Therapy based on personalized medicine has become a leading strategy to treat cancer. Small molecule drugs such as kinase inhibitors, which target key effectors of cancer signaling pathways, constitute a major component of this strategy. This class of inhibitors inhabits a diverse chemical space, however, making it difficult to develop nanomedicines against the wide set of precision drug targets. We are developing machine learning processes to predict and facilitate the encapsulation of diverse drug classes into nanoparticles based on the molecular structures of the drugs. We devised quantitative structure-nanoparticle assembly prediction models to identify and validate electrotopological molecular descriptors as highly predictive indicators of nano-assembly and nanoparticle size. The resulting nanoparticles selectively targeted kinase inhibitors to caveolin-1-expressing RAS-driven human colon cancer and autochthonous liver cancer models to yield striking therapeutic effects while avoiding dose-limiting toxicities. This work enables the computational design of nanomedicines based on quantitative models for drug payload selection.

Development of targeted nanomedicines facilitated by nanoinformatics

2019 Fall National Meeting

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.