Predicting DNA origami stability in physiological media by machine learning

DNA origami nanostructures offer substantial potential as programmable, biocompatible platforms for drug delivery and diagnostics. However, their structural stability under physiological conditions remains a major barrier to practical applications. Stability assessment of DNA origami nanostructures has traditionally relied on image-based and empirical approaches, which are time-consuming and difficult to generalize across conditions. To address these limitations, we developed a machine learning approach for DNA origami stability prediction, based on measurable physicochemical parameters. Using dynamic light scattering (DLS) to quantify diffusion coefficients as a proxy for structural integrity, we characterized over 1400 DNA origami samples under varying physiologically relevant variables: temperature, incubation time, MgCl ₂ concentration, pH, and DNase I concentrations. The predictive performance of the model was confirmed using an independent set of samples under previously untested conditions. This data-driven approach offers a scalable and generalizable framework to guide the design of robust DNA nanostructures for biomedical applications.