Impact of AlphaFold on structure prediction of protein complexes: The CASP15‐CAPRI experiment - Université de Lille Accéder directement au contenu
Article Dans Une Revue Proteins - Structure, Function and Bioinformatics Année : 2023

Impact of AlphaFold on structure prediction of protein complexes: The CASP15‐CAPRI experiment

Marc Lensink (1) , Guillaume Brysbaert (1) , Nessim Raouraoua (1) , Paul A. Bates (2) , Marco Giulini (3) , Rodrigo V. Honorato (3) , Charlotte van Noort (3) , Joao M. C. Teixeira (3) , Alexandre M. J. J. Bonvin (3) , Ren Kong (4) , Hang Shi (4) , Xufeng Lu (4) , Shan Chang (4) , Jian Liu (5) , Zhiye Guo (5) , Xiao Chen (5) , Alex Morehead (5) , Raj S. Roy (5) , Tianqi Wu (5) , Nabin Giri (5) , Farhan Quadir (5) , Chen Chen (5) , Jianlin Cheng (5) , Carlos A. del Carpio , Eichiro Ichiishi (6) , Luis A. Rodriguez‐lumbreras (7, 8) , Juan Fernandez‐recio (7, 8) , Ameya Harmalkar (9) , Lee‐shin Chu (9) , Sam Canner (9) , Rituparna Smanta (9) , Jeffrey J. Gray (9, 10) , Hao Li (11) , Peicong Lin (11) , Jiahua He (11) , Huanyu Tao (11) , Sheng‐you Huang (11) , Jorge Roel‐touris , Brian Jimenez‐garcia , Charles W. Christoffer (12) , Anika J. Jain (13) , Yuki Kagaya (13) , Harini Kannan (14, 13) , Tsukasa Nakamura (13) , Genki Terashi (13) , Jacob C. Verburgt (13) , Yuanyuan Zhang (12) , Zicong Zhang (12) , Hayato Fujuta (14) , Masakazu Sekijima (15) , Daisuke Kihara (12, 13) , Omeir Khan (16) , Sergei Kotelnikov (17) , Usman Ghani (16) , Dzmitry Padhorny (17) , Dmitri Beglov (16) , Sandor Vajda (16) , Dima Kozakov (17) , Surendra S. Negi (18) , Tiziana Ricciardelli (19) , Didier Barradas‐bautista (19) , Zhen Cao (19) , Mohit Chawla (19) , Luigi Cavallo (19, 20) , Romina Oliva (21) , Rui Yin (22) , Melyssa Cheung (22) , Johnathan D. Guest (22) , Jessica Lee (22) , Brian G. Pierce (22) , Ben Shor (23) , Tomer Cohen (23) , Matan Halfon (23) , Dina Schneidman‐duhovny (23) , Shaowen Zhu (24) , Rujie Yin (24) , Yuanfei Sun (24) , Yang Shen (24) , Martyna Maszota‐zieleniak , Krzysztof K. Bojarski , Emilia A. Lubecka , Mateusz Marcisz , Annemarie Danielsson , Lukasz Dziadek , Margrethe Gaardlos , Artur Gieldon , Adam Liwo , Sergey A. Samsonov , Rafal Slusarz , Karolina Zieba , Adam K. Sieradzan , Cezary Czaplewski , Shinpei Kobayashi (25) , Yuta Miyakawa (25) , Yasuomi Kiyota (25) , Mayuko Takeda‐shitaka (25) , Kliment Olechnovic (26) , Lukas Valancauskas (26) , Justas Dapkunas (26) , Ceslovas Venclovas (26) , Bjorn Wallner (27) , Lin Yang (28, 29) , Chengyu Hou (29) , Xiaodong He (29) , Shuai Guo (29) , Shenda Jiang (29) , Xiaoliang Ma (29) , Rui Duan (30) , Liming Qui (30) , Xianjin Xu (30) , Xiaoqin Zou (30) , Sameer Velankar (31) , Shoshana J. Wodak (32)
1 UGSF - Unité de Glycobiologie Structurale et Fonctionnelle - UMR 8576
2 Biomolecular Modelling laboratory [London]
3 Bijvoet Center for Biomolecular Research [Utrecht]
4 Jiangsu University of Technology [Changzhou]
5 EECS - Department of Electrical Engineering and Computer Science [Columbia]
6 IUHW Hospital - International University of Health and Welfare Hospital
7 BSC-CNS - Barcelona Supercomputing Center - Centro Nacional de Supercomputacion
8 ICVV - Instituto de Ciencias de la Vid y el Vino
9 JHU - Johns Hopkins University
10 Program in Molecular Biophysics [Baltimore]
11 HUST - Huazhong University of Science and Technology [Wuhan]
12 Department of Computer Science [Purdue]
13 Department of Biological Sciences [West Lafayette]
14 IIT Madras - Indian Institute of Technology Madras
15 TITECH - Tokyo Institute of Technology [Tokyo]
16 BU - Boston University [Boston]
17 SBU - Stony Brook University [SUNY]
18 UTMB - The University of Texas Medical Branch
19 KAUST - King Abdullah University of Science and Technology [Saudi Arabia]
20 UNISA - Università degli Studi di Salerno = University of Salerno
21 PARTHENOPE - Università degli Studi di Napoli “Parthenope” = University of Naples
22 University of Maryland [College Park]
23 HUJ - The Hebrew University of Jerusalem
24 Texas A&M University [College Station]
25 Kitasato University
26 Institute of Biotechnology [Vilnius]
27 LIU - Linköping University
28 The University of Sydney
29 HIT - Harbin Institute of Technology
30 Mizzou - University of Missouri [Columbia]
31 EMBL-EBI - European Bioinformatics Institute [Hinxton]
32 VIB-VUB Center for Structural Biology [Bruxelles]
Carlos A. del Carpio
  • Fonction : Auteur
Jorge Roel‐touris
  • Fonction : Auteur
Brian Jimenez‐garcia
  • Fonction : Auteur
Martyna Maszota‐zieleniak
  • Fonction : Auteur
Krzysztof K. Bojarski
  • Fonction : Auteur
Emilia A. Lubecka
  • Fonction : Auteur
Mateusz Marcisz
  • Fonction : Auteur
Annemarie Danielsson
  • Fonction : Auteur
Lukasz Dziadek
  • Fonction : Auteur
Margrethe Gaardlos
  • Fonction : Auteur
Artur Gieldon
  • Fonction : Auteur
Adam Liwo
  • Fonction : Auteur
Sergey A. Samsonov
  • Fonction : Auteur
Rafal Slusarz
  • Fonction : Auteur
Karolina Zieba
  • Fonction : Auteur
Adam K. Sieradzan
  • Fonction : Auteur
Cezary Czaplewski
  • Fonction : Auteur

Résumé

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 ~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.
Fichier principal
Vignette du fichier
P23.38 Lensink-capri-casp-2023.pdf (7.97 Mo) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-04279362 , version 1 (10-11-2023)

Licence

Identifiants

Citer

Marc Lensink, Guillaume Brysbaert, Nessim Raouraoua, Paul A. Bates, Marco Giulini, et al.. Impact of AlphaFold on structure prediction of protein complexes: The CASP15‐CAPRI experiment. Proteins - Structure, Function and Bioinformatics, 2023, Proteins - Structure, Function and Bioinformatics, ⟨10.1002/prot.26609⟩. ⟨hal-04279362⟩

Collections

CNRS UNIV-LILLE
25 Consultations
16 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More