Drug/nondrug classification using Support Vector Machines with various feature selection strategies

Computer Methods and Programs in Biomedicine

Volumn 117, Issue 2, 2014, Pages 51-60

  Korkmaz, Selcuk ^a   Zararsiz, Gokmen ^a   Goksuluk, Dincer ^a  

^a HACETTEPE UNIVERSITY   (Turkey)

Author keywords

Drug discovery; Feature selection; Machine learning; Molecular descriptors; Support vector machines

Indexed keywords

CORRELATION METHODS; DATA HANDLING; FEATURE EXTRACTION; LEARNING SYSTEMS; MOLECULES;

CLASSIFICATION TASKS; COMPOUND COLLECTIONS; DRUG DISCOVERY; FEATURE SELECTION METHODS; MACHINE LEARNING APPLICATIONS; MOLECULAR DESCRIPTORS; PEARSON'S CORRELATION COEFFICIENTS; RECURSIVE FEATURE ELIMINATION;

SUPPORT VECTOR MACHINES;

ACEBUTOLOL; FENOLDOPAM; LABETALOL; MONTELUKAST; NORADRENALIN; SALAZOSULFAPYRIDINE; SALBUTAMOL; DRUG; PROTEIN BINDING; TUMOR PROTEIN;

AREA UNDER THE CURVE; ARTICLE; CONTROLLED STUDY; DATA ANALYSIS; DRUG CLASSIFICATION; DRUG DEVELOPMENT; GENETIC ALGORITHM; KERNEL METHOD; MOLECULAR LIBRARY; PHARMACOPHORE; PREDICTIVE VALUE; RECEIVER OPERATING CHARACTERISTIC; SENSITIVITY AND SPECIFICITY; SUPPORT VECTOR MACHINE; ALGORITHM; AUTOMATED PATTERN RECOGNITION; BINDING SITE; CHEMISTRY; CLASSIFICATION; DRUG DESIGN; PROCEDURES; PROTEIN ANALYSIS;

ALGORITHMS; BINDING SITES; DRUG DESIGN; NEOPLASM PROTEINS; PATTERN RECOGNITION, AUTOMATED; PHARMACEUTICAL PREPARATIONS; PROTEIN BINDING; PROTEIN INTERACTION MAPPING; SUPPORT VECTOR MACHINES;

EID: 84907969343     PISSN: 01692607     EISSN: 18727565     Source Type: Journal    
DOI: 10.1016/j.cmpb.2014.08.009     Document Type: Article

References (95)

1. Jones S.D., Warren P.D. Drug Discovery and Development 2006, John Wiley and Sons, New Jersey. M.S. Chorghade (Ed.).
2. Rester U. From virtuality to reality - virtual screening in lead discovery and lead optimization: a medicinal chemistry perspective. Curr. Opin. Drug Discov. Devel. 2008, 11:559-568.
3. Rollinger J.M., Hermann S., Thierry L. Natural Compounds as Drugs 2008, vol. I. Birkhäuser, Basel.
4. Byvatov E., et al. Comparison of support vector machine and artificial neural network systems for drug/nondrug classification. J. Chem. Inf. Comput. Sci. 2003, 43:1882-1889.
5. Chen B., et al. Evaluation of machine-learning methods for ligand-based virtual screening. J. Comput. Aided Mol. Des. 2007, 21:53-62.
6. García-Sosa A.T., et al. DrugLogit: logistic discrimination between drugs and nondrugs including disease-specificity by assigning probabilities based on molecular properties. J. Chem. Inf. Model. 2012, 52:2165-2180.
7. Lipinski C.A., et al. Experimental and computational approaches to estimate solubility and permeability in drug discovery and development settings. Adv. Drug Deliv. Rev. 2001, 46:3-26.
8. Hou T., et al. ADME evaluation in drug discovery. 6. Can oral bioavailability in humans be effectively predicted by simple molecular property-based rules?. J. Chem. Inf. Model. 2007, 47:460-463.
9. Hou T., et al. ADME evaluation in drug discovery. 7. Prediction of oral absorption by correlation and classification. J. Chem. Inf. Model. 2007, 47:208-218.
10. Tian S., et al. ADME evaluation in drug discovery. 9. Prediction of oral bioavailability in humans based on molecular properties and structural fingerprints. Mol. Pharm. 2011, 8:841-851.
11. Ajay A., Walters W.P., Murcko M.A. Can we learn to distinguish between "drug-like" and "nondrug-like" molecules?. J. Med. Chem. 1998, 41:3314-3324.
12. Sadowski J., Kubinyi H. A scoring scheme for discriminating between drugs and nondrugs. J. Med. Chem. 1998, 41:3325-3329.
13. Clark D.E., Pickett S.D. Computational methods for the prediction of 'drug-likeness'. Drug Discov. Today 2000, 5:49-58.
14. Ajay Predicting drug-likeness: why and how?. Curr. Top. Med. Chem. 2002, 2:1273-1286.
15. Muegge I. Selection criteria for drug-like compounds. Med. Res. Rev. 2003, 23:302-321.
16. Shen M., et al. Drug-likeness analysis of traditional Chinese medicines: 1. Property distributions of drug-like compounds, non-drug-like compounds and natural compounds from traditional Chinese medicines. J. Cheminform. 2012, 4:31.
17. Tian S., et al. Drug-likeness analysis of traditional Chinese medicines: prediction of drug-likeness using machine learning approaches. Mol. Pharmacol. 2012, 9:2875-2886.
18. Tian S., et al. Drug-likeness analysis of traditional Chinese medicines: 2. Characterization of scaffold architectures for drug-like compounds, non-drug-like compounds, and natural compounds from traditional Chinese medicines. J. Cheminform. 2013, 5:5.
19. Oprea T.I., et al. Is there a difference between leads and drugs? A historical perspective. J. Chem. Inf. Comput. Sci. 2001, 41:1308-1315.
20. Ritchie T.J., Macdonald S.J.F. The impact of aromatic ring count on compound developability - are too many aromatic rings a liability in drug design?. Drug Discov. Today 2009, 14:1011-1020.
21. Chen H., Yang Y., Engkvist O. Molecular topology analysis of the differences between drugs, clinical candidate compounds, and bioactive molecules. J. Chem. Inf. Model. 2010, 50:2141-2150.
22. Bemis G.W., Murcko M.A. The properties of known drugs. 1. Molecular frameworks. J. Med. Chem. 1996, 39:2887-2893.
23. Yang Y., et al. Investigation of the relationship between topology and selectivity for druglike molecules. J. Med. Chem. 2010, 53:7709-7714.
24. Gillet V.J., Willett P., Bradshaw J. Identification of biological activity profiles using substructural analysis and genetic algorithms. J. Chem. Inf. Comput. Sci. 1998, 38:165-179.
25. Gálvez J., de Julián-Ortiz J.V., García-Domenech R. General topological patterns of known drugs. J. Mol. Graph. Model. 2001, 20:84-94.
26. Batista J., Bajorath J. Mining of randomly generated molecular fragment populations uncovers activity-specific fragment hierarchies. J. Chem. Inf. Model. 2007, 47:1405-1413.
27. Hu Y., Bajorath J. Scaffold distributions in bioactive molecules, clinical trials compounds, and drugs. Chem. Med. Chem. 2010, 5:187-190.
28. Ursu O., et al. Understanding drug-likeness. WIREs Comput. Mol. Sci. 2011, 1:760-781.
29. Heikamp K., Bajorath J. Support vector machines for drug discovery. Expert Opin. Drug Discov. 2014, 9:93-104.
30. Wang J., Hou T. Drug and drug candidate building block analysis. J. Chem. Inf. Model. 2010, 50:55-67.
31. Schneider N., et al. Gradual in silico filtering for druglike substances. J. Chem. Inf. Model. 2008, 48:613-628.
32. Gärtner T., Flach P., Wrobel S. Learning Theory and Kernel Machines 2003, Springer, Berlin. 1st ed. M.K. Warmuth, B. Schölkopf (Eds.).
33. Kashima H., Tsuda K., Inokuchi A. Marginalized kernels between labeled graphs. Proceedings of the Twentieth International Conference on Machine Learning 2003, 321-328.
34. Mahé P., et al. Graph kernels for molecular structure-activity relationship analysis with support vector machines. J. Chem. Inf. Model. 2005, 45:939-951.
35. Ralaivola L., et al. Graph kernels for chemical informatics. Neural Netw. 2005, 18:1093-1110.
36. Mahé P., et al. The pharmacophore kernel for virtual screening with support vector machines. J. Chem. Inf. Model. 2006, 46:2003-2014.
37. Mohr J.A., Jain B.J., Obermayer K. Molecule kernels: a descriptor-and alignment-free quantitative structure-activity relationship approach. J. Chem. Inf. Model. 2008, 48:1868-1881.
38. Azencott C.A., et al. One-to four-dimensional kernels for virtual screening and the prediction of physical, chemical, and biological properties. J. Chem. Inf. Model. 2007, 47:965-974.
39. Erhan D., et al. Collaborative filtering on a family of biological targets. J. Chem. Inf. Model. 2006, 46:626-635.
40. Jacob L., Vert J.P. Protein-ligand interaction prediction: an improved chemogenomics approach. Bioinformatics 2008, 24:2149-2156.
41. Meslamani J., Rognan D. Enhancing the accuracy of chemogenomic models with a three-dimensional binding site kernel. J. Chem. Inf. Model. 2011, 51:1593-1603.
42. Wassermann A.M., Heikamp K., Bajorath J. Potency-directed similarity searching using support vector machines. Chem. Biol. Drug Des. 2011, 77:30-38.
43. Heikamp K., et al. Prediction of activity cliffs using support vector machines. J. Chem. Inf. Model. 2012, 52:2354-2365.
44. Jorissen R.N., Gilson M.K. Virtual screening of molecular databases using a support vector machine. J. Chem. Inf. Model. 2005, 45:549-561.
45. Liew C.Y., et al. SVM model for virtual screening of Lck inhibitors. J. Chem. Inf. Model. 2009, 49:877-885.
46. Lv W., Xue Y. Prediction of acetylcholinesterase inhibitors and characterization of correlative molecular descriptors by machine learning methods. Eur. J. Med. Chem. 2010, 45:1167-1172.
47. Sun H., et al. Predictive models for cytochrome P450 isozymes based on quantitative high throughput screening data. J. Chem. Inf. Model. 2011, 51:2474-2481.
48. Agarwal S., Dugar D., Sengupta S. Ranking chemical structures for drug discovery: a new machine learning approach. J. Chem. Inf. Model. 2010, 50:716-731.
49. Rathke F., et al. StructRank: a new approach for ligand-based virtual screening. J. Chem. Inf. Model. 2010, 51:83-92.
50. Sun H., et al. Structure based model for the prediction of phospholipidosis induction potential of small molecules. J. Chem. Inf. Model. 2012, 52:1798-1805.
51. Sciabola S., et al. Predicting kinase selectivity profiles using free-Wilson QSAR analysis. J. Chem. Inf. Model. 2008, 48:1851-1867.
52. Chen H., et al. Beyond the scope of free-Wilson analysis: building interpretable QSAR models with machine learning algorithms. J. Chem. Inf. Model. 2013, 53:1324-1336.
53. Jacob L., et al. Virtual screening of GPCRs: an in silico chemogenomics approach. BMC Bioinform. 2008, 9:363-379.
54. Wang Y.C., et al. Kernel-based data fusion improves the drug-protein interaction prediction. Comput. Biol. Chem. 2011, 35:53-362.
55. Wang F., et al. Computational screening for active compounds targeting protein sequences: methodology and experimental validation. J. Chem. Inf. Model. 2011, 51:2821-2828.
56. Wassermann A.M., Geppert H., Bajorath J. Ligand prediction for orphan targets using support vector machines and various target-ligand kernels is dominated by nearest neighbor effects. J. Chem. Inf. Model. 2009, 49:2155-2167.
57. Geppert H., et al. Ligand prediction from protein sequence and small molecule information using support vector machines and fingerprint descriptors. J. Chem. Inf. Model. 2009, 49:767-779.
58. Zernov V.V., et al. Drug discovery using support vector machines. The case studies of drug-likeness, agrochemical-likeness, and enzyme inhibition predictions. J. Chem. Inf. Comput. Sci. 2003, 43:2048-2056.
59. Wassermann A.M., Geppert H., Bajorath J. Searching for target-selective compounds using different combinations of multiclass support vector machine ranking methods, kernel functions, and fingerprint descriptors. J. Chem. Inf. Model. 2009, 49:582-592.
60. Michielan L., et al. Exploring potency and selectivity receptor antagonist profiles using a multilabel classification approach: the human adenosine receptors as a key study. J. Chem. Inf. Model. 2009, 49:2820-2836.
61. Heikamp K., Bajorath J. Prediction of compounds with closely related activity profiles using weighted support vector machine linear combinations. J. Chem. Inf. Model. 2013, 53:791-801.
62. Kawai K., Fujishima S., Takahashi Y. Predictive activity profiling of drugs by topological-fragment-spectra-based support vector machines. J. Chem. Inf. Model. 2008, 48:1152-1160.
63. Sato T., et al. In silico functional profiling of small molecules and its applications. J. Med. Chem. 2008, 51:7705-7716.
64. Lind P., Maltseva T. Support vector machines for the estimation of aqueous solubility. J. Chem. Inf. Comput. Sci. 2003, 43:1855-1859.
65. Cheng T., et al. Binary classification of aqueous solubility using support vector machines with reduction and recombination feature selection. J. Chem. Inf. Model. 2011, 51:229-236.
66. Shen J., et al. Estimation of ADME properties with substructure pattern recognition. J. Chem. Inf. Model. 2010, 50:1034-1041.
67. Hou T., Wang J., Li Y. ADME evaluation in drug discovery. 8. The prediction of human intestinal absorption by a support vector machine. J. Chem. Inf. Model. 2007, 47:2408-2415.
68. Kumar R., Sharma A., Varadwaj P.K. A prediction model for oral bioavailability of drugs using physicochemical properties by support vector machine. J. Nat. Sci. Biol. Med. 2011, 2:168-173.
69. Bhavani S., et al. Substructure-based support vector machine classifiers for prediction of adverse effects in diverse classes of drugs. J. Chem. Inf. Model. 2006, 46:2478-2486.
70. Zhang H., et al. Rapid and accurate assessment of seizure liability of drugs by using an optimal support vector machine method. Toxicol. In Vitro 2011, 25:1848-1854.
71. Hu X., Yan A. In silico models to discriminate compounds inducing and noninducing toxic myopathy. Mol. Inf. 2012, 31:27-39.
72. Su B.H., et al. Predictive toxicology modeling: protocols for exploring hERG classification and tetrahymenapyriformis end point predictions. J. Chem. Inf. Model. 2012, 52:1660-1673.
73. Ding B., Li N., Wang W. Characterizing binding of small molecules. II. Evaluating the potency of small molecules to combat resistance based on docking structures. J. Chem. Inf. Model. 2013, 53:1213-1222.
74. Podolyan Y., Walters M.A., Karypis G. Assessing synthetic accessibility of chemical compounds using machine learning methods. J. Chem. Inf. Model. 2010, 50:979-991.
75. Müller K.R., et al. Classifying 'drug-likeness' with kernel-based learning methods. J. Chem. Inf. Model. 2005, 45:249-253.
76. Kortagere S., et al. New predictive models for blood-brain barrier permeability of drug-like molecules. Pharm. Res. 2008, 25:1836-1845.
77. Volkamer A., et al. Combining global and local measures for structure-based druggability predictions. J. Chem. Inf. Model. 2012, 52:360-372.
78. Li L., Wang B., Meroueh S.O. Support vector regression scoring of receptor-ligand complexes for rank-ordering and virtual screening of chemical libraries. J. Chem. Inf. Model. 2011, 51:2132-2138.
79. Li G.B., et al. ID-score: a new empirical scoring function based on a comprehensive set of descriptors related to protein-ligand interactions. J. Chem. Inf. Model. 2013, 53:592-600.
80. Hou T., et al. Characterization of domain-peptide interaction interface a generic structure-based model to decipher the binding specificity of SH3 domains. Mol. Cell. Proteomics 2009, 8:639-649.
81. Hou T., et al. Characterization of domain-peptide interaction interface: prediction of SH3 domain-mediated protein-protein interaction network in yeast by generic structure-based models. J. Proteome Res. 2012, 11:2982-2995.
82. Vapnik V. The Nature of Statistical Learning Theory 2000, Springer, New York.
83. Zararsiz G., Elmali F., Ozturk A. Bagging support vector machines for leukemia classification. Int. J. Comput. Sci. Issues 2012, 9:355-358.
84. Cortes C., Vapnik V. Support vector network. Mach. Learn. 1995, 20:273-297.
85. Tropsha A., Golbraikh A. Handbook of Chemoinformatics Algorithms 2010, Chapman & Hall/CRC, London. J.L. Faulon, A. Bender (Eds.).
86. Guyon I., et al. Gene selection for cancer classification using support vector machines. Mach. Learn. 2002, 46:389-422.
87. Yu Y. SVM-RFE Algorithm for Gene Feature Selection, University of Delaware. Technical Report 2007, (accessed 01.02.14). http://www.eecis.udel.edu/~yuy/report0531.pdf.
88. Kohavi R., John G.H. Wrappers for feature subset selection. Artif. Intell. 1997, 97:273-324.
89. Witten I.H., Frank E. Data Mining: Practical Machine Learning Tools and Techniques 2005, Morgan Kaufmann Publishers, San Francisco, CA. 2nd ed.
90. Hall M., et al. The WEKA data mining software: an update. ACM SIGKDD Explor. Newsl. 2009, 11:10-18.
91. Xue Y., et al. Effect of molecular descriptor feature selection in support vector machine classification of pharmacokinetic and toxicological properties of chemical agents. J. Chem. Inf. Comput. Sci. 2004, 44:1630-1638.
92. Li H., et al. Effect of selection of molecular descriptors on the prediction of blood-brain barrier penetrating and nonpenetrating agents by statistical learning methods. J. Chem. Inf. Model. 2005, 45:1376-1384.
93. Veber D.F., et al. Molecular properties that influence the oral bioavailability of drug candidates. J. Med. Chem. 2002, 45:2615-2623.
94. Hou T.J., et al. Recent developments of in silico predictions of intestinal absorption and oral bioavailability. Comb. Chem. High Throughput Screen. 2009, 12:497-506.
95. Hou T.J., et al. Recent advances in computational prediction of drug absorption and permeability in drug discovery. Curr. Med. Chem. 2006, 13:2653-2667.