Research Explorer

Project

Chemical property prediction using spectral-signature Kriging of molecular surface topology
Code
01SF2415
Duration
01 December 2015 → 30 November 2019
Funding
Regional and community funding: Special Research Fund
Research disciplines
  • Natural sciences
    • Artificial intelligence
    • Inorganic chemistry
    • Organic chemistry
    • Physical chemistry
    • Theoretical and computational chemistry
    • Other chemical sciences
  • Social sciences
    • Cognitive science and intelligent systems
Keywords
3D-QSAR Kriging Chemical Property Prediction Computer-Aided Molecular Design
 
Project description

The combinatorial complexity of chemical space makes finding a molecule with desired properties challenging. This is compounded by the fact some properties are difficult to measure and impossible to compute. To surmount these limitations, I am developing a new machine-learning technique called spectral-signature kriging that is fast, robust, and universal.