What has AlphaFold3 learned about antibody and nanobody docking, and what remains unsolved?
Hitawala, F. N.; Gray, J. J.
Show abstract
Antibody therapeutic development is a major focus in healthcare. To accelerate drug development, significant efforts have been directed towards the in silico design and screening of antibodies for which high modeling accuracy is necessary. To probe AlphaFold3s (AF3) capabilities and limitations, we tested AF3s ability to capture the fine details and interplay between antibody structure prediction and antigen docking accuracy. With one seed, AF3 achieves an 11.0% and 11.4% high-accuracy docking success rate for antibodies and nanobodies, respectively, and a median unbound CDR H3 RMSD accuracy of 2.73 [A] and 2.30 [A]. CDR H3 accuracy boosts complex prediction accuracy, with antigen context improving CDR H3 accuracy, particularly for loops longer than 15 residues. Combining I-pLDDT with {Delta}GB improves discriminative power for correctly docked complexes. However, AF3s 60% failure rate for antibody and nanobody docking (with single seed sampling) demonstrates necessary refinement to improve antibody design endeavors.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Evaluating Deep Learning Based Structure Prediction Methods on Antibody-Antigen Complexes 94%
- ParaSurf: A Surface-Based Deep Learning Approach for Paratope-Antigen Interaction Prediction 94%
- Rhapsody: Pathogenicity prediction of human missense variants based on protein sequence, structure and dynamics 94%
Similar papers in this journal
Similar papers in this journal
- Protein language model embeddings for fast, accurate, alignment-free protein structure prediction 95%
- ANTIPASTI: interpretable prediction of antibody binding affinity exploiting Normal Modes and Deep Learning 95%
- Computational pipeline provides mechanistic understanding of Omicron variant of concern neutralizing engineered ACE2 receptor traps 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.