Abstract
In the last several decades, the drug research has moved to involve various IT technologies in order to rationalize the design of novel bioactive chemical compounds. An important role among these computer-aided drug design (CADD) methods is played by a technique known as quantitative structure-activity relationship (QSAR). The approach is utilized to find a statistically significant model correlating the biological activity with more or less extent data derived from the chemical structures. The present article deals with approaches for discriminating unimportant information in the data input within the three dimensional variant of QSAR – 3D QSAR. Special attention is turned to uninformative and iterative variable elimination (UVE/IVE) methods applicable in connection with partial least square regression (PLS). Herein, we briefly introduce 3D QSAR approach by analyzing 30 antituberculotics. The analysis is examined by four UVE/IVE-PLS based data-noise reduction methods.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Brown, A.C., Fraser, T.R.: XX.—On the Connection between Chemical Constitution and Physiological Action. Part II.—On the Physiological Action of the Ammonium Bases derived from Atropia and Conia. Trans. Roy. Soc. Edinburgh 25, 693–739 (1869)
Hansch, C., Fujita, T.: ρ-σ-π Analysis. A method for the correlation of biological activity and chemical structure. J. Am. Chem. Soc. 86, 1616–1626 (1964)
Free, S.M., Wilson, J.W.: A mathematical contribution to structure-activity studies. J. Med. Chem. 7, 395–399 (1964)
Cramer Iii, R.D.: Partial least squares (PLS): its strengths and limitations. Perspect. Drug. Discov. 1, 269–278 (1993)
Dolezal, R., Korabecny, J., Malinak, D., Honegr, J., Musilek, K., Kuca, K.: Ligand-based 3D QSAR analysis of reactivation potency of mono- and bis-pyridinium aldoximes toward VX-inhibited rat acetylcholinesterase. J. Mol. Graph. Model. 56c, 113–129 (2014)
Tropsha, A., Gramatica, P., Gombar, V.K.: The importance of being earnest: validation is the absolute essential for successful application and interpretation of QSPR models. QSAR Comb. Sci. 22, 69–77 (2003)
Chuang, Y.C., Chang, C.H., Lin, J.T., Yang, C.N.: Molecular modelling studies of sirtuin 2 inhibitors using three-dimensional structure-activity relationship analysis and molecular dynamics simulations. Mol. Biosyst. 11, 723–733 (2015)
Kastenholz, M.A., Pastor, M., Cruciani, G., Haaksma, E.E., Fox, T.: GRID/CPCA: a new computational tool to design selective ligands. J. Med. Chem. 43, 3033–3044 (2000)
Bro, R., Elden, L.: PLS works. J. Chemometr. 23, 69–71 (2009)
Centner, V., Massart, D.L., de Noord, O.E., de Jong, S., Vandeginste, B.M., Sterna, C.: Elimination of uninformative variables for multivariate calibration. Anal. Chem. 68, 3851–3858 (1996)
Polanski, J., Gieleciak, R.: The comparative molecular surface analysis (CoMSA) with modified uniformative variable elimination-PLS (UVE-PLS) method: application to the steroids binding the aromatase enzyme. J. Chem. Inf. Comp. Sci. 43, 656–666 (2003)
Gieleciak, R., Polanski, J.: Modeling robust QSAR. 2. iterative variable elimination schemes for CoMSA: application for modeling benzoic acid pKa values. J. Chem. Inf. Model. 47, 547–556 (2007)
Mehmood, T., Liland, K.H., Snipen, L., Sæbø, S.: A review of variable selection methods in partial least squares regression. Chemometr. Intel. Lab. 118, 62–69 (2012)
Pastor, M., Cruciani, G., Clementi, S.: Smart region definition: a new way to improve the predictive ability and interpretability of three-dimensional quantitative structure-activity relationships. J. Med. Chem. 40, 1455–1464 (1997)
Dolezal, R., Waisser, K., Petrlikova, E., Kunes, J., Kubicova, L., Machacek, M., Kaustova, J., Dahse, H.M.: N-Benzylsalicylthioamides: Highly Active Potential Antituberculotics. Arch. Pharm. 342, 113–119 (2009)
Waisser, K., Matyk, J., Kunes, J., Dolezal, R., Kaustova, J., Dahse, H.M.: Highly Active Potential Antituberculotics: 3-(4-Alkylphenyl)-4-thioxo-2H-1,3-benzoxazine-2(3H)-ones and 3-(4-Alkylphenyl)-2H-1,3-benzoxazine-2,4(3H)-dihiones Substituted in Ring-B by Halogen. Archiv Der Pharmazie 341, 800–803 (2008)
Tosco, P., Balle, T., Shiri, F.: Open3DALIGN: an open-source software aimed at unsupervised ligand alignment. J. Comput. Aid. Mol. Des. 25, 777–783 (2011)
Tosco, P., Balle, T.: Open3DQSAR: a new open-source software aimed at high-throughput chemometric analysis of molecular interaction fields. J. Mol. Model. 17, 201–208 (2011)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Dolezal, R. et al. (2015). Variable Elimination Approaches for Data-Noise Reduction in 3D QSAR Calculations. In: Pereira, F., Machado, P., Costa, E., Cardoso, A. (eds) Progress in Artificial Intelligence. EPIA 2015. Lecture Notes in Computer Science(), vol 9273. Springer, Cham. https://doi.org/10.1007/978-3-319-23485-4_33
Download citation
DOI: https://doi.org/10.1007/978-3-319-23485-4_33
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-23484-7
Online ISBN: 978-3-319-23485-4
eBook Packages: Computer ScienceComputer Science (R0)