AntBO: Towards Real-World Automated Antibody Design with Combinatorial Bayesian Optimisation

Antibodies are canonically Y-shaped multimeric proteins capable of highly specific molecular recognition. The CDRH3 region located at the tip of variable chains of an antibody dominates antigen-binding specificity. Therefore, it is a priority to design optimal antigen-specific CDRH3 regions to develop therapeutic antibodies. However, the combinatorial nature of CDRH3 sequence space makes it impossible to search for an optimal binding sequence exhaustively and efficiently using computational approaches. Here, we present textttAntBO: a combinatorial Bayesian optimisation framework enabling efficient textitin silico design of the CDRH3 region. Ideally, antibodies are expected to have high target specificity and developability. We introduce a CDRH3 trust region that restricts the search to sequences with favourable developability scores to achieve this goal. For benchmarking, textttAntBO uses the textttAbsolut! software suite as a black-box oracle to score the target specificity and affinity of designed antibodies textitin silico in an unconstrained fashion~citeprobert2021one. The experiments performed for 159 discretised antigens used in textttAbsolut! demonstrate the benefit of textttAntBO in designing CDRH3 regions with diverse biophysical properties. In under 200 calls to black-box oracle, textttAntBO can suggest antibody sequences that outperform the best binding sequence drawn from 6.9 million experimentally obtained CDRH3s and a commonly used genetic algorithm baseline. Additionally, textttAntBO finds very-high affinity CDRH3 sequences in only 38 protein designs whilst requiring no domain knowledge. We conclude textttAntBO brings automated antibody design methods closer to what is practically viable for in vitro experimentation.