Identifying applicability domains for quantitative structure property relationships

Mordechai Shacham, Neima Brauner, Georgi St. Cholakov, Roumiana P. Stateva

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

2 Scopus citations


Development of Quantitative Structure Property Relationships (QSPR) for property prediction, targeted for a particular applicability domain (AD), and definition of the AD boundaries are considered. The AD is defined in terms of the target compound (for which a property has to be predicted) belonging to a homologous series and including carbon atoms above a particular number. If the target compound satisfies these requirements simple linear QSPR, with one or two descriptors are shown to predict the property within experimental error level. The method presented can also identify the cases where lack of experimental data can prevent derivation of a reliable QSPR.

Original languageEnglish
Title of host publication17th European Symposium on Computer Aided Process Engineering
EditorsValentin Plesu, Paul Serban Agachi
Number of pages6
StatePublished - 1 Dec 2007

Publication series

NameComputer Aided Chemical Engineering
ISSN (Print)1570-7946


  • Homologous series
  • Molecular descriptors
  • Property prediction
  • QSPR

ASJC Scopus subject areas

  • General Chemical Engineering
  • Computer Science Applications


Dive into the research topics of 'Identifying applicability domains for quantitative structure property relationships'. Together they form a unique fingerprint.

Cite this