Optimizing Nanobody Sequence Design through Multi-Objective Engineering

Nanobodies, small single-domain antibodies, represent a promising class of protein therapeutics for treating cancer, autoimmune disorders, and infectious diseases. The successful development of nanobody therapeutics depends on designing nanobody sequences that simultaneously achieve critical physicochemical and biological attributes, including affinity, stability, selectivity, and solubility. Any inadequacy in one of these attributes can lead to the failure of nanobody therapeutic development. Simultaneously optimizing these attributes poses a significant scientific challenge due to inherent trade-offs -improving one attribute often compromises others. Additionally, the complex interdependencies among these attributes necessitate an iterative, trial-and-error approach that is time-consuming and resource-intensive, often delaying development timelines and increasing costs. This project aims to address these challenges through multi-objective engineering, leveraging advanced feature extraction and modeling capabilities to simultaneously predict and optimize critical developability attributes of nanobody sequences. We will first develop a multi-objective model for the simultaneous prediction of multiple developability attributes of nanobody sequences. Subsequently, we will establish an end-to-end multi- objective engineering system that integrates the multi-objective learning model with wet-lab experimentation in a co-evolution loop. Iterative feedback from laboratory results will continuously refine the predictive model, while the multi-objective model generates high-quality, selective sequence candidates for rapid laboratory evaluation, thereby enhancing both model accuracy and experimental outcomes. By integrating multiple objectives into a unified model early in the design process, this approach is expected to significantly reduce development time and costs while enhancing the overall success rate of nanobody therapeutics. Positioned at the intersection of AI and biology, this project will advance research capabilities, expand the scope and depth of interdisciplinary collaboration, and promote workforce development across various levels in both domains. Project Number: 1R16GM159671-01 | Fiscal Year: 2025 | NIH Institute/Center: National Institute of General Medical Sciences (NIGMS) | Principal Investigator: Haibo Yang | Institution: ROCHESTER INSTITUTE OF TECHNOLOGY, ROCHESTER, NY | Award Amount: $186,250 | Activity Code: R16 | Study Section: Special Emphasis Panel[ZGM1 RCB-7 (SF)] View on NIH RePORTER: https://reporter.nih.gov/project-details/11199442