Classification of Src Kinase Inhibitors Based on Support Vector Machine

In this work, the support vector machine (SVM), an effective machine learning method, was employed to make a distinction within a class of Src kinase inhibitors. The minimum redundancy maximum relevance (mRMR) feature selection method was used to remove redundant variables, then sequential forward selection (SFS) and sequential backward selection (SBS) methods were used to extract informative features. It had been demonstrated that sequential forward selection (SFS) and sequential backward selection (SBS) methods were useful tools for variable selection. As a special cross-validation method, leave one out cross validation (LOOCV) method was used to test the generalization and reliability of the model obtained. By using the SVM, the support vector classification (SVC) model was obtained, with a classification accuracy of 94%. And the prediction accuracy of activities of the Src kinase inhibitors is 92.4% in LOOCV method. The results show that SVM method could be employed to SAR modeling with much improved quality and predictability.

[1]  Wencong Lu,et al.  Using support vector regression for the prediction of the band gap and melting point of binary and ternary compound semiconductors , 2006 .

[2]  Milan Randic,et al.  Novel Shape Descriptors for Molecular Graphs , 2001, J. Chem. Inf. Comput. Sci..

[3]  Harry P. Schultz,et al.  Topological organic chemistry. 1. Graph theory and topological indices of alkanes , 1989, J. Chem. Inf. Comput. Sci..

[4]  Özge Uncu,et al.  A novel feature selection approach: Combining feature wrappers and filters , 2007, Inf. Sci..

[5]  A. Balaban.  Highly discriminating distance-based topological index , 1982 .

[6]  Fei Ye,et al.  7-Alkoxy-4-phenylamino-3-quinolinecar-bonitriles as dual inhibitors of Src and Abl kinases. , 2004, Journal of medicinal chemistry.

[7]  J. Kittler,et al.  Feature Set Search Alborithms , 1978 .

[8]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[9]  Yan Wang,et al.  Further studies on ethenyl and ethynyl-4-phenylamino-3-quinolinecarbonitriles: identification of a subnanomolar Src kinase inhibitor. , 2005, Bioorganic & medicinal chemistry letters.

[10]  D. Boschelli,et al.  Inhibition of Src kinase activity by 7-ethynyl-4-phenylamino-3-quinolinecarbonitriles: identification of SKS-927. , 2007, Bioorganic & medicinal chemistry letters.

[11]  Bernard F. Buxton,et al.  Drug Design by Machine Learning: Support Vector Machines for Pharmaceutical Data Analysis , 2001, Comput. Chem..

[12]  G. Gallick,et al.  Src family kinases in tumor progression and metastasis , 2003, Cancer and Metastasis Reviews.

[13]  Tingjun Hou,et al.  Mapping the Binding Site of a Large Set of Quinazoline Type EGF-R Inhibitors Using Molecular Field Analyses and Molecular Docking Studies , 2003, J. Chem. Inf. Comput. Sci..

[14]  D. Boschelli,et al.  Synthesis and Src kinase inhibitory activity of a series of 4-phenylamino-3-quinolinecarbonitriles. , 2001, Journal of medicinal chemistry.

[15]  S. Courtneidge.  Role of Src in Signal Transduction Pathways , 2001 .

[16]  Allan Bradley,et al.  Targeted disruption of the c-src proto-oncogene leads to osteopetrosis in mice , 1991, Cell.

[17]  D. Boschelli,et al.  Optimization of 4-phenylamino-3-quinolinecarbonitriles as potent inhibitors of Src kinase activity. , 2001, Journal of medicinal chemistry.

[18]  D. Boschelli,et al.  Inhibitors of src tyrosine kinase: the preparation and structure-activity relationship of 4-anilino-3-cyanoquinolines and 4-anilinoquinazolines. , 2000, Bioorganic & medicinal chemistry letters.

[19]  B. Narasimhan,et al.  Synthesis, antimicrobial, and QSAR studies of substituted benzamides. , 2007, Bioorganic & medicinal chemistry.

[20]  Michael Chopp,et al.  Src deficiency or blockade of Src activity in mice provides cerebral protection following stroke , 2001, Nature Medicine.

[21]  Ram Thaimattam,et al.  3D-QSAR studies on c-Src kinase inhibitors and docking analyses of a potent dual kinase inhibitor of c-Src and c-Abl kinases. , 2005, Bioorganic & medicinal chemistry.

[22]  Wencong Lu,et al.  Predicting Anti‐HIV‐1 Activities of HEPT‐analog Compounds by Using Support Vector Classification , 2005 .

[23]  Biye Ren,et al.  A New Topological Index for QSPR of Alkanes , 1999, J. Chem. Inf. Comput. Sci..

[24]  D. Boschelli,et al.  7-(aryl/heteroaryl-2-ylethynyl)-4-phenylamino-3-quinolinecarbonitriles as new Src kinase inhibitors: addition of water solubilizing groups. , 2006, Bioorganic & medicinal chemistry letters.

[25]  Fuhui Long,et al.  Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy , 2003, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[26]  Fei Ye,et al.  Synthesis and inhibition of Src kinase activity by 7-ethenyl and 7-ethynyl-4-anilino-3-quinolinecarbonitriles. , 2004, Bioorganic & medicinal chemistry letters.

[27]  Rajarshi Guha,et al.  Development of Linear, Ensemble, and Nonlinear Models for the Prediction and Interpretation of the Biological Activity of a Set of PDGFR Inhibitors , 2004, J. Chem. Inf. Model..

[28]  Kuo-Chen Chou,et al.  Support Vector Machine for predicting α-turn types , 2003, Peptides.

[29]  S. Courtneidge,et al.  Src family tyrosine kinases and growth factor signaling. , 2000, Experimental cell research.

[30]  Yu-Dong Cai,et al.  Predicting N-terminal acetylation based on feature selection method. , 2008, Biochemical and biophysical research communications.

[31]  Lemont B. Kier,et al.  Electrotopological State Indices for Atom Types: A Novel Combination of Electronic, Topological, and Valence State Information , 1995, J. Chem. Inf. Comput. Sci..

[32]  Wei Kong,et al.  QSAR analysis of tyrosine kinase inhibitor using modified ant colony optimization and multiple linear regression. , 2007, European journal of medicinal chemistry.

[33]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .