Determining the three-dimensional structures of protein-peptide complexes is crucial for elucidating biological processes and designing peptide-based drugs. Protein-peptide docking has become essential for predicting complex structures. AlphaFold-Multimer, ColabFold, and AlphaFold3 provided groundbreaking tools to enhance the protein-peptide docking accuracy. This study evaluates these three tools for predicting protein-peptide complex structures using template-based (TB) and template-free (TF) methods. AlphaFold-Multimer excels in TB predictions and performs moderately in TF scenarios in the prediction pool, but TF outperforms TB in the first-ranked models. ColabFold demonstrates versatility in both TB and TF settings. AlphaFold3 generates high-quality structures for more proteins, but the medium accuracy is not as good as AlphaFold-Multimer using a large model pool. We also assessed the performance of various scoring functions in ranking predicted protein-peptide complex structures. While the scoring function built in AlphaFold demonstrates the best performance, some other scoring functions, e.g., FoldX-Stability and HADDOCK-mdscore, provide complementary values. The findings suggest the potential for enhancing scoring functions targeting AlphaFold-based predictions by combining multiple scoring functions or using a consensus approach from many prediction models.
Manshour et al. (Thu,) studied this question.