Rational polymer design is impeded by the “curse of dimensionality” since numerous design variables such as polymer composition, architecture, length and formulation parameters are involved. Intuition-based methods of pattern recognition cannot alleviate challenges arising from a complex multidimensional design space. Ramya has employed machine learning algorithms to build predictive models that shed light on the roles played by polymer design attributes such as polymer phase behavior, basicity, surface charge, nucleic acid binding, and hydrophobicity in shaping biological responses such as cellular uptake, payload delivery and cytotoxicity. Statistical learning helped Ramya zero in on the molecular attributes of the hit polymers that promoted highly efficient gene editing efficiency and apply this knowledge to provide experimental guidance for the design of subsequent generations of polymer libraries. Check out Ramya’s talk on applying data-driven methodologies to gene delivery below.