A prediction model of substrates and non-substrates of breast cancer resistance protein (BCRP) developed by GA-CG-SVM method

Breast cancer resistance protein (BCRP) is one of the key multi-drug resistance proteins, which significantly influences the therapeutic effects of many drugs, particularly anti-cancer drugs. Thus, distinguishing between substrates and non-substrates of BCRP is important not only for clinical use but also for drug discovery and development. In this study, a prediction model of the substrates and non-substrates of BCRP was developed using a modified support vector machine (SVM) method, namely GA-CG-SVM. The overall prediction accuracy of the established GA-CG-SVM model is 91.3% for the training set and 85.0% for an independent validation set. For comparison, two other machine learning methods, namely, C4.5 DT and k-NN, were also adopted to build prediction models. The results show that the GA-CG-SVM model is significantly superior to C4.5 DT and k-NN models in terms of the prediction accuracy. To sum up, the prediction model of BCRP substrates and non-substrates generated by the GA-CG-SVM method is sufficiently good and could be used as a screening tool for identifying the substrates and non-substrates of BCRP.

[1]  Chang-Ying Ma,et al.  In silico prediction of mitochondrial toxicity by using GA-CG-SVM approach. , 2009, Toxicology in vitro : an international journal published in association with BIBRA.

[2]  Sarah Jane Delany.  k-Nearest Neighbour Classifiers , 2007 .

[3]  Alfred H. Schinkel,et al.  Human Breast Cancer Resistance Protein: Interactions with Steroid Drugs, Hormones, the Dietary Carcinogen 2-Amino-1-methyl-6-phenylimidazo(4,5-b)pyridine, and Transport of Cimetidine , 2005, Journal of Pharmacology and Experimental Therapeutics.

[4]  F H Hausheer,et al.  Circumvention of breast cancer resistance protein (BCRP)-mediated resistance to camptothecins in vitro using non-substrate drugs or the BCRP inhibitor GF120918. , 2001, Clinical cancer research : an official journal of the American Association for Cancer Research.

[5]  Z R Li,et al.  Prediction of genotoxicity of chemical compounds by statistical learning methods. , 2005, Chemical research in toxicology.

[6]  L. Breiman,et al.  Submodel selection and evaluation in regression. The X-random case , 1992 .

[7]  Yuichi Sugiyama,et al.  Role of Breast Cancer Resistance Protein (Bcrp1/Abcg2) in the Extrusion of Glucuronide and Sulfate Conjugates from Enterocytes to Intestinal Lumen , 2005, Molecular Pharmacology.

[8]  Ying Xue,et al.  Statistical learning approach for predicting specific pharmacodynamic, pharmacokinetic, or toxicological properties of pharmaceutical agents , 2005 .

[9]  C. B. Lucasius,et al.  Understanding and using genetic algorithms Part 1. Concepts, properties and context , 1993 .

[10]  Emese Kis,et al.  Pentoxifylline and its major oxidative metabolites exhibit different pharmacological properties. , 2006, European journal of pharmacology.

[11]  H. van de Waterbeemd,et al.  ADMET in silico modelling: towards prediction paradise? , 2003, Nature reviews. Drug discovery.

[12]  J. F. Wang,et al.  Prediction of P-Glycoprotein Substrates by a Support Vector Machine Approach , 2004, J. Chem. Inf. Model..

[13]  Hui Zhang,et al.  An integrated scheme for feature selection and parameter setting in the support vector machine modeling and its application to the prediction of pharmacokinetic properties of drugs , 2009, Artif. Intell. Medicine.

[14]  Yuichi Sugiyama,et al.  ATP-binding cassette, subfamily G (ABCG family) , 2007, Pflügers Archiv - European Journal of Physiology.

[15]  T. Ishikawa,et al.  High-speed screening and quantitative SAR analysis of human ABC transporter ABCG2 for molecular modeling of anticancer drugs to circumvent multidrug resistance. , 2007, Mini reviews in medicinal chemistry.

[16]  M. Gottesman,et al.  Targeting multidrug resistance in cancer , 2006, Nature Reviews Drug Discovery.

[17]  Yves Pommier,et al.  Novel E-ring camptothecin keto analogues (S38809 and S39625) are stable, potent, and selective topoisomerase I inhibitors without being substrates of drug efflux transporters , 2007, Molecular Cancer Therapeutics.

[18]  G. Kéri,et al.  High-affinity interaction of tyrosine kinase inhibitors with the ABCG2 multidrug transporter. , 2004, Molecular pharmacology.

[19]  Hiroyuki Hirano,et al.  A New Strategy of High-Speed Screening and Quantitative Structure-Activity Relationship Analysis to Evaluate Human ATP-Binding Cassette Transporter ABCG2-Drug Interactions , 2006, Journal of Pharmacology and Experimental Therapeutics.

[20]  Andreas Zell,et al.  Towards Optimal Descriptor Subset Selection with Support Vector Machines in Classification and Regression , 2004 .

[21]  R. Baron,et al.  Finding genes in the C2C12 osteogenic pathway by k-nearest-neighbor classification of expression data. , 2002, Genome research.

[22]  L. Doyle,et al.  Multidrug resistance mediated by the breast cancer resistance protein BCRP (ABCG2) , 2003, Oncogene.

[23]  Yuichi Sugiyama,et al.  ABCG2 Transports Sulfated Conjugates of Steroids and Xenobiotics* , 2003, Journal of Biological Chemistry.

[24]  E. Hazai,et al.  Homology modeling of breast cancer resistance protein (ABCG2). , 2008, Journal of structural biology.

[25]  S. Bates,et al.  Transport of methotrexate, methotrexate polyglutamates, and 17beta-estradiol 17-(beta-D-glucuronide) by ABCG2: effects of acquired mutations at R482 on methotrexate transport. , 2003, Cancer research.

[26]  Hui Zhang,et al.  Rapid and accurate assessment of seizure liability of drugs by using an optimal support vector machine method. , 2011, Toxicology in vitro : an international journal published in association with BIBRA.

[27]  S. Sathiya Keerthi,et al.  An Efficient Method for Gradient-Based Adaptation of Hyperparameters in SVM Models , 2006, NIPS.

[28]  Wei Li,et al.  Three-class classification models of logS and logP derived by using GA–CG–SVM approach , 2009, Molecular Diversity.

[29]  Jashvant D Unadkat,et al.  Interactions of azole antifungal agents with the human breast cancer resistance protein (BCRP). , 2007, Journal of pharmaceutical sciences.

[30]  Akira Tsuji,et al.  Transporter-mediated drug delivery: recent progress and experimental approaches. , 2004, Drug discovery today.

[31]  T. Janvilisri,et al.  Sterol Transport by the Human Breast Cancer Resistance Protein (ABCG2) Expressed in Lactococcus lactis* , 2003, Journal of Biological Chemistry.

[32]  B. Sarkadi,et al.  Characterization of Drug Transport, ATP Hydrolysis, and Nucleotide Trapping by the Human ABCG2 Multidrug Transporter , 2002, The Journal of Biological Chemistry.

[33]  C. Hrycyna,et al.  The nature of amino acid 482 of human ABCG2 affects substrate transport and ATP hydrolysis but not substrate binding , 2006, Protein Science.

[34]  C. Hrycyna,et al.  Differential Sensitivities of the Human ATP-Binding Cassette Transporters ABCG2 and P-Glycoprotein to Cyclosporin A , 2005, Molecular Pharmacology.

[35]  Yuquan Wei,et al.  Prediction models of human plasma protein binding rate and oral bioavailability derived by using GA-CG-SVM method. , 2008, Journal of pharmaceutical and biomedical analysis.

[36]  Christopher J. C. Burges,et al.  A Tutorial on Support Vector Machines for Pattern Recognition , 1998, Data Mining and Knowledge Discovery.

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

[38]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[39]  Alexander Tropsha,et al.  QSAR modeling of human serum protein binding with several modeling techniques utilizing structure-information representation. , 2006, Journal of medicinal chemistry.

[40]  Janet Morgan,et al.  The Tyrosine Kinase Inhibitor Imatinib Mesylate Enhances the Efficacy of Photodynamic Therapy by Inhibiting ABCG2 , 2007, Clinical Cancer Research.

[41]  I. Cascorbi,et al.  Role of pharmacogenetics of ATP-binding cassette transporters in the pharmacokinetics of drugs. , 2006, Pharmacology & therapeutics.

[42]  Cheng-Lung Huang,et al.  A GA-based feature selection and parameters optimizationfor support vector machines , 2006, Expert Syst. Appl..

[43]  Mei-Lin Go,et al.  Modulation of breast cancer resistance protein (BCRP/ABCG2) by non-basic chalcone analogues. , 2008, European journal of pharmaceutical sciences : official journal of the European Federation for Pharmaceutical Sciences.

[44]  Qingcheng Mao,et al.  Role of the breast cancer resistance protein (ABCG2) in drug transport , 2005, The AAPS Journal.

[45]  Suneet Shukla,et al.  Modulation of the function of the multidrug resistance–linked ATP-binding cassette transporter ABCG2 by the cancer chemopreventive agent curcumin , 2006, Molecular Cancer Therapeutics.

[46]  A. Calcagno,et al.  Role of the ABCG2 drug transporter in the resistance and oral bioavailability of a potent cyclin-dependent kinase/Aurora kinase inhibitor , 2006, Molecular Cancer Therapeutics.

[47]  Shuzhong Zhang,et al.  Structure activity relationships and quantitative structure activity relationships for the flavonoid-mediated inhibition of breast cancer resistance protein. , 2005, Biochemical pharmacology.

[48]  G. Jansen,et al.  Drug transporters: recent advances concerning BCRP and tyrosine kinase inhibitors , 2008 .

[49]  Uwe Muenster,et al.  Characterization of Substrates and Inhibitors for the In Vitro Assessment of Bcrp Mediated Drug–Drug Interactions , 2008, Pharmaceutical Research.

[50]  J. Schellens,et al.  Mechanism of the Pharmacokinetic Interaction between Methotrexate and Benzimidazoles , 2004, Cancer Research.

[51]  Mingzhi Liao,et al.  Predicting human microRNA precursors based on an optimized feature subset generated by GA-SVM. , 2011, Genomics.

[52]  K. Maeda,et al.  Involvement of BCRP (ABCG2) in the Biliary Excretion of Pitavastatin , 2005, Molecular Pharmacology.

[53]  Donald W. Miller,et al.  Drug efflux transport properties of 2',7'-bis(2-carboxyethyl)-5(6)-carboxyfluorescein acetoxymethyl ester (BCECF-AM) and its fluorescent free acid, BCECF. , 2004, Journal of pharmaceutical sciences.

[54]  Yuichi Sugiyama,et al.  Involvement of Breast Cancer Resistance Protein (BCRP/ABCG2) in the Biliary Excretion and Intestinal Efflux of Troglitazone Sulfate, the Major Metabolite of Troglitazone with a Cholestatic Effect , 2007, Drug Metabolism and Disposition.

[55]  Kim L. R. Brouwer,et al.  Differential Involvement of Mrp2 (Abcc2) and Bcrp (Abcg2) in Biliary Excretion of 4-Methylumbelliferyl Glucuronide and Sulfate in the Rat , 2006, Journal of Pharmacology and Experimental Therapeutics.

[56]  Shixing Chen,et al.  Prediction of antifungal activity by support vector machine approach , 2005 .

[57]  Minoru Sakurai,et al.  Theoretical studies for molecular modeling of new camptothecin analogues , 2007 .