Machine Learning Reveals Amine Type in Polymer Micelles Determines mRNA Binding, <i>In Vitro, and In Vivo</i> Performance for Lung-Selective Delivery

Cationic micelles, composed of amphiphilic block copolymers with polycationic coronas, offer a customizable platform for mRNA delivery. Here, we present a library of 30 cationic micelle nanoparticles (MNPs) formulated from diblock copolymers with reactive poly(pentafluorophenol acrylate) backbones modified with diverse amines. This library systematically varies in nitrogen-based cationic functionalities, exhibiting a spectrum of properties that encompass varied degrees of alkyl substitution (A1-A5), piperazine (A6), oligoamine (A7), guanidinium (A8), and hydroxylation (A9-A10) that vary in side-chain volume, substitution pattern, hydrophilicity, and p<i>K</i> _a to assess parameter impact on mRNA delivery. <i>In vitro</i> delivery assays using GFP+ mRNA across multiple cell lines reveal that amine side-chain bulk and chemical structure critically affect performance. Using machine learning analysis via SHapley Additive exPlanations (SHAP) on 180 formulations (3780 experimental measurements), we mapped key relationships between amine chemistry and performance metrics, finding that amine-specific binding efficiency was a major determinant of mRNA delivery efficacy, cell viability, and GFP intensity. Micelles with stronger mRNA binding capabilities (A1 and A7) have higher cellular delivery performance, whereas those with intermediate binding tendencies deliver a higher amount of functional mRNA per cell (A2, A10). This indicates that balancing the binding strength is crucial for performance. Micelles with hydrophobic and bulky pendant groups (A3-A5) tend to induce necrosis during cellular delivery, highlighting the significance of chemical optimization. A7 amphiphile, displaying primary and secondary amine, consistently demonstrates the highest GFP expression across various cell types and <i>in vivo</i> achieves high delivery specificity to lung tissue upon intravenous administration. Moreover, we established a strong correlation between <i>in vitro</i> and <i>in vivo</i> performance using Multitask Gaussian Process models, underscoring the predictive power of <i>in vitro</i> models for anticipating <i>in vivo</i> outcomes. Overall, this innovative study integrates advanced data science with experimental design, demonstrating the pivotal role of chemical amine-dependent optimization for advancing targeted mRNA delivery to the lungs.