Benchmarking all-atom biomolecular structure prediction with FoldBench
Top Cited Papers
Open Access
- 4 December 2025
- journal article
- research article
- Published by Springer Nature in Nature Communications
- Vol. 17 (1)
Abstract
Accurate prediction of biomolecular complex structures is fundamental for understanding biological processes and rational therapeutic design. Recent advances in deep learning methods, particularly all-atom structure prediction models, have significantly expanded their capabilities to include diverse biomolecular entities, such as proteins, nucleic acids, ligands, and ions. However, comprehensive benchmarks covering multiple interaction types and molecular diversity remain scarce, limiting fair and rigorous assessment of model performance and generalizability. To address this gap, we introduce FoldBench, an extensive benchmark dataset consisting of 1522 biological assemblies categorized into nine distinct prediction tasks. Our evaluations reveal critical performance dependencies, showing that ligand docking accuracy notably diminishes as ligand similarity to the training set decreases, a pattern similarly observed in protein-protein interaction modeling. Furthermore, antibody-antigen predictions remain particularly challenging, with current methods exhibiting failure rates exceeding 50%. Among evaluated models, AlphaFold 3 consistently demonstrates superior accuracy across the majority of tasks. In summary, our results highlight significant advancements yet reveal persistent limitations within the field, providing crucial insights and benchmarks to inform future model development and refinement.Keywords
This publication has 46 references indexed in Scilit:
- PepPCBench is a Comprehensive Benchmarking Framework for Protein–Peptide Complex Structure PredictionJournal of Chemical Information and Modeling, 2025
- Assessment of protein–ligand complexes in CASP15Proteins: Structure, Function, and Bioinformatics, 2023
- Development of allosteric and selective CDK2 inhibitors for contraception with negative cooperativity to cyclin bindingNature Communications, 2023
- AI models for protein design are driving antibody engineeringCurrent Opinion in Biomedical Engineering, 2023
- BenchmarkingAlphaFoldfor protein complex modeling reveals accuracy determinantsProtein Science, 2022
- AutoDock Vina: Improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreadingJournal of Computational Chemistry, 2009
- Analysis and improvements to Kabat and structurally correct numbering of antibody variable domainsMolecular Immunology, 2008
- Protein–ligand docking: Current status and future challengesProteins: Structure, Function, and Bioinformatics, 2006
- RNA structure: the long and the short of itCurrent Opinion in Structural Biology, 2005
- Canonical structures for the hypervariable regions of immunoglobulinsJournal of Molecular Biology, 1987