This Phase I SBIR project seeks to demonstrate a design-build-test-learn (DBTL) system for engineering nanocarriers (NCs) able to deliver molecular cargo across the blood-brain barrier (BBB) via receptor-mediated transport (RMT). The approach relies heavily on in silico design and characterization of NCs, with the ultimate goal of predicting BBB permeability of a given NC design with machine learning (ML) models. Molecular dynamics and computational chemistry methods will be developed to digitally characterize NC designs. NCs of different shape and size will be designed and labeled with either or both of two different RMT peptides. Labeled designs and unlabeled controls will be digitally characterized, synthesized and tested for BBB permeability in an established in vitro BBB model. These assay results will be used in combination with design parameters as data for eventual ML training. Design parameters that promote BBB permeability will be derived from statistical analysis and from feature importance analysis of the resulting ML models. Feasibility of the approach will be established through the ability to rapidly design, build, and test candidate NCs in the limited timeframe of a Phase I project. Armed with these capabilities, in Phase II, the affect of size, shape, hydrophobicity, type and number of RMT ligands and other NC design parameters will be assessed via combinatorial in silico and in vitro evaluation. Highly ranked NCs with promising in vitro BBB permeability will be evaluated in vivo with the goal of generating data to support an IND application with the FDA.
