Molecular Characterization


Machine-readable representations, descriptors, and features of molecules are vital for constructing statistical and machine learning models for chemical property prediction. In C-CAS, we use experimental data from spectroscopic techniques such as FTIR, UV-Vis, NMR, and mass spectrometry to construct and develop molecular representations.


  • Jie Xu, Samantha Grosslight, Kyle A. Mack, Sierra C. Nguyen, Kyle Clagg, Ngiap-Kie Lim, Jacob C. Timmerman, Jeff Shen, Nicholas A. White, Lauren E. Sirois, Chong Han, Haiming Zhang*, Matthew S. Sigman*, and Francis Gosselin. Atroposelective Negishi Coupling Optimization Guided by Multivariate Linear Regression Analysis: Asymmetric Synthesis of KRAS G12C Covalent Inhibitor GDC-6036. J. Am. Chem. Soc. 2022, 144, 45, 20955-20963.

  • Sigmund LM, Sowndarya S, Albers A, Erdmann P, Paton RS, Greb L. Predicting Lewis Acidity: Machine‐Learning the Fluoride Ion Affinity of p‐Block‐Atom‐based Molecules. Angewandte Chemie International Edition. 2024 Mar 7:e202401084.