Pre-Conference Workshops (pm only) and Training Course (full day)Sunday, 14 December 2025 - PT (Pacific Time, GMT-08:00)

Optimizing antibodies for efficacy requires careful consideration of several factors, including biology, modality selection, ADME (adsorption, distribution, metabolism, and excretion) and developability. In this workshop, I will provide an overview of these topics and share examples to highlight their importance.

Implementing high throughput developability workflows early in biologics generation guides optimized lead selection. Addressing sequence liabilities, chemical modifications, immunogenicity, and biophysical issues accelerates development and reduces failures. Complex formats like antibody-drug conjugates and bispecifics pose challenges requiring tailored strategies for successful developability and clinical outcomes.

Immunogenicity of biopharmaceuticals can affect their safety and efficacy. Mitigation of this risk should start early in development, at the drug design phase. This presentation discusses incorporating advanced in silico and in vitro de-immunisation tools into protein engineering processes to select a lead candidate that balances immunogenicity risk and desired biophysical properties.

Therapeutic antibody design is a complex multi-property optimization problem that traditionally relies on expensive search through sequence space. In this talk, I will introduce “Lab-in-the-loop,” a new approach to antibody design that orchestrates generative machine learning models, multi-task property predictors, active learning ranking and selection, and in vitro experimentation in a semi-autonomous, iterative optimization loop.

The development, delivery, and efficacy of therapeutic antibodies are strongly influenced by multiple types of molecular interactions mediated by their variable regions, including both specific and non-specific interactions. Here we report interpretable machine-learning models for identifying high-affinity mAbs with optimal combinations of low off-target binding and low self-association, and demonstrate that these co-optimal antibodies display drug-like properties both in vitro and in vivo.

BigHat Biosciences uses AI/ML and a high speed automated wet lab to rapidly design and optimize safer, more effective therapeutic antibodies. Our platform combines machine learning with experimental data to iteratively improve candidates based on key properties such as affinity, function, and developability. We've leveraged our platform to create antibodies with enhanced functionality, such as pH selectivity, logic gating, and avidity-optimized T cell engagement, demonstrating the power of AI/ML to overcome key challenges in antibody development.