Docking With Rosetta and Deep Learning Approaches in CAPRI Rounds 47–55
Authors:
- 22 September 2025
- journal article
- Published by Wiley in Proteins: Structure, Function, and Bioinformatics
- Vol. 94 (11) , 1836-1850
Abstract
Critical Assessment of PRediction of Interactions (CAPRI) rounds 47 through 55 introduced 49 targets comprising multistage assemblies, antibody–antigen complexes, and flexible interfaces. For these rounds, we combined various Rosetta docking approaches (RosettaDock, ReplicaDock, and SymDock) with deep learning approaches (AlphaFold2, IgFold, and AlphaRED). Since prior CAPRI rounds, we have developed methods to better capture conformational changes, updated our scoring function, and integrated structure prediction tools such as AlphaFold2 in our docking routines. Here, we highlight several notable CAPRI targets and address the major challenges in the blind prediction of protein–protein interactions, including binding‐induced conformational changes, large multimeric proteins, and antibody–antigen interactions. Although predictors have achieved modest improvements in accuracy for simpler targets post‐AlphaFold2, performance for more flexible complexes remains limited. We employed RosettaDock 4.0, ReplicaDock 2.0, and AlphaRED to enhance backbone conformational sampling for flexible complexes. Our docking routines improved the DockQ score (0.77 vs. 0.62 for AF2‐multimer) for a GP2 bacteriophage protein (T194), effectively capturing binding‐induced conformational changes. Additionally, we introduce a fold‐and‐dock approach for predicting the assembly of a surface‐layer SAP protein derived from Bacillus anthracis (T160), a large hetero‐multimer comprising six distinct sub‐units. For large symmetric complexes, we used Rosetta‐based SymDock 2.0, successfully predicting a human DNA repair protein complex with A10 stoichiometry (T230) with high CAPRI‐quality ranking. We also address the challenges in modeling antibody/nanobody‐antigen interactions, particularly through the integration of deep learning tools and docking methods. Despite advances with tools like IgFold and AlphaFold2, accurately predicting CDR H3 loops and antibody–antigen binding interfaces remains challenging. Combining ReplicaDock 2.0 with deep learning highlights these difficulties and underscores the need for extensive sampling and CDR‐focused strategies to improve prediction accuracy.Keywords
All Related Versions
Funding Information
- National Institutes of Health
This publication has 49 references indexed in Scilit:
- Flexible protein–protein docking with a multitrack iterative transformerProtein Science, 2024
- Crystal structure of Nsp15 endoribonuclease NendoU from SARS‐CoV‐2Protein Science, 2020
- The challenge of modeling protein assemblies: the CASP12‐CAPRI experimentProteins: Structure, Function, and Bioinformatics, 2017
- Modeling oblong proteins and water‐mediated interfaces with RosettaDock in CAPRI rounds 28–35Proteins: Structure, Function, and Bioinformatics, 2016
- Extending RosettaDock with water, sugar, and pH for prediction of complex structures and affinities for CAPRI rounds 20–27Proteins: Structure, Function, and Bioinformatics, 2013
- A generalized approach to sampling backbone conformations with RosettaDock for CAPRI rounds 13–19Proteins: Structure, Function, and Bioinformatics, 2010
- Sub-angstrom modeling of complexes between flexible peptides and globular proteinsProteins: Structure, Function, and Bioinformatics, 2010
- Incorporating biochemical information and backbone flexibility in RosettaDock for CAPRI rounds 6–12Proteins: Structure, Function, and Bioinformatics, 2007
- CAPRI rounds 3–5 reveal promising successes and future challenges for RosettaDockProteins: Structure, Function, and Bioinformatics, 2005
- Protein–protein docking predictions for the CAPRI experimentProteins: Structure, Function, and Bioinformatics, 2003