Please wait a minute...
物理化学学报  2017, Vol. 33 Issue (6): 1160-1170    DOI: 10.3866/PKU.WHXB201704051
论文     
Prediction of Blood-to-Brain Barrier Partitioning of Drugs and Organic Compounds Using a QSPR Approach
GOLMOHAMMADI Hassan1,*(),DASHTBOZORGI Zahra2,KHOOSHECHIN Sajad2
1 Young Researchers and Elite Club, Yadegar-e-Imam Khomeini(RAH) Shahr-e-Rey Branch, Islamic Azad University, Tehran, Iran
2 Young Researchers and Elite Club, Central Tehran Branch, Islamic Azad University, Tehran, Iran
Prediction of Blood-to-Brain Barrier Partitioning of Drugs and Organic Compounds Using a QSPR Approach
Hassan GOLMOHAMMADI1,*(),Zahra DASHTBOZORGI2,Sajad KHOOSHECHIN2
1 Young Researchers and Elite Club, Yadegar-e-Imam Khomeini(RAH) Shahr-e-Rey Branch, Islamic Azad University, Tehran, Iran
2 Young Researchers and Elite Club, Central Tehran Branch, Islamic Azad University, Tehran, Iran
 全文: PDF(1949 KB)   HTML 输出: BibTeX | EndNote (RIS) | Supporting Info
摘要:

The purpose of this study was to develop a quantitative structure-property relationship (QSPR) model based on the enhanced replacement method (ERM) and support vector machine (SVM) to predict the blood-to-brain barrier partitioning behavior (logBB) of various drugs and organic compounds. Different molecular descriptors were calculated using a dragon package to represent the molecular structures of the compounds studied. The enhanced replacement method (ERM) was used to select the variables and construct the SVM model. The correlation coefficient, R2, between experimental results and predicted logBB was 0.878 and 0.986, respectively. The results obtained demonstrated that, for all compounds, the logBB values estimated by SVM agreed with the experimental data, demonstrating that SVM is an effective method for model development, and can be used as a powerful chemometric tool in QSPR studies.

关键词: Quantitative structure-activity relationshipBlood-to-brain barrier partitioningDrugEnhanced replacement methodSupport vector machine    
Abstract:

The purpose of this study was to develop a quantitative structure-property relationship (QSPR) model based on the enhanced replacement method (ERM) and support vector machine (SVM) to predict the blood-to-brain barrier partitioning behavior (logBB) of various drugs and organic compounds. Different molecular descriptors were calculated using a dragon package to represent the molecular structures of the compounds studied. The enhanced replacement method (ERM) was used to select the variables and construct the SVM model. The correlation coefficient, R2, between experimental results and predicted logBB was 0.878 and 0.986, respectively. The results obtained demonstrated that, for all compounds, the logBB values estimated by SVM agreed with the experimental data, demonstrating that SVM is an effective method for model development, and can be used as a powerful chemometric tool in QSPR studies.

Key words: Quantitative structure-activity relationship    Blood-to-brain barrier partitioning    Drug    Enhanced replacement method    Support vector machine
收稿日期: 2017-02-05 出版日期: 2017-04-05
通讯作者: GOLMOHAMMADI Hassan     E-mail: Hassan.gol@gmail.com
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
GOLMOHAMMADI Hassan
DASHTBOZORGI Zahra
KHOOSHECHIN Sajad

引用本文:

GOLMOHAMMADI Hassan,DASHTBOZORGI Zahra,KHOOSHECHIN Sajad. Prediction of Blood-to-Brain Barrier Partitioning of Drugs and Organic Compounds Using a QSPR Approach[J]. 物理化学学报, 2017, 33(6): 1160-1170.

Hassan GOLMOHAMMADI,Zahra DASHTBOZORGI,Sajad KHOOSHECHIN. Prediction of Blood-to-Brain Barrier Partitioning of Drugs and Organic Compounds Using a QSPR Approach. Acta Physico-Chimica Sinca, 2017, 33(6): 1160-1170.

链接本文:

http://www.whxb.pku.edu.cn/CN/10.3866/PKU.WHXB201704051        http://www.whxb.pku.edu.cn/CN/Y2017/V33/I6/1160

Fig 1  Results of diversity analysis
Descriptor Notation Coefficient Mean effect VIF
average valence connectivity index chi-4X4av1.9560.1271.164
balaban centric indexBAC?0.006?0.1341.202
information content index neighborhood symmetry of 1-orderIC1?0.805?1.9611.416
dCoMMA2 value/weighted by atomic van der waals volumesDISPv0.0470.3061.337
leverage-weighted autocorrelation of lag 7/weighted by atomicHats7p3.1020.3301.187
3D-morse signal 04/weighted by atomic massesMor04m0.1390.0101.182
constant1.365
Table 1  Specification of selected enhanced replacement method ERM
X4avBACIC1DISPvHats7pMor04m
X4av1?0.032?0.297?0.300?0.053?0.092
BAC10.2610.1320.1010.319
IC110.3800.3320.075
DISPv10.2730.234
Hats7p1?0.042
Mor04m1
Table 2  Correlation matrix for descriptors applying in this work
Training set Prediction set
R2 RMSEC QCV2 RMSECV R2 RMSEP
ERM0.8700.2620.8650.2780.8780.228
SVM0.9900.0720.9880.0730.9860.074
Table 3  Comparison of the validation parameters ofSVM and ERM models
Fig 2  Plot of SVM calculated versus experimental values ofblood-to-brain barrier partitioning color online
Fig 3  Plot of SVM residual versus experimental values ofblood-to-brain barrier partitioning color online
Fig 4  Williams plot of standardized residuals versus leverages ofdescriptors matrix by ERM model The threshold leverage value h* = 0.09.
Fig 5  Williams plot of standardized residuals versus leverages ofdescriptors matrix by SVM model The threshold leverage value h* = 0.09.
R2Rcv2kk'R2-R02R2-R'02
R2 R2
SVM0.9860.9871.0160.971?0.011?0.013
ERM0.8780.5940.8741.023?0.112?0.122
Table 4  Statistical criteria of external validation prediction set ofthe proposed QSPR models
Model Method Dataset size Overall accuracy Reference
Kortagere et al. regression model 78-376 77 64
support vector machine 80-83
Li et al. logistic regression 415 71.0 65
linear discriminate analysis 71.2
K nearest neighbor 74.3
C4.5 decision tree 77.1
probabilistic neural network 76.5
support vector machine 83.7
Gerebtzoff and Seelig calculated molecular cross-sectional area 42-122 83.3-90.2 66
Muehlbacher et al. multiple linear regression 362 - 67
random forest 88.2
our models enhanced replacement method 310 90.4 this work
support vector machine 93.1
Table 5  Comparison between other models with our developed models
1 Goldstein G. W. ; Betz A. L. Sci. Am. 1986, 255, 74.
doi: 10.1038/scientificamerican0986-74
2 Greig, N. H. ; Brossi, A. ; Pei, X. F. ; Ingram, D. K. ; Soncrant, T. T. New Concepts of a Blood-Brain Barrier; Plenum: New York, NY, 1995; pp 251-264. doi: 10.1007/978-1-4899-1054-7-25
3 Weiss N. ; Miller F. ; Cazaubon S. ; Couraud P. O. Rev. Neurol. 2009, 165, 1010.
doi: 10.1016/j.neurol.2009.04.013
4 Partridge W. M. J. Neurochem 1998, 70, 1781.
doi: 10.1046/j.1471-4159.1998.70051781.x
5 Pardridge W. M. Drug Discov. Today 2001, 6, 1.
doi: 10.1016/S1359-6446(00)01583-X
6 Tamai I. ; Tsuji A. Adv. Drug. Deliv. Rev. 1996, 19, 401.
doi: 10.1016/0169-409X(96)00011-7
7 Eddy E. P. ; Maleef B. E. ; Hart T. K. ; Smith P. L. Adv. Drug Deliv. Rev. 1997, 23, 185.
doi: 10.1016/S0169-409X(96)00435-8
8 Reichel A. ; Begley D. J. Pharm. Res. 1998, 15, 1270.
doi: 10.1023/A:1011904311149
9 Cecchelli R. ; Dehouck B. ; Descamps L. ; Fenart L. ; Buee-Scherrer V. ; Duhem C. ; Landquist S. ; Rentfel M. ; Torpier G. ; Dehouck M. P. Adv. Drug Deliv. Rev. 1999, 36, 165.
doi: 10.1016/S0169-409X(98)00083-0
10 Bujak R. ; Struck-Lewicka W. ; Kaliszan M. ; Kaliszan R. ; Markuszewski M. J. J. Pharm. Bio. Anal. 2015, 108, 29.
doi: 10.1016/j.jpba.2015.01.046
11 Konovalov D. A. ; Coomans D. ; Deconinck E. ; Vander Heyden Y. J. Chem. Inf. Model. 2007, 47, 1648.
doi: 10.1021/ci700100f
12 Nikolic K. ; Filipic S. ; Smoliński A. ; Kaliszan R. ; Agbaba D. J. Pharm. Pharm. Sci. 2013, 166, 22.
doi: 10.18433/J3JK5P
13 Shityakov S. ; Neuhaus W. ; Dandekar T. ; F?rster C. Int. J. Comput. Bio. Dr. Desig. 2013, 6, 146.
doi: 10.1504/IJCBDD.2013.052195
14 Hemmateenejad B. ; Miri R. ; Safarpour M. A. ; Mehdipour A. R. J. Comput. Chem. 2006, 72, 1125.
doi: 10.1002/jcc.20437
15 Guerra A. ; Páez J. A. ; Campillo N. E. Mol. Inf. 2008, 27, 586.
doi: 10.1002/qsar.200710019
16 Vapnik, V. Estimation of Dependencies Based on Empirical Data; Springer: Berlin, 1982. doi: 10.1007/0-387-34239-7
17 Burges C. J. C. Data Min. Knowl. Disc. 1998, 2, 121.
doi: 10.1023/A:1009715923555
18 Golmohammadi H. ; Dashtbozorgi Z. ; Acree W. E. Jr. Mol. Inf. 2012, 31, 867.
doi: 10.1002/minf.201200091
19 Zhang L. ; Zhu H. ; Oprea T. I. ; Golbraikh A. ; Tropsha A. Pharm. Res. 2008, 25, 1902.
doi: 10.1007/s11095-008-9609-0
20 Yang S. ; Huang Q. ; Li L. L. ; Ma C. Y. ; Zhang H. ; Bai R. ; Teng Q. Z. ; Xiang M. L. ; Wei Y. Q. Art. Intel. Med. 2009, 46, 155.
doi: 10.1016/j.artmed.2008.07.001
21 Norinder U. Neurocomuting 2003, 55, 337.
doi: 10.1016/S0925-2312(03)00374-6
22 Cai Y. D. ; Liu X. J. ; Xu X. B. ; Chou K. C. Comput. Chem. 2002, 26, 293.
doi: 10.1016/S0097-8485(01)00113-9
23 Bao L. ; Sun Z. R. FEBS Lett. 2002, 521, 109.
doi: 10.1016/S0014-5793(02)02835-1
24 Zhao C. Y. ; Zhang R. S. ; Liu H. X. ; Xue C. X. ; Zhao S. G. ; Zhou X. F. ; Liu M. C. ; Fan B. T. J. Chem. Inf. Comput. Sci. 2004, 44, 2040.
doi: 10.1021/ci049877y
25 Muehlbacher M. ; Spitzer G. M. ; Liedl K. R. ; Kornhuber J. J. Comput. Aided Mol. Des. 2011, 25, 1095.
doi: 10.1007/s10822-011-9478-1
26 Hyperchem, Re. 4. for Windows; Autodesk: Sansalito, CA, 1995.
27 Todeschini, R. ; Consonni, V. ; Pavan, M. Dragon Software; Talete SRL: Milan, Italy, 2002.
28 Levet A. ; Bordes C. ; Clément Y. ; Mignon P. ; Chermette H. ; Marote P. ; Cren-Olivé C. ; Lantéri P. Chemosphere 2013, 93, 1094.
doi: 10.1016/j.chemosphere.2013.06.002
29 Duchowicz P. R. ; Castro E. A. ; Fernández F. M. ; González M. P. Chem. Phys. Lett. 2005, 412, 376.
doi: 10.1016/j.cplett.2005.07.016
30 MATLAB 7. 0, The Mathworks Inc. : Natick, MA, USA, 2005, http://www.mathworks.com.
31 Golmohammadi H. ; Dashtbozorgi Z. ; Acree W. E. Jr. Struct. Chem. 2013, 24, 1799.
doi: 10.1007/s11224-013-0222-4
32 Golmohammadi H. ; Dashtbozorgi Z. ; Acree W. E. Jr. Phys. Chem. Liq. 2013, 51, 182.
doi: 10.1080/00319104.2012.708932
33 Dashtbozorgi Z. ; Golmohammadi H. ; Acree W. E. Jr. Thermochim. Acta. 2012, 539, 7.
doi: 10.1016/j.tca.2012.03.017
34 Golmohammadi H. ; Dashtbozorgi Z. ; Acree W. E. Jr. Mol. Inf. 2012, 31, 867.
doi: 10.1002/minf.201200091
35 Zhou X. ; Li Z. ; Dai Z. ; Zou X. J. Mol. Graph. Model. 2010, 29, 188.
doi: 10.1016/j.jmgm.2010.06.002
36 Miao Y. ; Su H. ; Xu O. ; Chu J. Ind. Eng. Chem. Res. 2009, 48, 10903.
doi: 10.1021/ie801629f
37 Li H. ; Liang Y. ; Xu Q. Chemometr. Intell. Lab. Syst. 2009, 95, 188.
doi: 10.1016/j.chemolab.2008.10.007
38 Rojas C. ; Duchowicz P. R. ; Tripaldi P. ; Pis Diez R. Chemometr. Intell. Lab. Syst. 2015, 140, 126.
doi: 10.1016/j.chemolab.2014.09.020
39 Mercader G. ; Duchowicz P. R. ; Fernández F. M. ; Castro E. A. Chemometr. Intell. Lab. Syst. 2008, 92, 138.
doi: 10.1016/j.chemolab.2008.02.005
40 Davis, L. Handbook of Genetic Algorithms; Van Nostrand Reinhold: New York: 1991. doi: 10.1017/S0269888900006068
41 Cao D. S. ; Liang Y. Z. ; Xu Q. S. ; Li H. D. ; Chen X. J. Comput. Chem. 2010, 31, 592.
doi: 10.1002/jcc.21351
42 Yan J. ; Huang J. H. ; He M. ; Lu H. B. ; Yang R. ; Kong B. ; Xu Q. S. ; Liang Y. Z. J. Sep. Sci. 2013, 36, 2464.
doi: 10.1002/jssc.201300254
43 Cao D. S. ; Liang Y. Z. ; Xu Q. S. ; Yun Y. H. ; Li H. D. J. Comput. Aided Mol. Des. 2011, 25, 67.
doi: 10.1007/s10822-010-9401-1
44 Eriksson L. ; Jaworska J. ; Worth A. P. ; Cronin M. T. ; McDowell R. M. ; Gramatica P. Health Perspect. 2003, 111, 1361.
doi: 10.1289/ehp.5758
45 Golbraikh A. ; Shen M. ; Xiao Z. ; Xiao Y. ; Lee K. H. ; Tropsha A. J. Comput. Aided Mol. Des. 2003, 17, 241.
doi: 10.1023/A:1025386326946
46 Tang K. ; Li T. Anal. Chim. Acta 2003, 476, 85.
doi: 10.1016/S0003-2670(02)01257-6
47 de Campos L. J. ; de Melo E. B. J. Mol. Graph. Model. 2014, 54, 19.
doi: 10.1016/j.jmgm.2014.08.004
48 Golbraikh A. ; Tropsha A. J. Mol. Graph. Model. 2002, 20, 269.
doi: 10.1016/S1093-3263(01)00123-1
49 Zhao C. Y. ; Zhang H. X. ; Zhang X. Y. ; Liu M. C. ; Hu Z. D. ; Fan B. T. Toxicol 2006, 217, 105.
doi: 10.1016/j.tox.2005.08.019
50 Agrawal V. K. ; Khadikar P. V. Bioorg. Med. Chem. 2001, 911, 3035.
doi: 10.1016/S0968-0896(01)00211-5
51 Pourbasheer E. ; Riahi S. ; Ganjali M. R. ; Norouzi P. J. Enzyme. Inhib. Med. Chem. 2010, 256, 844.
doi: 10.3109/14756361003757893
52 Kier L. B. J. Pharm. Sci. 1980, 69, 807.
doi: 10.1002/jps.2600690914
53 Bonchev, D. Information Theoretic Indices for Characterization of Chemical Structure; Wiley-Interscience: New York, 1983. doi: 10.1002/jps.2600730950
54 Sliwoski G. ; Mendenhall J. ; Meiler J. J. Comput. Aided Mol. Des. 2016, 30, 209.
doi: 10.1007/s10822-015-9893-9
55 Todeschini, R. ; Consonni, V. Handbook of Molecular Descriptors, In: Methods and Principles in Medicinal Chemistry; Mannhold, R. , Kubinyi, H. , Timmerman, H. Eds. ; Wiley-VCH: Weinheim, 2000. doi: 10.1002/9783527613106
56 Silverman B. D. ; Platt D. E. J. Med. Chem. 1996, 39, 2129.
doi: 10.1021/jm950589q
57 Balaban A. T. Theor. Chim. Acta 1979, 53, 355.
doi: 10.1007/BF00555695
58 Kier, L. B. ; Hall, L. H. Molecular Connectivity in Structure-Activity Analysis; Wiley: New York, 1986. doi: 10.1002/aic.690331230
59 Hall L. H. ; Kier L. B. J. Mol. Graph. Model. 2001, 20, 4.
doi: 10.1016/S1093-3263(01)00097-3
60 Randic M. J. Mol. Graph. Model. 2001, 20, 19.
doi: 10.1016/S1093-3263(01)00098-5
61 Soltzberg L. J. ; Wilkins C. L. J. Am. Chem. Soc. 1977, 99, 439.
doi: 10.1021/ja00444a021
62 Kovtun D. M. ; Kochikov I. V. ; Tarasov Y. I. J.Phys. Chem. A 2015, 119, 1657.
doi: 10.1021/jp5082774
63 Ma S. ; Lv M. ; Deng F. ; Zhang X. ; Zhai H. ; Lv W. J. Hazard. Mater. 2015, 283, 591.
doi: 10.1016/j.jhazmat.2014.10.011
64 Kortagere S. ; Chekmarev D. ; Welsh W. J. ; Ekins S. Pharm. Res. 2008, 25, 1836.
doi: 10.1007/s11095-008-9584-5
65 Li H. ; Yap C. W. ; Ung C. Y. ; Xue Y. ; Cao Z. W. ; Chen Y. Z. J. Chem. Inf. Model. 2005, 45, 1376.
doi: 10.1021/ci050135u
66 Gerebtzoff G. ; Seelig A. J. Chem. Inf. Model. 2006, 46, 2638.
doi: 10.1021/ci0600814
67 Muehlbacher M. ; Spitzer G. M. ; Liedl K. R. ; Kornhuber J. J. Comput. Aided Mol. Des. 2011, 25, 1095.
doi: 10.1007/s10822-011-9478-1
[1] GOLMOHAMMADI Hassan, DASHTBOZORGI Zahra, KHOOSHECHIN Sajad. Developing a Support Vector Machine Based QSPR Model to PredictGas-to-Benzene Solvation Enthalpy of Organic Compounds[J]. 物理化学学报, 2017, 33(5): 918-926.
[2] RUB Malik Abdul, ASIRI Abdullah M, KUMAR Dileep, AZUM Naved, KHAN Farah. 水介质中药物-AOT混合物的温度依赖的混合胶束化行为[J]. 物理化学学报, 2014, 30(4): 699-707.
[3] KABIR-UD-DIN, RUB Malik Abdul, NAQVI Andleeb Z.. 不同浓度和温度时无机盐和尿素对抗抑郁剂药物丙咪嗪盐酸盐的胶束化行为的影响[J]. 物理化学学报, 2012, 28(04): 885-891.
[4] ALAMMd. Sayem;KABIR-UD-DIN. 电解质对两性药物分子盐酸氯丙嗪的胶团生长的影响[J]. 物理化学学报, 2008, 24(03): 411-415.