Exploring QSARs for Antiviral Activity of 4-Alkylamino-6-(2-hydroxyethyl)-2-methylthiopyrimidines by Support Vector Machine
作者： Siavash Riahi , Eslam Pourbasheer , Rassoul Dinarvand , Mohammad Reza Ganjali , Parviz Norouzi
DOI: 10.1111/J.1747-0285.2008.00695.X
关键词: Genetic algorithm 、 Machine learning 、 Mathematics 、 Support vector machine 、 Quantitative structure–activity relationship 、 Linear model 、 Pattern recognition 、 Statistical parameter 、 Linear regression 、 Artificial intelligence 、 Test set 、 Correlation 、 Molecular medicine 、 Biochemistry
摘要: The support vector machine, which is a novel algorithm from the machine learning community, was used to develop quantitative structure activity relationship models predict antiviral of 4-alkylamino-6-(2-hydroxyethyl)-2-methylthiopyrimidines. genetic employed select variables that resulted in best-fitted models. A comparison between obtained results using with those multiple linear regression revealed model much better than regression. root mean square errors training set and test for were calculated be 0.102 0.205, correlation coefficients (r2) 0.956 0.852, respectively. Furthermore, statistical parameter leave-one-out (LOO) leave-group-out (LGO) cross-validation on 0.893 0.881, respectively, prove reliability this model. suggest branching, volume lipophilicity are main independent factors contributing activities studied compounds.
sci-hub.se 参考文章(40)
Shandar Ahmad, M. Michael Gromiha, Design and training of a neural network for predicting the solvent accessibility of proteins. Journal of Computational Chemistry. ,vol. 24, pp. 1313- 1320 ,(2003) , 10.1002/JCC.10298
R. Burbidge, M. Trotter, B. Buxton, S. Holden, Drug design by machine learning: support vector machines for pharmaceutical data analysis. Computational Biology and Chemistry. ,vol. 26, pp. 5- 14 ,(2001) , 10.1016/S0097-8485(01)00094-8
H. X. Liu, R. S. Zhang, X. J. Yao, M. C. Liu, Z. D. Hu, B. T. Fan, Prediction of the isoelectric point of an amino acid based on GA-PLS and SVMs. Journal of Chemical Information and Computer Sciences. ,vol. 44, pp. 161- 167 ,(2004) , 10.1021/CI034173U
Chris L. Waller, Mary P. Bradley, Development and Validation of a Novel Variable Selection Technique with Application to Multidimensional Quantitative Structure−Activity Relationship Studies Journal of Chemical Information and Computer Sciences. ,vol. 39, pp. 345- 355 ,(1999) , 10.1021/CI980405R
Samantha Cooray, Jennifer M. Best, Li Jin, Time-course induction of apoptosis by wild-type and attenuated strains of rubella virus. Journal of General Virology. ,vol. 84, pp. 1275- 1279 ,(2003) , 10.1099/VIR.0.18785-0
AA Moosavi‐Movahedi, S Safarian, GH Hakimelahi, G Ataei, D Ajloo, S Panjehpour, S Riahi, MF Mousavi, S Mardanyan, N Soltani, A Khalafi‐Nezhad, H Sharghi, H Moghadamnia, AA Saboury, None, QSAR Analysis for ADA upon Interaction with a Series of Adenine Derivatives as Inhibitors Nucleosides, Nucleotides & Nucleic Acids. ,vol. 23, pp. 613- 624 ,(2004) , 10.1081/NCN-120030719
Jianzhong Liu, Liu Yang, Effect of cholesterol on DMPC phospholipid membranes and QSAR model construction in membrane-interaction QSAR study through molecular dynamics simulation Bioorganic & Medicinal Chemistry. ,vol. 14, pp. 2225- 2234 ,(2006) , 10.1016/J.BMC.2005.11.009
Mohammad Hossein Fatemi, Sajjad Gharaghani, A novel QSAR model for prediction of apoptosis-inducing activity of 4-aryl-4-H-chromenes based on support vector machine Bioorganic & Medicinal Chemistry. ,vol. 15, pp. 7746- 7754 ,(2007) , 10.1016/J.BMC.2007.08.057
Wenjian Wang, Zongben Xu, Weizhen Lu, Xiaoyun Zhang, Determination of the spread parameter in the Gaussian kernel for classification and regression Neurocomputing. ,vol. 55, pp. 643- 663 ,(2003) , 10.1016/S0925-2312(02)00632-X
Rajeshwar P. Verma, Alka Kurup, Corwin Hansch, On the role of polarizability in QSAR. Bioorganic & Medicinal Chemistry. ,vol. 13, pp. 237- 255 ,(2005) , 10.1016/J.BMC.2004.09.039