Predicting DNA origami stability in physiological media by machine learning
Zubia-Aranburu, J.; Gardin, A.; Paffen, L.; Tollemeto, M.; Alberdi, A.; Termenon, M.; Grisoni, F.; Patino Padial, T.
Show abstract
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, MgCl2 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.
Matching journals
The top 2 journals account for 50% of the predicted probability mass.