Accurate structures of protein complexes are essential for understanding biological pathway function. A previous study showed how downstream modifications to AlphaFold 2 could yield AF2Complex, a model better suited for protein complexes. Here, we introduce AF3Complex, a model equipped with the same improvements as AF2Complex, along with a novel method for excluding ligands, built on AlphaFold 3.
Benchmarking AF3Complex and AlphaFold 3 on a large dataset of protein complexes, it was shown that AF3Complex outperforms AlphaFold 3 to a significant degree. Moreover, by evaluating the structures generated by AF3Complex on a dataset of protein-peptide complexes and antibody-antigen complexes, it was established that AF3Complex could create high-fidelity structures for these challenging complex types. Additionally, when deployed to generate structural predictions for the two antibody-antigen and seven protein-protein complexes used in the recent CASP16 competition, AF3Complex yielded structures that would have placed it among the top models in the competition.
Details described in the following publication:
Feldman, J, Skolnick J. 2025. AF3Complex Yields Improved Structural Predictions of Protein Complexes. bioRxiv 2025.02.27.640585; doi: https://doi.org/10.1101/2025.02.27.640585. PDF
Source Code
The AF3Complex source code is stored in the GitHub repository.
Note: This service is freely available to all academic and non-commercial users, only.
Questions and comments to Jonathan Feldman and Jeffrey Skolnick.