Skip to main content
padlock icon - secure page this page is secure

Open Access Many Molecular Properties from One Kernel in Chemical Space

Download Article:
 Download
(PDF 965.2 kb)
 
We introduce property-independent kernels for machine learning models of arbitrarily many molecular properties. The kernels encode molecular structures for training sets of varying size, as well as similarity measures sufficiently diffuse in chemical space to sample over all training molecules. When provided with the corresponding molecular reference properties, they enable the instantaneous generation of machine learning models which can be systematically improved through the addition of more data. This idea is exemplified for single kernel based modeling of internal energy, enthalpy, free energy, heat capacity, polarizability, electronic spread, zero-point vibrational energy, energies of frontier orbitals, HOMO-LUMO gap, and the highest fundamental vibrational wavenumber. Models of these properties are trained and tested using 112,000 organic molecules of similar size. The resulting models are discussed as well as the kernels' use for generating and using other property models.

20 References.

No Supplementary Data.
No Article Media
No Metrics

Keywords: CHEMICAL SPACE; KERNEL RIDGE REGRESSION; MACHINE LEARNING; MOLECULAR PROPERTIES; QUANTUM CHEMISTRY

Document Type: Research Article

Affiliations: 1: Institute of Physical Chemistry and National Center for Computational Design and Discovery of Novel Materials (MARVEL), Department of Chemistry, University of Basel, Klingelbergstrasse 80, CH-4056 Basel, Switzerland 2: Institute of Physical Chemistry and National Center for Computational Design and Discovery of Novel Materials (MARVEL), Department of Chemistry, University of Basel, Klingelbergstrasse 80, CH-4056 Basel, Switzerland; Argonne Leadership Computing Facility, Argonne National Laboratory, 9700 S. Cass Avenue, Lemont, IL 60439, USA. [email protected]

Publication date: April 1, 2015

More about this publication?
  • International Journal for Chemistry and Official Membership Journal of the Swiss Chemical Society (SCS) and its Divisions

    CHIMIA, a scientific journal for chemistry in the broadest sense, is published 10 times a year and covers the interests of a wide and diverse readership. Contributions from all fields of chemistry and related areas are considered for publication in the form of Review Articles and Notes. A characteristic feature of CHIMIA are the thematic issues, each devoted to an area of great current significance.

  • Editorial Board
  • Information for Authors
  • Subscribe to this Title
  • Information for Advertisers
  • Ingenta Connect is not responsible for the content or availability of external websites
  • Access Key
  • Free content
  • Partial Free content
  • New content
  • Open access content
  • Partial Open access content
  • Subscribed content
  • Partial Subscribed content
  • Free trial content
Cookie Policy
X
Cookie Policy
Ingenta Connect website makes use of cookies so as to keep track of data that you have filled in. I am Happy with this Find out more