Efficient Generation of Epitope-Targeted De Novo Antibodies with Germinal

Learn about Germinal, a groundbreaking generative framework for designing antibodies against specific epitopes with nanomolar binding affinities in this research presentation. Discover how this computational method co-optimizes antibody structure and sequence by integrating a structure predictor with an antibody-specific protein language model to perform de novo design of functional complementarity-determining regions (CDRs) onto user-specified structural frameworks. Explore the experimental validation results showing success rates of 4-22% across four diverse protein targets while testing only 43-101 designs per antigen, demonstrating significant efficiency improvements over traditional antibody development methods. Examine how the validated nanobodies exhibited robust expression in mammalian cells and achieved nanomolar binding affinities, representing a major advancement in epitope-targeted de novo antibody design. Understand the methodology's potential implications for developing molecular tools and therapeutics, along with the availability of open-source code and comprehensive computational and experimental protocols to facilitate widespread adoption in the research community.