Adapting ProteinMPNN for antibody design without retraining
del Alamo, D.; Frick, R.; Truan, D.; Karpiak, J. D.
Show abstract
The neural network ProteinMPNN designs protein sequences capable of folding into predefined tertiary structures and quaternary assemblies. It has become widely used due to its high success rates when working with synthetic topologies rich in secondary structure. Here, we show degraded performance on the complementarity-determining regions (CDRs) of antibodies, with designs frequently failing to resemble native antibodies or failing to refold into the designed conformations. We also show that this underperformance can be rescued by ensembling its predictions with those from the antibody-specific protein language model AbLang, which designs exclusively using sequence information learned from large databases of antibody sequences. Finally, we tested 96 trastuzumab variants with CDRH3 loops redesigned by the ensembled ProteinMPNN+AbLang method and found that it generated thirty-six HER2 binders, compared to three out of 96 designs generated by ProteinMPNN alone. The data highlight the value of incorporating additional restraints derived from language models during structure-based sequence design of antibodies.
Matching journals
The top 8 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
Similar papers in this journal
- Two sequence- and two structure-based ML models have learned different aspects of protein biochemistry 94%
- Protein embeddings and deep learning predict binding residues for various ligand classes 94%
- Exploring the ability of the MD+FoldX method to predict SARS-CoV-2 antibody escape mutations using large-scale data 93%
Similar papers in this journal
- Contextualising the developability risk of antibodies with lambda light chains using enhanced therapeutic antibody profiling 95%
- Biophysical cartography of the native and human-engineered antibody landscapes quantifies the plasticity of antibody developability 94%
- Real-Time Structure Search and Structure Classification for AlphaFold Protein Models 93%
"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.