Dataset Information

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

ABSTRACT: 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.

SUBMITTER: Lensink MF

PROVIDER: S-EPMC10841881 | biostudies-literature | 2023 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Lensink Marc F MF Brysbaert Guillaume G Raouraoua Nessim N Bates Paul A PA Giulini Marco M Honorato Rodrigo V RV van Noort Charlotte C Teixeira Joao M C JMC Bonvin Alexandre M J J AMJJ Kong Ren R Shi Hang H Lu Xufeng X Chang Shan S Liu Jian J Guo Zhiye Z Chen Xiao X Morehead Alex A Roy Raj S RS Wu Tianqi T Giri Nabin N Quadir Farhan F Chen Chen C Cheng Jianlin J Del Carpio Carlos A CA Ichiishi Eichiro E Rodriguez-Lumbreras Luis A LA Fernandez-Recio Juan J Harmalkar Ameya A Chu Lee-Shin LS Canner Sam S Smanta Rituparna R Gray Jeffrey J JJ Li Hao H Lin Peicong P He Jiahua J Tao Huanyu H Huang Sheng-You SY Roel-Touris Jorge J Jimenez-Garcia Brian B Christoffer Charles W CW Jain Anika J AJ Kagaya Yuki Y Kannan Harini H Nakamura Tsukasa T Terashi Genki G Verburgt Jacob C JC Zhang Yuanyuan Y Zhang Zicong Z Fujuta Hayato H Sekijima Masakazu M Kihara Daisuke D Khan Omeir O Kotelnikov Sergei S Ghani Usman U Padhorny Dzmitry D Beglov Dmitri D Vajda Sandor S Kozakov Dima D Negi Surendra S SS Ricciardelli Tiziana T Barradas-Bautista Didier D Cao Zhen Z Chawla Mohit M Cavallo Luigi L Oliva Romina R Yin Rui R Cheung Melyssa M Guest Johnathan D JD Lee Jessica J Pierce Brian G BG Shor Ben B Cohen Tomer T Halfon Matan M Schneidman-Duhovny Dina D Zhu Shaowen S Yin Rujie R Sun Yuanfei Y Shen Yang Y Maszota-Zieleniak Martyna M Bojarski Krzysztof K KK Lubecka Emilia A EA Marcisz Mateusz M Danielsson Annemarie A Dziadek Lukasz L Gaardlos Margrethe M Gieldon Artur A Liwo Adam A Samsonov Sergey A SA Slusarz Rafal R Zieba Karolina K Sieradzan Adam K AK Czaplewski Cezary C Kobayashi Shinpei S Miyakawa Yuta Y Kiyota Yasuomi Y Takeda-Shitaka Mayuko M Olechnovic Kliment K Valancauskas Lukas L Dapkunas Justas J Venclovas Ceslovas C Wallner Bjorn B Yang Lin L Hou Chengyu C He Xiaodong X Guo Shuai S Jiang Shenda S Ma Xiaoliang X Duan Rui R Qui Liming L Xu Xianjin X Zou Xiaoqin X Velankar Sameer S Wodak Shoshana J SJ

Proteins 20231031 12

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 ...[more]

PMID: 37905971

Similar Datasets

Project description:The ability to predict a protein's three-dimensional conformation represents a crucial starting point for investigating evolutionary connections with other members of the corresponding protein family, examining interactions with other proteins, and potentially utilizing this knowledge for the purpose of rational drug design. In this work, we evaluated the feasibility of improving AlphaFold2's three-dimensional protein predictions by developing a novel pipeline (AlphaMod) that incorporates AlphaFold2 with MODELLER, a template-based modeling program. Additionally, our tool can drive a comprehensive quality assessment of the tertiary protein structure by incorporating and comparing a set of different quality assessment tools. The outcomes of selected tools are combined into a composite score (BORDASCORE) that exhibits a meaningful correlation with GDT_TS and facilitates the selection of optimal models in the absence of a reference structure. To validate AlphaMod's results, we conducted evaluations using two distinct datasets summing up to 72 targets, previously used to independently assess AlphaFold2's performance. The generated models underwent evaluation through two methods: i) averaging the GDT_TS scores across all produced structures for a single target sequence, and ii) a pairwise comparison of the best structures generated by AlphaFold2 and AlphaMod. The latter, within the unsupervised setups, shows a rising accuracy of approximately 34% over AlphaFold2. While, when considering the supervised setup, AlphaMod surpasses AlphaFold2 in 18% of the instances. Finally, there is an 11% correspondence in outcomes between the diverse methodologies. Consequently, AlphaMod's best-predicted tertiary structures in several cases exhibited a significant improvement in the accuracy of the predictions with respect to the best models obtained by AlphaFold2. This pipeline paves the way for the integration of additional data and AI-based algorithms to further improve the reliability of the predictions.

Dataset Information

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

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets