CAPRI: A Critical Assessment of PRedicted Interactions

By Joël Janin, K. Henrick, John Moult, L. T. Eyck, Michael J.E. Sternberg, Sandor Vajda, Ilya A. Vakser, Shoshana J. Wodak. Proteins: Structure, Function, and Bioinformatics, 2003

678 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Language and Linguistics, Philosophy

View Paper: https://www.semanticscholar.org/paper/1b4e7359562b005cfe58d48bcf9e35f1597a667e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Language and Linguistics

In Philosophy

Citations in the corpus

Outcome of a Workshop on Applications of Protein Models in Biomedical Research (2009, background): “Despite remaining challenges, the results of the Critical Assessment of Predicted Interactions (CAPRI) effort (Janin et al., 2003) demonstrate that substantial progress in docking methods has been made during the last few years (Lensink et al., 2007).”
The Immune Epitope Database and Analysis Resource: From Vision to Blueprint (2005, background): “Such prediction “contests” have had a tremendous positive impact in the fi eld of tool evaluation and prediction of protein structure [3,4].”
Updates to the integrated protein-protein interaction benchmarks: Docking benchmark version 5 and affinity benchmark version 2 (2015, methodology): “These complexes were then filtered using various quality criteria: (1) the complex structure needed to be determined by X-ray crystallography, the unbound structures by either X-ray crystallography or NMR; (2) the sequence identity between bound and unbound chains needed to be at least 96% with an a”
Templates are available to model nearly all complexes of structurally characterized proteins (2012, methodology): “Benchmarking of the predictive approaches, based on the X-ray structures in PDB or on those available in blind experiments, like critical assessment of structure prediction (9) and CAPRI (7), has its limitations.”
An iterative knowledge‐based scoring function for protein–protein recognition (2008, methodology): “In the present work, the prediction quality was judged with the criteria used in the CAPRI (Critical Assessment of PRedicted Interactions) contest,68,69 which involve three parameters, f nat , L rms , and I rms .”
HawkDock: a web server to predict and analyze the protein–protein complex based on computational docking and MM/GBSA (2019, background): “When I RMSD is 4 ˚A or L RMSD is 10 ˚A, the prediction is considered to be successful (44).”
Protein Docking Model Evaluation by Graph Neural Networks (2020, methodology): “DOVE captures atoms and interaction energies of atoms located at the interface of a docking model using a cube of 203 or 403 Å3 and judges if the model is correct or incorrect according to the CAPRI criteria (34).”
SnugDock: Paratope Structural Optimization during Antibody-Antigen Docking Compensates for Errors in Antibody Homology Models (2010, background): “In CAPRI rounds 1–18, eleven of the forty targets involved docking of at least one homology modeled partner (both partners were homology models for Target 35) [43–45].”
Benchmarking AlphaFold for protein complex modeling reveals accuracy determinants (2021, background): “18 However, the Critical Assessment of Predicted Interactions (CAPRI) blind docking prediction experiment 19 and several protein docking benchmarks, 20,21 which have enabled the systematic assessment of predictive docking performance, revealed persistent shortcomings of current computational…”