Todd, M.M., Harten, P., Douglas, M.Y., Muratov, E.N., Golbraikh, A., Zhu, H. and Tropsha, A. (2012) Does Rational Selection of Training and Test Sets Improve the Outcome of QSAR Modeling? Journal of Chemical Information and Modeling, 52, 2570-2578.
http://dx.doi.org/10.1021/ci300338w

has been cited by the following article:

• TITLE: Quantitative Structure Activity Relationship Analysis of Selected Chalcone Derivatives as Mycobacterium tuberculosis Inhibitors

  AUTHORS: Alisi Ikechukwu Ogadimma, Uzairu Adamu

  KEYWORDS: Anti-Tuberculosis, Descriptors, GFA, Model Validation, QSAR

  JOURNAL NAME: Open Access Library Journal, Vol.3 No.3, March 14, 2016

  ABSTRACT: In order to gain further insights into the structural requirements for anti-tuberculosis activity by chalcone derivatives of 1,3-diphenylprop-2-ene-1-one, quantitative structure activity relationship (QSAR) was performed using genetic function approximation (GFA). Geometry optimization was achieved at the density functional theory (DFT) level using Becke’s three-parameter Lee-Yang-Parr hybrid functional (B3LYP) in combination with the 6-31G* basis set. Subsequently, quantum chemical and molecular descriptors were generated and divided into training and test sets by Kennard Stone algorithm. Internal and external validations as well as Y-randomization tests were employed in model validation. Five predictive models were generated by GFA. The generated models showed that constitutional indices, 2D autocorrelations and radial distribution function (RDF) descriptors were important contributors to anti-tuberculosis activity of 1,3-diphenylprop-2-ene-1-one derivatives. Based on validation results, model 4 was chosen as the best of the five models.