Project Title: Big-Data-driven prediction of toxicity of nanomedicine
Research overview. Emerging nanotechnology uses nanoscale materials for medical purposes such as diagnosis, controlled drug delivery, and sensing in a living organism. Though great progress has been achieved in nanomedicine, its toxicity is a significant concern and poorly understood. Current assessment methods, typically using many test animals, are very slow and costly. According to the National Toxicology Program, the preferred approach to addressing chemical toxicity is developing a predictive scientific model that focuses on target-specific, mechanistic observations such as computer-based predictive toxicology models. Big-data and machine learning techniques are bringing us revolutionary tools. PR-CLIMB participants will carry out large scale computations (including first principles, QM/MM, and molecular dynamics) to examine the physicochemical parameters of various nanoparticles (NPs), probe their interactions with important biological systems, and use available experimental toxicity data by machine learning and big data approaches. These efforts will help identify ways to minimize nanomedicine toxicity..
Skills/Techniques: PR-CLIMB participants will benefit from the wealth of knowledge that Chen’s 20+ years’ experiences in computational chemistry and computational materials science (with over 300 papers) have generated. They will actively be involved in the experimental design for NP toxicology profiling.