QSAR models for ACE-inhibitor activity of tri-peptides based on representation of the molecular structure by graph of atomic orbitals and SMILES

A. P. Toropova, A. A. Toropov, B. F. Rasulev, E. Benfenati, G. Gini, D. Leszczynska, J. Leszczynski

Research output: Contribution to journalArticlepeer-review

Abstract

The CORAL software (http:/www.insilico.eu/CORAL) has been examined as a tool of modeling of the angiotensin-converting enzyme-inhibitor activity of 54 tripeptides. Three versions of the models were examined: (i) models based on the graph of atomic orbitals (GAO); (ii) models based on the simplified molecular input-line entry systems (SMILES); and (iii) hybrid models based on both GAO and SMILES. The hybrid models have provided the best prediction. The robustness of the approach has been checked with four random splits into training set and test set.

Original languageEnglish
Pages (from-to)1873-1878
Number of pages6
JournalStructural Chemistry
Volume23
Issue number6
DOIs
Publication statusPublished - Dec 2012

Keywords

  • ACE-inhibitory activity
  • CORAL software
  • QSAR
  • SMILES
  • Validation

ASJC Scopus subject areas

  • Condensed Matter Physics
  • Physical and Theoretical Chemistry

Fingerprint

Dive into the research topics of 'QSAR models for ACE-inhibitor activity of tri-peptides based on representation of the molecular structure by graph of atomic orbitals and SMILES'. Together they form a unique fingerprint.

Cite this