臺灣博碩士論文加值系統

Estrogen receptor alpha (ERα) 是 Estrogen receptor (ER)的一種子型，經由雌激素活化後影響人體的生理功能如乳腺生長，青春期的發育，及生殖行為等。此外，ERα 也是治療 ER+ 乳癌的主要目標。Endocrine disrupting chemicals (EDCs) 會透過一些 receptor 特別是 ERα 擾亂內分泌系統。
本次研究中，蒐集文獻所發表的各種分子定量上與ERα 的鍵結能力，使用 PhE/SVM 方法建構預測分子與ERα 鍵結力模型，採用31個分子做為 training set (n = 31, r2 = 0.80, q2 = 0.77, RMSE = 0.57, s = 0.58)，179個分子做為test set (n = 179, r2 = 0.95, RMSE = 0.33, s = 0.26)，及15個分子做為outlier set (n = 15, r2 = 0.82, RMSE = 0.56, s = 0.49)。
此 PhE/SVM 預測模型通過各種模型驗證方式，因此據有良好的預測能力，並且能夠合理解釋文獻中的 ERα 預測模型。綜合上述，此 PhE/SVM 預測模型是一個準確的預測工具，有助於開發 ER+ 乳癌新藥物及檢測潛在的 EDCs 避免在工業上和生活中使用這些毒素。

The estrogen receptor alpha (ERα) is one of estrogen receptor subtype which can be activated by the hormone estrogen to affect a variety of physiological functions such as growth of mammary glands, pubertal development, and reproductive behavior. Moreover, ERα is the main therapeutic target for treating ER positive breast cancer. The endocrine disrupting chemicals (EDCs) can disturb the endocrine system via receptors especially ERα. An in silico model was developed to predict the binding affinity of ERα using the pharmacophore ensemble/support vector machine (PhE/SVM) scheme based on the data compiled from literatures. The prediction by the PhE/SVM model are in good agreement with the experimental observations for those molecules in the training set (n = 31, r2 = 0.80, q2 = 0.77, RMSE = 0.57, s = 0.58), the test set (n = 179, r2 = 0.95, RMSE = 0.33, s = 0.26), and the outlier set (n = 15, r2 = 0.82, RMSE = 0.56, s = 0.49). When subjected to a variety of statistical validations, the developed PhE/SVM model consistently met those stringent criteria. A mock test by marketed drug also asserted its predictivity. Thus, this PhE/SVM models is an accurate predictive tool to promote drug discovery for the treatment of ER positive breast cancer and to identify the potential EDCs of ERα.

Table of Content i
摘要： vii
Abstract viii
Keywords viii
1. Introduction 1
2. Materials and Methods 5
2.1 Data Collection 5
2.2 Conformation Search 5
2.3 Data set selection 6
2.4 Pharmacophore Generation 6
2.5 SVM Calculations 7
2.6 Model Validation 7
3. Results 11
3.1 PhE 11
3.2 PhE/SVM 13
3.3 Validation by Outliers 14
3.4 Predictive Evaluations 15
3.5 Mock Test 15
4. Discussion 17
5. Conclusions 21
6. Reference 23
 
Table 1. Statistic parameters correlation coefficient (r2), Statistic parameter correlation coefficient(ΔMax), mean absolute error (MAE), standard deviation of (s), RMSE, and cross-validation coefficient evaluated by HypoA, HypoB and PhE/SVM in the training set. 30
Table 2. Statistic parameters correlation coefficient (r2), maximum residual (ΔMax), mean absolute error (MAE), standard deviation of (s), RMSE, validation parameters correlation coefficients , , and , concordance correlation coefficient (CCC) evaluated by HypoA, HypoB and PhE/SVM in the test set. 31
Table 3. Weights, Tolerances. three-dimensional coordinates of chemical features and interfeature distances of pharmacophore model HypoA. 32
Table 4. Weights, Tolerances. three-dimensional coordinates of chemical features and interfeature distances of pharmacophore model HypoB. 33
Table 5. Optimal Runtime Parameters for the SVM model. 34
Table 6. Statistic parameters correlation coefficient (r2), maximum residual (ΔMax), mean absolute error (MAE), standard deviation of (s), RMSE, validation parameters correlation coefficients , , and , concordance correlation coefficient (CCC) evaluated by PhE/SVM in the outlier set. 35
Table 7. Validation verification of PhE/SVM based on prediction performance of those molecules in the training set, test set, outlier set, and mock test. 36
Table 8. Statistic parameters correlation coefficient (r2), maximum residual (ΔMax), mean absolute error (MAE), standard deviation of (s), RMSE, validation parameters correlation coefficients , , and , concordance correlation coefficient (CCC) evaluated by PhE/SVM in the Mock test. 37
Table 9. Summary of developed ERα binding affinity quantitative pharmacophore hypotheses. 38
Table S1 Compound source 60
 
Figure 1. The superposition of proteins in various cocomplex structures. The superposition of proteins in various cocomplex structures (PDB codes: chain A of 1X7R, 1XP1 and 2IOG), which are color-coded by purple, fuchsia, and yellow, respectively. 39
Figure 2. Pharmacophore models in the ensemble. Generated pharmacophore models (A) Hypo and (B) Hypo B , consisting of hydrogen-bond donor (purple), hydrophobic (light blue), hydrophobic aromatic (blue), and ring aromatic (orange) chemical features. The interfeature distances and angles among features, depicted in black, are measured in Ångstroms and degrees, respectively. 41
Figure 3. Superimposed pharmacophore models. Superposition of two pharmacophore models Hypo A and Hypo B, denoted in blue and red, respectively. 42
Figure 4. Superposition of pharmacophore models and 4. Pharmacophore models (A) Hypo A and (B) Hypo B fitted to 4. 44
Figure 5. Superposition of pharmacophore models and 4 (II). Overlay of these two models, which are color-coded by blue and red, respectively. The chemical features are described in Figure 2. 45
Figure 6. Observed vs. predicted pIC50 values in the training set. Observed pIC50 vs. the pIC50 predicted by Hypo A, Hypo B and PhE/SVM for those molecules in the training set. The solid line, dashed lines, and dotted lines correspond to the PhE/SVM regression of the data, 95% confidence interval for the PhE/SVM regression, and 95% confidence interval for the prediction, respectively. 46
Figure 7. Observed vs. predicted pIC50 values in the test set. Observed pIC50 vs. the pIC50 predicted by Hypo A, Hypo B and PhE/SVM for those molecules in the tset set. The solid line, dashed lines, and dotted lines correspond to the PhE/SVM regression of the data, 95% confidence interval for the PhE/SVM regression, and 95% confidence interval for the prediction, respectively. 47
Figure 8. Sample distribution in the chemical space. Molecular distribution for those samples in the training set (black circle), test set (white triangle), and outlier set (grey square) in the chemical space spanned by three principal components. 48
Figure 9. Observed vs. predicted pIC50 values in the outlier set. Observed pIC50 vs. the pIC50 predicted by Hypo A, Hypo B and PhE/SVM for those molecules in the outlier set. The solid line, dashed lines, and dotted lines correspond to the PhE/SVM regression of the data, 95% confidence interval for the PhE/SVM regression, and 95% confidence interval for the prediction, respectively. 49
Figure 10. Residual vs. predicted pIC50 values. Residual vs. the pIC50 predicted by PhE/SVM in the training set (black circles), test set (white triangles), and outlier set (gray squares). 50
Figure 11. Observed vs. predicted pIC50 values in the mock test. Observed pIC50 vs. the pIC50 predicted by PhE/SVM. The solid line, dashed lines, and dotted lines correspond to the PhE/SVM regression of the data, 95% confidence interval for the PhE/SVM regression, and 95% confidence interval for the prediction, respectively. 51
Figure 12. The aligment of the E2 conformation mapped by Hypo A with bound E2 in the crystal structure (PDB code: 1ERE). The RA feature and Phe404 are represented in orange and purple, respectively. 52
Figure 13. Conformations of bound in 1YIN and the 208 mapped by Hypo A. The conformation (atom color) of 208 mapped by Hypo A and the conformation (green) bound in crystal structure (PDB code: 1YIN) are superimposed. 53
Figure 14. Binding interactions between E2 and ERα. Binding interactions between E2 and ERα based on the crystal structure (PDB :1ERE) of the chain A. Figure generated by LigPlot+ 54
Figure 15. Model proposed by Mukherjee et al. and excerpted model of this study. Geometrical relationships in the pharmacophore models (A) proposed by Mukherjee et al. and (B) excerpted from the PhE in this study. The interfeature distances are measured in Ångstroms. 56
Figure 16. Model proposed by Fang et al. and excerpted model of this study. Geometrical relationships in the pharmacophore models (A) proposed by Fang et al. and (B) excerpted from the PhE in this study. The interfeature distances are measured in Ångstroms. 58
Figure 17. The alignment of 12 with 129 in the hERα cocomplex structures. The alignment of 12 with 129 in the hERα cocomplex structures (PDB code: 2IOG). THR347, ASP351, CYS530 and LYS531 represented by purple, and 129 is depicted in green. The green meshed lobs shows the molecular volume of 12. 59

1. Kuiper GG, Enmark E, Pelto-Huikko M, Nilsson S, Gustafsson JA (1996) Cloning of a novel receptor expressed in rat prostate and ovary. Proc Natl Acad Sci USA 93: 5925-5930.
2. Behl C (2001) Estrogen—Mystery Drug for the Brain?: The Neuroprotective Activities of the Female Sex Hormone: Springer.
3. Enmark E, Pelto-Huikko M, Grandien K, Lagercrantz S, Lagercrantz J, et al. (1997) Human Estrogen Receptor β-Gene Structure, Chromosomal Localization, and Expression Pattern. J Clin Endocrinol Metab 82: 4258-4265.
4. Shughrue PJ, Lane MV, Scrimo PJ, Merchenthaler I (1998) Comparative distribution of estrogen receptor-α (ER-α) and β (ER-β) mRNA in the rat pituitary, gonad, and reproductive tract. Steroids 63: 498-504.
5. Kuiper GGJM, Carlsson B, Grandien K, Enmark E, Häggblad J, et al. (1997) Comparison of the Ligand Binding Specificity and Transcript Tissue Distribution of Estrogen Receptors α and β. Endocrinology 138: 863-870.
6. Couse JF, Lindzey J, Grandien K, Gustafsson J-Å, Korach KS (1997) Tissue Distribution and Quantitative Analysis of Estrogen Receptor-α (ERα) and Estrogen Receptor-β (ERβ) Messenger Ribonucleic Acid in the Wild-Type and ERα-Knockout Mouse. Endocrinology 138: 4613-4621.
7. Shughrue PJ, Lane MV, Merchenthaler I (1997) Comparative distribution of estrogen receptor-α and -β mRNA in the rat central nervous system. J Comp Neurol 388: 507-525.
8. Lonard DM, Smith CL (2002) Molecular perspectives on selective estrogen receptor modulators (SERMs): progress in understanding their tissue-specific agonist and antagonist actions. Steroids 67: 15-24.
9. Jordan VC (2003) Antiestrogens and Selective Estrogen Receptor Modulators as Multifunctional Medicines. 1. Receptor Interactions. J Med Chem 46: 883-908.
10. Pearce ST, Jordan VC (2004) The biological role of estrogen receptors α and β in cancer. Crit Rev Oncol/Hematol 50: 3-22.
11. Jensen EV, Jordan VC (2003) The Estrogen Receptor: A Model for Molecular Medicine. Clin Cancer Res 9: 1980-1989.
12. Palmieri C, Cheng GJ, Saji S, Zelada-Hedman M, Wärri A, et al. (2002) Estrogen receptor beta in breast cancer. Endocr-Relat Cancer 9: 1-13.
13. Gustafsson J-Å, Warner M (2000) Estrogen receptor β in the breast: role in estrogen responsiveness and development of breast cancer. J Steroid Biochem Mol Biol 74: 245-248.
14. Leygue E, Dotzlaw H, Watson PH, Murphy LC (1998) Altered Estrogen Receptor α and β Messenger RNA Expression during Human Breast Tumorigenesis. Cancer Res 58: 3197-3201.
15. Zhu Y, Wang A, Liu MC, Zwart A, Lee RY, et al. (2006) Estrogen receptor alpha positive breast tumors and breast cancer cell lines share similarities in their transcriptome data structures. Int J Oncol 29: 1581-1590.
16. Diamanti-Kandarakis E, Bourguignon J-P, Giudice LC, Hauser R, Prins GS, et al. (2009) Endocrine-Disrupting Chemicals: An Endocrine Society Scientific Statement. Endocr Rev 30: 293-342.
17. Fang H, Tong W, Shi LM, Blair R, Perkins R, et al. (2001) Structure−Activity Relationships for a Large Diverse Set of Natural, Synthetic, and Environmental Estrogens. Chem Res Toxicol 14: 280-294.
18. Jacobs MN (2004) In silico tools to aid risk assessment of endocrine disrupting chemicals. Toxicology 205: 43-53.
19. Brogi S, Papazafiri P, Roussis V, Tafi A (2013) 3D-QSAR using pharmacophore-based alignment and virtual screening for discovery of novel MCF-7 cell line inhibitors. Eur J Med Chem 67: 344-351.
20. Sadler BR, Cho SJ, Ishaq KS, Chae K, Korach KS (1998) Three-Dimensional Quantitative Structure−Activity Relationship Study of Nonsteroidal Estrogen Receptor Ligands Using the Comparative Molecular Field Analysis/Cross-Validated r2-Guided Region Selection Approach. J Med Chem 41: 2261-2267.
21. Shi LM, Fang H, Tong W, Wu J, Perkins R, et al. (2000) QSAR Models Using a Large Diverse Set of Estrogens. J Chem Inf Comput Sci 41: 186-195.
22. Cherkasov A, Muratov EN, Fourches D, Varnek A, Baskin II, et al. (2013) QSAR Modeling: Where Have You Been? Where Are You Going To? J Med Chem 57: 4977-5010.
23. Mukherjee S, Nagar S, Mullick S, Mukherjee A, Saha A (2007) Pharmacophore Mapping of Selective Binding Affinity of Estrogen Modulators through Classical and Space Modeling Approaches:  Exploration of Bridged-Cyclic Compounds with Diarylethylene Linkage. J Chem Inf Model 47: 475-487.
24. Brogi S, Kladi M, Vagias C, Papazafiri P, Roussis V, et al. (2009) Pharmacophore Modeling for Qualitative Prediction of Antiestrogenic Activity. J Chem Inf Model 49: 2489-2497.
25. Fang  J, Shen  J, Cheng F, Xu Z, Liu G, et al. (2011) Computational Insights into Ligand Selectivity of Estrogen Receptors from Pharmacophore Modeling. Mol Inform 30: 539-549.
26. Ai N, Krasowski MD, Welsh WJ, Ekins S (2009) Understanding nuclear receptors using computational methods. Drug Discov Today 14: 486-494.
27. Blizzard TA, DiNinno F, Morgan Ii JD, Chen HY, Wu JY, et al. (2005) Estrogen receptor ligands. Part 9: Dihydrobenzoxathiin SERAMs with alkyl substituted pyrrolidine side chains and linkers. Bioorg Med Chem Lett 15: 107-113.
28. Bruning JB, Parent AA, Gil G, Zhao M, Nowak J, et al. (2010) Coupling of receptor conformation and ligand orientation determine graded activity. Nat Chem Biol 6: 837-843.
29. Brzozowski AM, Pike ACW, Dauter Z, Hubbard RE, Bonn T, et al. (1997) Molecular basis of agonism and antagonism in the oestrogen receptor. Nature 389: 753-758.
30. Dykstra KD, Guo L, Birzin ET, Chan W, Yang YT, et al. (2007) Estrogen receptor ligands. Part 16: 2-Aryl indoles as highly subtype selective ligands for ERα. Bioorg Med Chem Lett 17: 2322-2328.
31. Fang J, Akwabi-Ameyaw A, Britton JE, Katamreddy SR, Navas Iii F, et al. (2008) Synthesis of 3-alkyl naphthalenes as novel estrogen receptor ligands. Bioorg Med Chem Lett 18: 5075-5077.
32. Heldring N, Pawson T, McDonnell D, Treuter E, Gustafsson J-Å, et al. (2007) Structural Insights into Corepressor Recognition by Antagonist-bound Estrogen Receptors. J Biol Chem 282: 10449-10455.
33. Kim S, Wu JY, Birzin ET, Frisch K, Chan W, et al. (2004) Estrogen Receptor Ligands. II. Discovery of Benzoxathiins as Potent, Selective Estrogen Receptor α Modulators. J Med Chem 47: 2171-2175.
34. Kong EH, Heldring N, Gustafsson J-Å, Treuter E, Hubbard RE, et al. (2005) Delineation of a unique protein–protein interaction site on the surface of the estrogen receptor. Proc Natl Acad Sci U S A 102: 3593-3598.
35. Manas ES, Xu ZB, Unwalla RJ, Somers WS (2004) Understanding the Selectivity of Genistein for Human Estrogen Receptor-β Using X-Ray Crystallography and Computational Methods. Structure 12: 2197-2207.
36. Manas ES, Unwalla RJ, Xu ZB, Malamas MS, Miller CP, et al. (2004) Structure-Based Design of Estrogen Receptor-β Selective Ligands. J Am Chem Soc 126: 15106-15119.
37. Nettles KW, Bruning JB, Gil G, O'Neill EE, Nowak J, et al. (2007) Structural plasticity in the oestrogen receptor ligand-binding domain. EMBO Rep 8: 563-568.
38. Osz J, Brélivet Y, Peluso-Iltis C, Cura V, Eiler S, et al. (2012) Structural basis for a molecular allosteric control mechanism of cofactor binding to nuclear receptors. Proc Natl Acad Sci U S A 109: E588-E594.
39. Phillips C, Roberts LR, Schade M, Bazin R, Bent A, et al. (2011) Design and Structure of Stapled Peptides Binding to Estrogen Receptors. J Am Chem Soc 133: 9696-9699.
40. Shiau AK, Barstad D, Loria PM, Cheng L, Kushner PJ, et al. (1998) The Structural Basis of Estrogen Receptor/Coactivator Recognition and the Antagonism of This Interaction by Tamoxifen. Cell 95: 927-937.
41. Tan Q, Blizzard TA, Morgan Ii JD, Birzin ET, Chan W, et al. (2005) Estrogen receptor ligands. Part 10: Chromanes: old scaffolds for new SERAMs. Bioorg Med Chem Lett 15: 1675-1681.
42. Tanenbaum DM, Wang Y, Williams SP, Sigler PB (1998) Crystallographic comparison of the estrogen and progesterone receptor’s ligand binding domains. Proc Natl Acad Sci USA 95: 5998-6003.
43. Vajdos FF, Hoth LR, Geoghegan KF, Simons SP, LeMotte PK, et al. (2007) The 2.0 Å crystal structure of the ERα ligand-binding domain complexed with lasofoxifene. Protein Sci 16: 897-905.
44. Wärnmark A, Treuter E, Gustafsson J-Å, Hubbard RE, Brzozowski AM, et al. (2002) Interaction of Transcriptional Intermediary Factor 2 Nuclear Receptor Box Peptides with the Coactivator Binding Site of Estrogen Receptor α. J Biol Chem 277: 21862-21868.
45. Wu Y-L, Yang X, Ren Z, McDonnell DP, Norris JD, et al. (2005) Structural Basis for an Unexpected Mode of SERM-Mediated ER Antagonism. Mol Cell 18: 413-424.
46. Huang S-Y, Zou X (2007) Ensemble docking of multiple protein structures: Considering protein structural variations in molecular docking. Proteins 66: 399-421.
47. Leong MK (2007) A Novel Approach Using Pharmacophore Ensemble/Support Vector Machine (PhE/SVM) for Prediction of hERG Liability. Chem Res Toxicol 20: 217-226.
48. Leong MK, Chen T-H (2008) Prediction of cytochrome P450 2B6-substrate interactions using pharmacophore ensemble/support vector machine (PhE/SVM) approach. Med Chem 4: 396-406.
49. Leong MK, Chen Y-M, Chen H-B, Chen P-H (2009) Development of a new predictive model for interactions with human cytochrome P450 2A6 using pharmacophore ensemble/support vector machine (PhE/SVM) approach. Pharm Res 26: 987-1000.
50. Chen C-N, Shih Y-H, Ding Y-L, Leong MK (2011) Predicting Activation of the Promiscuous Human Pregnane X Receptor by Pharmacophore Ensemble/Support Vector Machine Approach. Chem Res Toxicol 24: 1765-1778.
51. Leong MK, Chen H-B, Shih Y-H (2012) Prediction of promiscuous p-glycoprotein inhibition using a novel machine learning scheme. PloS one 7: e33829.
52. Ding Y-L, Shih Y-H, Tsai F-Y, Leong MK (2014) In Silico Prediction of Inhibition of Promiscuous Breast Cancer Resistance Protein (BCRP/ABCG2). PloS one 9: e90689.
53. Blizzard TA, DiNinno F, Morgan Ii JD, Chen HY, Wu JY, et al. (2004) Estrogen receptor ligands. Part 7: Dihydrobenzoxathiin SERAMs with bicyclic amine side chains. Bioorg Med Chem Lett 14: 3861-3864.
54. Blizzard TA, DiNinno F, Morgan Ii JD, Wu JY, Chen HY, et al. (2004) Estrogen receptor ligands. Part 8: Dihydrobenzoxathiin SERAMs with heteroatom-substituted side chains. Bioorg Med Chem Lett 14: 3865-3868.
55. Blizzard TA, DiNinno F, Chen HY, Kim S, Wu JY, et al. (2005) Estrogen receptor ligands. Part 13: Dihydrobenzoxathiin SERAMs with an optimized antagonist side chain. Bioorg Med Chem Lett 15: 3912-3916.
56. Blizzard TA, Morgan IIJD, Mosley RT, Birzin ET, Frisch K, et al. (2003) 2-Phenylspiroindenes: a novel class of selective estrogen receptor modulators (SERMs). Bioorg Med Chem Lett 13: 479-483.
57. Blizzard TA, Morgan Ii JD, Chan W, Birzin ET, Pai L-Y, et al. (2005) Estrogen receptor ligands. Part 14: Application of novel antagonist side chains to existing platforms. Bioorg Med Chem Lett 15: 5124-5128.
58. Blizzard TA, Gude C, Morgan Ii JD, Chan W, Birzin ET, et al. (2006) Androstenediol analogs as ER-β-selective SERMs. Bioorg Med Chem Lett 16: 834-838.
59. Blizzard TA, Gude C, Chan W, Birzin ET, Mojena M, et al. (2007) Bridged androstenediol analogs as ER-β selective SERMs. Bioorg Med Chem Lett 17: 2944-2948.
60. Blizzard TA, Gude C, Morgan Ii JD, Chan W, Birzin ET, et al. (2007) Androstene-3,5-dienes as ER-β selective SERMs. Bioorg Med Chem Lett 17: 6295-6298.
61. Chen HY, Dykstra KD, Birzin ET, Frisch K, Chan W, et al. (2004) Estrogen receptor ligands. Part 1: The discovery of flavanoids with subtype selectivity. Bioorg Med Chem Lett 14: 1417-1421.
62. Kim S, Wu J, Chen HY, Birzin ET, Chan W, et al. (2004) Estrogen receptor ligands. Part 4: The SAR of the syn-dihydrobenzoxathiin SERAMs. Bioorg Med Chem Lett 14: 2741-2745.
63. Liu J, Birzin ET, Chan W, Yang YT, Pai L-Y, et al. (2005) Estrogen receptor ligands. Part 11: Synthesis and activity of isochromans and isothiochromans. Bioorg Med Chem Lett 15: 715-718.
64. Tan Q, Birzin ET, Chan W, Tien Yang Y, Pai L-Y, et al. (2004) Estrogen receptor ligands. Part 5: The SAR of dihydrobenzoxathiins containing modified basic side chains. Bioorg Med Chem Lett 14: 3747-3751.
65. Tan Q, Birzin ET, Chan W, Yang YT, Pai L-Y, et al. (2004) Estrogen receptor ligands. Part 6: Synthesis and binding affinity of dihydrobenzodithiins. Bioorg Med Chem Lett 14: 3753-3755.
66. Chang G, Guida WC, Still WC (1989) An internal-coordinate Monte Carlo method for searching conformational space. J Am Chem Soc 111: 4379-4386.
67. Kolossváry I, Guida WC (1996) Low Mode Search. An Efficient, Automated Computational Method for Conformational Analysis:  Application to Cyclic and Acyclic Alkanes and Cyclic Peptides. J Am Chem Soc 118: 5011-5019.
68. Still WC, Tempczyk A, Hawley RC, Hendrickson T (1990) Semianalytical treatment of solvation for molecular mechanics and dynamics. J Am Chem Soc 112: 6127-6129.
69. Halgren TA (1996) Merck molecular force field. I. Basis, form, scope, parameterization, and performance of MMFF94. J Comput Chem 17: 490-519.
70. Leong MK, Chen Y-M, Chen T-H (2009) Prediction of human cytochrome P450 2B6-substrate interactions using hierarchical support vector regression approach. J Comput Chem 30: 1899-1909.
71. Golbraikh A, Shen M, Xiao Z, Xiao Y-D, Lee K-H, et al. (2003) Rational selection of training and test sets for the development of validated QSAR models. J Comput-Aided Mol Des 17: 241-253.
72. Benfenati E, Chrétien JR, Gini G, Piclin N, Pintore M, et al. (2007) Validation of the models. 185-199.
73. Roy PP, Roy K (2008) On Some Aspects of Variable Selection for Partial Least Squares Regression Models. QSAR Comb Sci 27: 302-313.
74. Chirico N, Gramatica P (2012) Real External Predictivity of QSAR Models. Part 2. New Intercomparable Thresholds for Different Validation Criteria and the Need for Scatter Plot Inspection. J Chem Inf Model 52: 2044-2058.
75. Ojha PK, Mitra I, Das RN, Roy K (2011) Further exploring rm2 metrics for validation of QSPR models. Chemometrics Intell Lab Syst 107: 194-205.
76. Roy K, Mitra I, Kar S, Ojha PK, Das RN, et al. (2011) Comparative Studies on Some Metrics for External Validation of QSPR Models. J Chem Inf Model 52: 396-408.
77. Gao L, Tu Y, Ågren H, Eriksson LA (2012) Characterization of Agonist Binding to His524 in the Estrogen Receptor α Ligand Binding Domain. J Phys Chem B 116: 4823-4830.
78. Wolber G, Seidel T, Bendix F, Langer T (2008) Molecule-pharmacophore superpositioning and pattern matching in computational drug design. Drug Discov Today 13: 23-29.