Next Article in Journal
Altered Expression of Signaling Genes in Jurkat Cells upon FTY720 Induced Apoptosis
Next Article in Special Issue
3D-QSAR and Molecular Docking Studies on Fused Pyrazoles as p38α Mitogen-Activated Protein Kinase Inhibitors
Previous Article in Journal
Sol Gel-Derived SBA-16 Mesoporous Material
Previous Article in Special Issue
A Review on Progress in QSPR Studies for Surfactants
Int. J. Mol. Sci. 2010, 11(9), 3052-3068; doi:10.3390/ijms11093052

2D Quantitative Structure-Property Relationship Study of Mycotoxins by Multiple Linear Regression and Support Vector Machine

2,*  and 3
1 Food and Drug Laboratory Research Center, MOH & ME, Tehran, Iran 2 Department of Chemistry, Faculty of Sciences, K.N., Toosi University of Technology, Tehran 16617, Iran 3 Faculty of Chemistry, Razi University, Kermanshah, Iran
* Author to whom correspondence should be addressed.
Received: 6 July 2010 / Revised: 15 August 2010 / Accepted: 16 August 2010 / Published: 31 August 2010
(This article belongs to the Special Issue Recent Advances in QSAR/QSPR Theory)
View Full-Text   |   Download PDF [610 KB, uploaded 19 June 2014]   |   Browse Figures


In the present work, support vector machines (SVMs) and multiple linear regression (MLR) techniques were used for quantitative structure–property relationship (QSPR) studies of retention time (tR) in standardized liquid chromatography–UV–mass spectrometry of 67 mycotoxins (aflatoxins, trichothecenes, roquefortines and ochratoxins) based on molecular descriptors calculated from the optimized 3D structures. By applying missing value, zero and multicollinearity tests with a cutoff value of 0.95, and genetic algorithm method of variable selection, the most relevant descriptors were selected to build QSPR models. MLRand SVMs methods were employed to build QSPR models. The robustness of the QSPR models was characterized by the statistical validation and applicability domain (AD). The prediction results from the MLR and SVM models are in good agreement with the experimental values. The correlation and predictability measure by r2 and q2 are 0.931 and 0.932, repectively, for SVM and 0.923 and 0.915, respectively, for MLR. The applicability domain of the model was investigated using William’s plot. The effects of different descriptors on the retention times are described.
Keywords: QSPR; mycotoxins; SVM; MLR; genetic algorithm; William’s Plot QSPR; mycotoxins; SVM; MLR; genetic algorithm; William’s Plot
This is an open access article distributed under the Creative Commons Attribution License (CC BY) which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Share & Cite This Article

Further Mendeley | CiteULike
Export to BibTeX |
EndNote |
MDPI and ACS Style

Khosrokhavar, R.; Ghasemi, J.B.; Shiri, F. 2D Quantitative Structure-Property Relationship Study of Mycotoxins by Multiple Linear Regression and Support Vector Machine. Int. J. Mol. Sci. 2010, 11, 3052-3068.

View more citation formats

Related Articles

Article Metrics

For more information on the journal, click here


[Return to top]
Int. J. Mol. Sci. EISSN 1422-0067 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert