High-accuracy protein structure prediction in CASP14



Pereira, Joana, Simpkin, Adam J, Hartmann, Marcus D, Rigden, Daniel J ORCID: 0000-0002-7565-8937, Keegan, Ronan M and Lupas, Andrei N
(2021) High-accuracy protein structure prediction in CASP14. PROTEINS-STRUCTURE FUNCTION AND BIOINFORMATICS, 89 (12). pp. 1687-1699.

Access the full-text of this item by clicking on the Open Access link.

Abstract

The application of state-of-the-art deep-learning approaches to the protein modeling problem has expanded the "high-accuracy" category in CASP14 to encompass all targets. Building on the metrics used for high-accuracy assessment in previous CASPs, we evaluated the performance of all groups that submitted models for at least 10 targets across all difficulty classes, and judged the usefulness of those produced by AlphaFold2 (AF2) as molecular replacement search models with AMPLE. Driven by the qualitative diversity of the targets submitted to CASP, we also introduce DipDiff as a new measure for the improvement in backbone geometry provided by a model versus available templates. Although a large leap in high-accuracy is seen due to AF2, the second-best method in CASP14 out-performed the best in CASP13, illustrating the role of community-based benchmarking in the development and evolution of the protein structure prediction field.

Item Type: Article
Uncontrolled Keywords: CASP14, high-accuracy, molecular replacement
Divisions: Faculty of Health and Life Sciences
Faculty of Health and Life Sciences > Institute of Systems, Molecular and Integrative Biology
Depositing User: Symplectic Admin
Date Deposited: 12 Jul 2021 09:51
Last Modified: 18 Jan 2023 21:36
DOI: 10.1002/prot.26171
Open Access URL: https://onlinelibrary.wiley.com/doi/abs/10.1002/pr...
Related URLs:
URI: https://livrepository.liverpool.ac.uk/id/eprint/3129739