Combinatorial Optimization of Antibody Libraries via Constrained Integer Programming

Conor F. Hayes, Andre R Goncalves, Steven Magana-Zook, Jacob Pettit, Ahmet Can Solak, Daniel faissol, Mikel Landajuela

Keywords: Combinatorial Optimization, Integer Programming, Antibody Library Design, Diversity Constraints, Search and Planning Algorithms, Protein Language Models, Deep Mutational Scanning

TL;DR: We propose a novel integer linear programming (ILP) method for antibody library design that explicitly controls diversity and affinity objectives.

Abstract: Designing effective antibody libraries is a challenging combinatorial search problem in computational biology. We propose a novel integer linear programming (ILP) method that explicitly controls diversity and affinity objectives when generating candidate libraries. Our approach formulates library design as a constrained optimization: we encode diversity parameters and predicted binding scores (from in silico deep mutational scanning and protein language models) as ILP constraints and objectives. This enables automated search for high-quality, diverse antibody sequences under explicit experimental constraints. We demonstrate the method on cold-start design tasks for Trastuzumab, D44.1, and Spesolimab, showing that our optimized libraries outperform baseline designs in both predicted affinity and sequence diversity. This hybrid search-and-learning framework illustrates how constrained optimization and predictive modeling can be combined to deliver interpretable, high-quality solutions to antibody library engineering.

Area: Innovative Applications (IA)

Generative A I: I acknowledge that I have read and will follow this policy.

Submission Number: 528