< Back to previous page
Project
Chemical property prediction using spectral-signature Kriging of molecular surface topology
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.
Date:1 Dec 2015 → 30 Nov 2019
Keywords:3D-QSAR, Kriging, Chemical Property Prediction, Computer-Aided Molecular Design
Disciplines:Cognitive science and intelligent systems, Organic chemistry, Artificial intelligence, Other chemical sciences, Physical chemistry, Inorganic chemistry, Theoretical and computational chemistry