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 10
Overall B-factor and resolution estimation for each of the SSRL data sets shown in Table 3

and Fig. 8

. The `min' subscript for the B factor (B_min) and resolution (d_min) represents the minimum of the four values inferred across the quadrants of each image and the angle brackets 〈〉 indicate an `average over images per data set' (the number of images in each data set is labeled in Fig. 8

). Top: the overall Resonet B factor, the Wilson B factor (from AIMLESS) and the median atomic B factor (from structure solution and refinement using REFMAC). Bottom: the overall Resonet resolution, the resolution determined with AIMLESS and a resolution estimate d_fit based on all processed images but extrapolated to unit multiplicity (for comparison with the Resonet inference, which is for a single shot). See Section A2

for a detailed description of d_fit.

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