Impact of AlphaFold on structure prediction of protein complexes: The CASP15-CAPRI experiment 2023 (English)In: Proteins: Structure, Function, and Bioinformatics, ISSN 0887-3585, E-ISSN 1097-0134, Vol. 91, no 12, p. 1658-1683Article in journal (Refereed) Published

Abstract [en]

We present the results for CAPRI Round 54, the 5th joint CASP-CAPRI protein assembly prediction challenge. The Round offered 37 targets, including 14 homodimers, 3 homo-trimers, 13 heterodimers including 3 antibody-antigen complexes, and 7 large assemblies. On average similar to 70 CASP and CAPRI predictor groups, including more than 20 automatics servers, submitted models for each target. A total of 21 941 models submitted by these groups and by 15 CAPRI scorer groups were evaluated using the CAPRI model quality measures and the DockQ score consolidating these measures. The prediction performance was quantified by a weighted score based on the number of models of acceptable quality or higher submitted by each group among their five best models. Results show substantial progress achieved across a significant fraction of the 60+ participating groups. High-quality models were produced for about 40% of the targets compared to 8% two years earlier. This remarkable improvement is due to the wide use of the AlphaFold2 and AlphaFold2-Multimer software and the confidence metrics they provide. Notably, expanded sampling of candidate solutions by manipulating these deep learning inference engines, enriching multiple sequence alignments, or integration of advanced modeling tools, enabled top performing groups to exceed the performance of a standard AlphaFold2-Multimer version used as a yard stick. This notwithstanding, performance remained poor for complexes with antibodies and nanobodies, where evolutionary relationships between the binding partners are lacking, and for complexes featuring conformational flexibility, clearly indicating that the prediction of protein complexes remains a challenging problem.

Place, publisher, year, edition, pages

WILEY , 2023. Vol. 91, no 12, p. 1658-1683

Keywords [en]

AlphaFold; blind prediction; CAPRI; CASP; deep learning; protein assemblies; protein complexes; protein-protein interaction

National Category

Bioinformatics (Computational Biology)

Identifiers

URN: urn:nbn:se:liu:diva-200076DOI: 10.1002/prot.26609ISI: 001102951600001PubMedID: 37905971OAI: oai:DiVA.org:liu-200076DiVA, id: diva2:1827625

Note

Funding Agencies|Francis Crick Institute; Cancer Research UK [FC0001003]; UK Medical Research Council [FC001003]; Wellcome Trust [FC001003]; European Union Horizon 2020 [823830]; Netherlands e-Science Center [027.020.G13]; US National Institutes of Health [R01GM146340, R01GM093123]; Spanish Ministry of Science [501100011033, AEI/10.13039, PID2019-110167RB-I00]; National Institute of Health [R35 GM144083, RM1135136, R35GM118078, R01GM140098, R01GM123055, R01GM133840, R35-GM141881]; Advanced Research Computing at Hopkins (ARCH) core facility; National Natural Science Foundation of China [32161133002, 62072199]; European Molecular Biology Organization (EMBO) [ALTF 145-2021]; Government of Catalonia's Agency for Business Competitiveness (ACCIO); National Science Foundation [DMS 2054251, DBI2003635, IIS2211598, DBI2146026, MCB1925643, CMMI1825941, IIS1763246, DBI1759934, CCF-1943008, OAC1920103]; National Institute of General Medical Sciences [T32 GM132024]; NIH/NIGMS [R35GM136409, R35GM124952]; National Science Center of Poland (Narodowe Centrum Nauki) (NCN) [UMO2017/27/B/ST4/00926, UMO-2017/26/M/ ST4/00044, UMO2017/25/B/ST4/01026]; Research Council of Lithuania [: S-MIP-21-25]; Wallenberg AI, Autonomous System and Software Program (WASP); Knut and Alice Wallenberg Foundation (KAW); Swedish Research Council; Science Foundation of the National Key Laboratory of Science and Technology; Fundamental Research Funds for the Central Universities of China; [801342]

Available from: 2024-01-15 Created: 2024-01-15 Last updated: 2024-11-18Bibliographically approved

Open Access in DiVA

Other links

Publisher's full textPubMed

Authority records

Wallner, Björn

Search in DiVA

By author/editor

Wallner, Björn

By organisation

BioinformaticsFaculty of Science & Engineering

In the same journal

Proteins: Structure, Function, and Bioinformatics

On the subject

Bioinformatics (Computational Biology)

Search outside of DiVA

GoogleGoogle ScholarTotal: 451 downloadsTotal: 165 hits