Sigma profiles in deep learning: towards a universal molecular descriptor.

Journal: Chemical communications (Cambridge, England)
Published Date: May 5, 2022

Abstract

This work showcases the remarkable ability of sigma profiles to function as molecular descriptors in deep learning. The sigma profiles of 1432 compounds are used to train convolutional neural networks that accurately correlate and predict a wide range of physicochemical properties. The architectures developed are then exploited to include temperature as an additional feature.

Authors

  • Dinis O Abranches
    Department of Chemical and Biomolecular Engineering, University of Notre Dame, Notre Dame, Indiana 46556, USA. ycolon@nd.edu.
  • Yong Zhang
    Outpatient Department of Hepatitis, The Sixth Affiliated People's Hospital of Dalian Medical University, Dalian, Liaoning, China.
  • Edward J Maginn
    Department of Chemical and Biomolecular Engineering, University of Notre Dame, Notre Dame, Indiana 46556, United States.
  • Yamil J Colón
    Department of Chemical and Biomolecular Engineering, University of Notre Dame, Notre Dame, Indiana 46556, USA. ycolon@nd.edu.

Keywords

External Resources

Popular Topics
Recent Journals