles mark the average resolutions determined by Resonet for the images that went into each maximum composite. Different features in the data can influence the Resonet resolution. Here, we observe asymmetric diffraction influencing the predicted resolution of the pattern.

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