Figure - PMC

Skip to main content

An official website of the United States government

Here's how you know

Here's how you know

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

View full-text article in PMC

. 2022 Apr 5;5:316. doi: 10.1038/s42003-022-03261-8

Search in PMC
Search in PubMed
View in NLM Catalog
Add to search

© The Author(s) 2022

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/.

PMC Copyright notice

Fig. 2 — a The secondary structure classes were assigned to SCOPe domains and domains of high confidence in AlphaFold2 models. Four classes were considered, α, β, αβ, and small proteins. Left, SCOPe (232,630 domains); right, domains of high confidence in AlphaFold2 models. (508,787 domains). The classification was performed using a bagged SVM ensemble (see Methods). SCOPe domains (left) were also classified with the SVM ensemble to be able to compare with the results on AlphaFold2 domains (right). b Fold classification of the AlphaFold2 structure domains of high confidence. The classification was performed with the deep neural networks that were trained on the fold assignment provided in SCOPe (see Methods). The outer wheel indicates the fraction of each fold. Folds were ordered according to SCOPe IDs. Left, the fold distribution of AlphaFold2 domains using the deep network trained on 3DZDs of full atom domain structure surface. The inner wheel shows the fraction of secondary structure classes. Since this classification was based on the fold assignment, the fractions are overall consistent but not identical to those shown in panel (a). The top 10 most abundant folds are indicated. Right, the fold distribution using the deep network trained on 3DZDs of surface shapes with main-chain atoms. c The 10 most abundant folds among AlphaFold2 domains. The fraction of each fold is indicated in the wheel diagram on the left in panel b. For each fold, an example of AlphaFold domains is shown. (1) Non-globular all-alpha subunits of globular proteins (a.137). Example shown is A0A1D6E4Z3_F1, residue 823-895 (maize). (2) ROP-like (a.30): A0A1D6MV33_F1, residue 758-815 (maize). (3) Mediator hinge subcomplex-like (a.252). Q4DL50_F1, residue 384-495 (T. cruzi). (4) BAR/IMD domain-like (a.238). Q8LE58_F1, residue 2-133 (Arabidopsis). (5) Intrinsically disordered proteins (g.88). I1L2C2_F1, residue 210-284 (soybean). (6) N-terminal domain of bifunctional PutA protein (a.176). A7MBM2_F1, residue 157-225 (human). (7) L27 domain (a.194). A0A1D6PKM6_F1, residue 314-375 (maize). (8) alpha-alpha superhelix (a.118). K7KHY8_F, residue 213-524 (soybean). (9) Spectrin repeat-like (a.7). P38637_F1, residue 149-238_AFv1 (S. cerevisiae). 10 SRF-like (d.88). A0A1D6NUQ9_F1, residue 2-74 (maize).