Integrative modeling in the age of machine learning: a summary of
HADDOCK strategies in CAPRI rounds 47-55
- Victor Reys,
- Marco Giulini,
- Vlad Cojocaru,
- Anna Engel,
- Xiaotong Xu,
- Jorge Roel,
- Cunliang Geng,
- Francesco Ambrosetti,
- Brian Jimenes-Garcia,
- Zuzana Jandova,
- Panagiotis I. Koukos,
- Charlotte van Noort,
- João Teixeira,
- Siri C. van Keulen,
- Manon Reau,
- Rodrigo Vargas Honorato,
- Alexandre M.J.J. Bonvin
Marco Giulini
Universiteit Utrecht Departement Scheikunde
Author ProfileVlad Cojocaru
Universiteit Utrecht Departement Scheikunde
Author ProfileCunliang Geng
Universiteit Utrecht Departement Scheikunde
Author ProfileFrancesco Ambrosetti
Universiteit Utrecht Departement Scheikunde
Author ProfileBrian Jimenes-Garcia
Universiteit Utrecht Departement Scheikunde
Author ProfileZuzana Jandova
Universiteit Utrecht Departement Scheikunde
Author ProfilePanagiotis I. Koukos
Universiteit Utrecht Departement Scheikunde
Author ProfileCharlotte van Noort
Universiteit Utrecht Departement Scheikunde
Author ProfileJoão Teixeira
Universiteit Utrecht Departement Scheikunde
Author ProfileSiri C. van Keulen
Universiteit Utrecht Departement Scheikunde
Author ProfileRodrigo Vargas Honorato
Universiteit Utrecht Departement Scheikunde
Author ProfileAlexandre M.J.J. Bonvin
Universiteit Utrecht Departement Scheikunde
Corresponding Author:a.m.j.j.bonvin@uu.nl
Author ProfileAbstract
The HADDOCK team participated in CAPRI rounds 47-55 as both server,
manual predictor, and scorers. Throughout these CAPRI rounds, we used a
plethora of computational strategies to predict the structure of protein
complexes. Of the 10 targets comprising 24 interfaces, we achieved
acceptable or better models for 3 targets in the human category and 1 in
the server category. Our performance in the scoring challenge was
slightly better, with our simple scoring protocol being the only one
capable of identifying an acceptable model for Target 234. This result
highlights the robustness of the simple, fully physics-based HADDOCK
scoring function, especially when applied to highly flexible
antibody-antigen complexes. Inspired by the significant advances in
machine learning for structural biology and the dramatic improvement in
our success rates after the public release of Alphafold2, we identify
the integration of classical approaches like HADDOCK with AI-driven
structure prediction methods as a key strategy for improving the
accuracy of model generation and scoring.16 Sep 2024Submitted to PROTEINS: Structure, Function, and Bioinformatics 18 Sep 2024Submission Checks Completed
18 Sep 2024Assigned to Editor
18 Sep 2024Review(s) Completed, Editorial Evaluation Pending
09 Oct 2024Reviewer(s) Assigned
25 Oct 2024Editorial Decision: Revise Minor
12 Nov 20241st Revision Received
15 Nov 2024Submission Checks Completed
15 Nov 2024Assigned to Editor
15 Nov 2024Review(s) Completed, Editorial Evaluation Pending
15 Nov 2024Reviewer(s) Assigned
09 Dec 2024Editorial Decision: Revise Minor
12 Dec 20242nd Revision Received
13 Dec 2024Submission Checks Completed
13 Dec 2024Assigned to Editor
13 Dec 2024Review(s) Completed, Editorial Evaluation Pending
13 Dec 2024Reviewer(s) Assigned
16 Dec 2024Editorial Decision: Accept