Combination of kernel PCA and linear support vector machine for modeling a nonlinear relationship between bioactivity and molecular descriptors
In this paper, a two‐step nonlinear classification algorithm is proposed to model the structure–activity relationship (SAR) between bioactivities and molecular descriptors of compounds, which consists of kernel principal component analysis (KPCA) and linear support vector machines (KPCA + LSVM). KPC...
Saved in:
| Published in | Journal of chemometrics Vol. 25; no. 2; pp. 92 - 99 |
|---|---|
| Main Authors | , , , , |
| Format | Journal Article |
| Language | English |
| Published |
Chichester, UK
John Wiley & Sons, Ltd
01.02.2011
Wiley Wiley Subscription Services, Inc |
| Subjects | |
| Online Access | Get full text |
| ISSN | 0886-9383 1099-128X 1099-128X |
| DOI | 10.1002/cem.1364 |
Cover
| Abstract | In this paper, a two‐step nonlinear classification algorithm is proposed to model the structure–activity relationship (SAR) between bioactivities and molecular descriptors of compounds, which consists of kernel principal component analysis (KPCA) and linear support vector machines (KPCA + LSVM). KPCA is used to remove some uninformative gradients such as noises and then exactly capture the latent structure of the training dataset using some new variables called the principal components in the kernel‐defined feature space. LSVM makes full use of the maximal margin hyperplane to give the best generalization performance in the KPCA‐transformed space. The combination of KPCA and LSVM can effectively improve the prediction performance compared with the linear SVM as well as two nonlinear methods. Three datasets related to different categorical bioactivities of compounds are used to evaluate the performance of KPCA + LSVM. The results show that our algorithm is competitive. Copyright © 2011 John Wiley & Sons, Ltd.
In this paper, a two‐step nonlinear classification algorithm is proposed to model the structure‐activity relationship (SAR) between bioactivities and molecular descriptors of compounds, which consists of kernel principal component analysis (KPCA) and linear support vector machines (KPCA+ LSVM). The combination of KPCA and LSVM can effectively improve the prediction performance compared with the linear SVM as well as two nonlinear methods. Three datasets related to different categorical bioactivities of compounds are used to evaluate the performance of KPCA+LSVM. The results show that our algorithm is competitive. |
|---|---|
| AbstractList | In this paper, a two-step nonlinear classification algorithm is proposed to model the structure-activity relationship (SAR) between bioactivities and molecular descriptors of compounds, which consists of kernel principal component analysis (KPCA) and linear support vector machines (KPCA + LSVM). KPCA is used to remove some uninformative gradients such as noises and then exactly capture the latent structure of the training dataset using some new variables called the principal components in the kernel-defined feature space. LSVM makes full use of the maximal margin hyperplane to give the best generalization performance in the KPCA-transformed space. The combination of KPCA and LSVM can effectively improve the prediction performance compared with the linear SVM as well as two nonlinear methods. Three datasets related to different categorical bioactivities of compounds are used to evaluate the performance of KPCA + LSVM. The results show that our algorithm is competitive. [PUBLICATION ABSTRACT] In this paper, a two‐step nonlinear classification algorithm is proposed to model the structure–activity relationship (SAR) between bioactivities and molecular descriptors of compounds, which consists of kernel principal component analysis (KPCA) and linear support vector machines (KPCA + LSVM). KPCA is used to remove some uninformative gradients such as noises and then exactly capture the latent structure of the training dataset using some new variables called the principal components in the kernel‐defined feature space. LSVM makes full use of the maximal margin hyperplane to give the best generalization performance in the KPCA‐transformed space. The combination of KPCA and LSVM can effectively improve the prediction performance compared with the linear SVM as well as two nonlinear methods. Three datasets related to different categorical bioactivities of compounds are used to evaluate the performance of KPCA + LSVM. The results show that our algorithm is competitive. Copyright © 2011 John Wiley & Sons, Ltd. In this paper, a two‐step nonlinear classification algorithm is proposed to model the structure‐activity relationship (SAR) between bioactivities and molecular descriptors of compounds, which consists of kernel principal component analysis (KPCA) and linear support vector machines (KPCA+ LSVM). The combination of KPCA and LSVM can effectively improve the prediction performance compared with the linear SVM as well as two nonlinear methods. Three datasets related to different categorical bioactivities of compounds are used to evaluate the performance of KPCA+LSVM. The results show that our algorithm is competitive. In this paper, a two-step nonlinear classification algorithm is proposed to model the structure-activity relationship (SAR) between bioactivities and molecular descriptors of compounds, which consists of kernel principal component analysis (KPCA) and linear support vector machines (KPCA+LSVM). KPCA is used to remove some uninformative gradients such as noises and then exactly capture the latent structure of the training dataset using some new variables called the principal components in the kernel-defined feature space. LSVM makes full use of the maximal margin hyperplane to give the best generalization performance in the KPCA-transformed space. The combination of KPCA and LSVM can effectively improve the prediction performance compared with the linear SVM as well as two nonlinear methods. Three datasets related to different categorical bioactivities of compounds are used to evaluate the performance of KPCA+LSVM. The results show that our algorithm is competitive. |
| Author | Fu, Guang-Hui Liang, Yi-Zeng Xu, Qing-Song Li, Hong-Dong Cao, Dong-Sheng |
| Author_xml | – sequence: 1 givenname: Guang-Hui surname: Fu fullname: Fu, Guang-Hui organization: School of Mathematical Science and Computing Technology, Central South University, Changsha 410083, P. R. China – sequence: 2 givenname: Dong-Sheng surname: Cao fullname: Cao, Dong-Sheng organization: Research Center of Modernization of Traditional Chinese Medicines, Central South University, Changsha 410083, P. R. China – sequence: 3 givenname: Qing-Song surname: Xu fullname: Xu, Qing-Song email: qsxu@mail.csu.edu.cn organization: School of Mathematical Science and Computing Technology, Central South University, Changsha 410083, P. R. China – sequence: 4 givenname: Hong-Dong surname: Li fullname: Li, Hong-Dong organization: Research Center of Modernization of Traditional Chinese Medicines, Central South University, Changsha 410083, P. R. China – sequence: 5 givenname: Yi-Zeng surname: Liang fullname: Liang, Yi-Zeng organization: Research Center of Modernization of Traditional Chinese Medicines, Central South University, Changsha 410083, P. R. China |
| BackLink | http://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=23876609$$DView record in Pascal Francis |
| BookMark | eNp10ctu1TAQBuAIFYnTgsQjWEgINjk4cXzJsopKiyiXBZTuLMcZU7eOndo5LecpeGV8LqpEBauxNN_8GnkOiwMfPBTFywovK4zrdxrGZUVY86RYVLhty6oWlwfFAgvBypYI8qw4TOka49wjzaL43YWxt17NNngUDLqB6MGhr90xUn5AznpQEaXVNIU4ozvQc4hoVPoqN5DZvMMAWf1ECuVN9j6C2yamKzuhHuZ7AI96G5Se7Z2d19vsMTjQK5f5AElHO-Xo9Lx4apRL8GJfj4rv70--dWfl-ZfTD93xealJWzclp9gAIQYU0ao3NaEglGhMTwjNhVZDxRtaV6YdBG_6tmGM1GKgHFpDgQlyVLzZ5U4x3K4gzXK0SYNzykNYJdniinHMaprlq0fyOqyiz8tJQRkmDWt4Rq_3SCWtnInKa5vkFO2o4lrWRHDGcJvd253TMaQUwTyQCsvN_WS-n9zcL9PlI6rtvP3VOSrr_jVQ7gburYP1f4Nld_Lpb2_TDL8evIo3knHCqfzx-VTis48XvLsg8pL8AbGvvnU |
| CODEN | JOCHEU |
| CitedBy_id | crossref_primary_10_1016_j_chemolab_2012_11_008 crossref_primary_10_1016_j_chemolab_2013_07_001 crossref_primary_10_1016_j_chemolab_2015_07_009 crossref_primary_10_1088_1742_6596_1897_1_012057 crossref_primary_10_1002_cem_2746 crossref_primary_10_1186_s12859_020_3411_3 crossref_primary_10_1002_cem_2508 crossref_primary_10_1016_j_cherd_2011_05_005 crossref_primary_10_1002_jccs_201600803 crossref_primary_10_1016_j_snb_2021_129726 crossref_primary_10_1002_bimj_201800148 crossref_primary_10_1002_cem_3311 crossref_primary_10_1016_j_chemolab_2016_11_006 crossref_primary_10_1016_j_chemolab_2020_104196 crossref_primary_10_1002_cem_2490 crossref_primary_10_1002_cem_3094 |
| Cites_doi | 10.1162/15324430152748218 10.1023/A:1012487302797 10.1016/j.aca.2006.08.031 10.1002/qsar.200390007 10.1109/72.788641 10.1007/978-1-4757-2440-0 10.1016/j.chemosphere.2005.04.115 10.1021/ci049869h 10.1016/j.ejmech.2008.03.004 10.1021/ci050041k 10.1016/j.chemolab.2009.01.002 10.1080/03610910903072391 10.1007/s521-001-8051-z 10.1021/ci700356w 10.1002/qsar.200810166 10.1007/s10822‐008‐9225‐4 10.2174/157340609788185927 10.3390/ijms10073237 10.1021/jm060604z 10.1021/jm030999b 10.1109/IGARSS.2006.48 10.1124/dmd.108.023507 10.1021/ci049971e 10.1021/ci600343x 10.1137/1.9780898719697 10.1016/j.ejmech.2009.04.050 10.1002/qsar.200610151 10.1016/S0169‐7439(97)00010‐5 10.1002/jcc.21190 |
| ContentType | Journal Article |
| Copyright | Copyright © 2011 John Wiley & Sons, Ltd. 2015 INIST-CNRS Copyright John Wiley and Sons, Limited Feb 2011 |
| Copyright_xml | – notice: Copyright © 2011 John Wiley & Sons, Ltd. – notice: 2015 INIST-CNRS – notice: Copyright John Wiley and Sons, Limited Feb 2011 |
| DBID | BSCLL AAYXX CITATION IQODW 7SC 7U5 8FD JQ2 L7M L~C L~D |
| DOI | 10.1002/cem.1364 |
| DatabaseName | Istex CrossRef Pascal-Francis Computer and Information Systems Abstracts Solid State and Superconductivity Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional |
| DatabaseTitle | CrossRef Technology Research Database Computer and Information Systems Abstracts – Academic ProQuest Computer Science Collection Computer and Information Systems Abstracts Solid State and Superconductivity Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional |
| DatabaseTitleList | Technology Research Database CrossRef Technology Research Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Chemistry |
| EISSN | 1099-128X |
| EndPage | 99 |
| ExternalDocumentID | 2286995351 23876609 10_1002_cem_1364 CEM1364 ark_67375_WNG_0HKV7CV3_X |
| Genre | article Feature |
| GroupedDBID | .3N .GA .Y3 05W 0R~ 10A 1L6 1OB 1OC 1ZS 31~ 33P 3SF 3WU 4.4 50Y 50Z 51W 51X 52M 52N 52O 52P 52S 52T 52U 52W 52X 53G 5GY 5VS 66C 702 7PT 8-0 8-1 8-3 8-4 8-5 8UM 930 A03 AAESR AAEVG AAHHS AANLZ AAONW AASGY AAXRX AAZKR ABCQN ABCUV ABDBF ABEML ABIJN ABPVW ACAHQ ACBWZ ACCFJ ACCZN ACGFS ACIWK ACPOU ACSCC ACXBN ACXQS ADBBV ADEOM ADIZJ ADKYN ADMGS ADOZA ADXAS ADZMN AEEZP AEIGN AEIMD AENEX AEQDE AEUQT AEUYR AFBPY AFFNX AFFPM AFGKR AFPWT AFZJQ AHBTC AITYG AIURR AIWBW AJBDE AJXKR ALAGY ALMA_UNASSIGNED_HOLDINGS ALUQN AMBMR AMYDB AQPKS ASPBG ATUGU AUFTA AVWKF AZBYB AZFZN AZVAB BAFTC BDRZF BFHJK BHBCM BMNLL BMXJE BNHUX BROTX BRXPI BSCLL BY8 CS3 D-E D-F DCZOG DPXWK DR1 DR2 DRFUL DRSTM DU5 EBS EJD F00 F01 F04 F5P FEDTE G-S G.N GNP GODZA H.T H.X HF~ HGLYW HHZ HVGLF HZ~ IX1 J0M JPC KQQ LATKE LAW LC2 LC3 LEEKS LH4 LH5 LITHE LOXES LP6 LP7 LUTES LW6 LYRES MEWTI MK4 MRFUL MRSTM MSFUL MSSTM MXFUL MXSTM N04 N05 N9A NF~ NNB O66 O9- OIG P2P P2W P2X P4D PALCI PQQKQ Q.N Q11 QB0 QRW R.K RIWAO RJQFR RNS ROL RWI RX1 RYL SAMSI SUPJJ UB1 W8V W99 WBFHL WBKPD WH7 WIB WIH WIK WJL WOHZO WQJ WRC WRJ WXSBR WYISQ XG1 XPP XV2 ZZTAW ~IA ~WT AAHQN AAMNL AANHP AAYCA ACRPL ACUHS ACYXJ ADNMO AFWVQ ALVPJ AAYXX AEYWJ AGHNM AGQPQ AGYGG CITATION AAMMB AEFGJ AGXDD AIDQK AIDYY IQODW 7SC 7U5 8FD JQ2 L7M L~C L~D |
| ID | FETCH-LOGICAL-c3924-750fe33fea3cabf235e8a84fb33584f51d174521f9d874b9466328d57e9f5e683 |
| IEDL.DBID | DR2 |
| ISSN | 0886-9383 1099-128X |
| IngestDate | Fri Jul 11 04:25:34 EDT 2025 Fri Jul 25 10:40:44 EDT 2025 Mon Jul 21 09:14:45 EDT 2025 Tue Jul 01 03:16:59 EDT 2025 Thu Apr 24 23:01:46 EDT 2025 Wed Jan 22 16:23:44 EST 2025 Wed Oct 30 10:01:58 EDT 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 2 |
| Keywords | Gradient Support Prediction Algorithm Modeling de-noising Structure activity relation structure-activity relationship (SAR) Classification kernel methods Models kernel principal component analysis (KPCA) Structure Chemometrics Principal component analysis support vector machines (SVMs) |
| Language | English |
| License | http://onlinelibrary.wiley.com/termsAndConditions#vor CC BY 4.0 |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c3924-750fe33fea3cabf235e8a84fb33584f51d174521f9d874b9466328d57e9f5e683 |
| Notes | ark:/67375/WNG-0HKV7CV3-X istex:08D606403290E3F1CED58B36EFE825803936F5FD ArticleID:CEM1364 SourceType-Scholarly Journals-1 ObjectType-Feature-1 content type line 14 ObjectType-Article-2 content type line 23 |
| PQID | 856034647 |
| PQPubID | 37374 |
| PageCount | 8 |
| ParticipantIDs | proquest_miscellaneous_901670625 proquest_journals_856034647 pascalfrancis_primary_23876609 crossref_primary_10_1002_cem_1364 crossref_citationtrail_10_1002_cem_1364 wiley_primary_10_1002_cem_1364_CEM1364 istex_primary_ark_67375_WNG_0HKV7CV3_X |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | February 2011 |
| PublicationDateYYYYMMDD | 2011-02-01 |
| PublicationDate_xml | – month: 02 year: 2011 text: February 2011 |
| PublicationDecade | 2010 |
| PublicationPlace | Chichester, UK |
| PublicationPlace_xml | – name: Chichester, UK – name: Bognor Regis – name: Chichester |
| PublicationTitle | Journal of chemometrics |
| PublicationTitleAlternate | J. Chemometrics |
| PublicationYear | 2011 |
| Publisher | John Wiley & Sons, Ltd Wiley Wiley Subscription Services, Inc |
| Publisher_xml | – name: John Wiley & Sons, Ltd – name: Wiley – name: Wiley Subscription Services, Inc |
| References | Li H, Sun J, Fan X, Sui X, Zhang L, Wang Y, He Z. Considerations and recent advances in qsar models for cytochrome p450-mediated drug metabolism prediction. J. Comput. Aided Mol. Des. 2008; 22(11): 843-855. DOI: 10.1007/s10822-008-9225-4 Vapnik V. The Nature of Statistical Learning Theory. Springer: New York,USA, 1995. Leong MK, Chen YM, Chen TH. Prediction of human cytochrome p450 2b6-substrate interactions using hierarchical support vector regression approach. J. Comput. Chem. 2009; 30(12): 1899-1909. Guyon I, Weston J, Barnhill S, Vapnik V. Gene selection for cancer classification using support vector machines. Mach. Learn. 2002; 46(1-3): 389-422. Schokopf B, Smola A (eds). Learning with Kernels. MIT Press: Cambridge, 2002. Bierman S, Steel S. Variable selection for support vector machines. Commun. Stat. Simul. Comput. 2009; 38(8): 1640-1658. Tropsha A, Gramatica P, Gombar V. The importance of being earnest: validation is the absolute essential for successful application and interpretation of QSPR models. QSAR Comb. Sci. 2003; 22(1): 69-77. Hou T, Wang J, Zhang W, Xu X. Adme evaluation in drug discovery. 7. prediction of oral absorption by correlation and classification. J. Chem. Inf. Model. 2006; 47(1): 208-218. DOI: 10.1021/ci600343x Yuan YN, Zhang RS, Hu RJ, Ruan XF. Prediction of ccr5 receptor binding affinity of substituted 1-(3,3-diphenylpropyl)-piperidinyl amides and ureas based on the heuristic method, support vector machine and projection pursuit regression. Eur. J. Med. Chem. 2009; 44(1): 25-34. Willmann S, Schmitt W, Keldenich J, Lippert J, Dressman JB. A physiological model for the estimation of the fraction dose absorbed in humans. J. Med. Chem. 2004; 47(16): 4022-4031. DOI: 10.1021/jm030999b Wu W, Massart DL, de Jong S. The kernel pca algorithms for wide data. part i: theory and algorithms. Chemom. Intell. Lab. Syst. 1997; 36(2): 165-172. DOI: 10.1016/S0169-7439(97)00010-5 Asikainen A, Kolehmainen M, Ruuskanen J, Tuppurainen K. Structure-based classification of active and inactive estrogenic compounds by decision tree, lvq and knn methods. Chemosphere 2006; 62(4): 658-673. Darnag R, Schmitzer A, Belmiloud Y, Villemin D, Jarid A, Chait A, Seyagh M, Cherqaoui D. Qsar studies of hept derivatives using support vector machines. QSAR Comb. Sci. 2009; 28(6-7): 709-718. Hansen P. Rank-deficient and Discrete Ill-posed Problems: Numerical Aspects of Linear Inversion. Society for Industrial Mathematics: Philadelphia, USA, 1998. Yuan H, Huang JP, Cao CZ. Prediction of skin sensitization with a particle swarm optimized support vector machine. Int. J. Mol. Sci. 2009; 10(7): 3237-3254. Liu XQ, Kruger U, Littler T, Xie L, Wang SQ. Moving window kernel pca for adaptive monitoring of nonlinear processes. Chemom. Intell. Lab. Syst. 2009; 96(2): 132-143. Agatonovic-Kustrin S, Davies P, Turner JV. Structure-activity relationships for serotonin transporter and dopamine receptor selectivity. Med. Chem. 2009; 5(3): 271-278. Wang Y-H, Li Y, Yang S-L, Yang L. Classification of substrates and inhibitors of p-glycoprotein using unsupervised machine learning approach. J. Chem. Inf. Model. 2005; 45(3): 750-757. DOI: 10.1021/ci050041k Gramatica P. Principles of QSAR models validation: internal and external. QSAR Comb. Sci. 2007; 26(5): 694-701. Vasanthanathan P, Taboureau O, Oostenbrink C, Vermeulen NPE, Olsen L, Jorgensen FS. Classification of cytochrome p450 1a2 inhibitors and noninhibitors by machine learning techniques. Drug Metab. Dispos. 2009; 37(3): 658-664. Cristianini N, Shawe-Taylor J (eds). An Introduction to Support Vector Machines. Cambridge University Press: Cambridge, 2000. Kaiser D, Terfloth L, Kopp S, Schulz J, de Laet R, Chiba P, Ecker GF, Gasteiger J. Self-organizing maps for identification of new inhibitors of p-glycoprotein. J. Med. Chem. 2007; 50(7): 1698-1702. DOI: 10.1021/jm060604z Mangasarian O, Musicant D. Lagrangian support vector machines. J. Mach. Learn. Res. 2001; 1: 161-177. Xue Y, Yap CW, Sun LZ, Cao ZW, Wang JF, Chen YZ. Prediction of p-glycoprotein substrates by a support vector machine approach. J. Chem. Inf. Comput. Sci. 2004; 44(4): 1497-1505. Askjaer S, Langgard M. Combining pharmacophore fingerprints and pls-discriminant analysis for virtual screening and sar elucidation. J. Chem. Inf. Model. 2008; 48(3): 476-488. Scholkopf B, Mika S, Burges CJC, Knirsch P, Muller KR, Ratsch G, Smola AJ. Input space versus feature space in kernel-based methods. IEEE Trans. Neural Netw. 1999; 10(5): 1000-1017. Xue Y, Li ZR, Yap CW, Sun LZ, Chen X, Chen YZ. 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(5): 1630-1638. DOI: 10.1021/ci049869h Rosipal R, Girolami M, Trejo LJ, Cichocki A. Kernel pca for feature extraction and de-noising in nonlinear regression. Neural Comput. Appl. 2001; 10(3): 231-243. Li JZ, Liu HX, Yao XJ, Liu MC, Hu ZD, Fan BT. Structure-activity relationship study of oxindole-based inhibitors of cyclin-dependent kinases based on least-squares support vector machines. Anal. Chim. Acta 2007; 581(2): 333-342. Dong XW, Jiang CY, Hu HY, Yan JY, Chen J, Hu YZ. Qsar study of akt/protein kinase b (pkb) inhibitors using support vector machine. Eur. J. Med. Chem. 2009; 44(10): 4090-4097. 2009; 44 2004; 44 2004; 47 2007; 581 1998 2006 1995 2007; 50 2002 2005; 45 2009; 28 2009; 30 2009; 96 2009; 10 2006; 62 2000 2002; 46 1997; 36 2006; 47 2008; 48 1999; 10 2008; 22 2009; 5 2001; 1 2009; 38 2009; 37 2007; 26 2003; 22 2001; 10 e_1_2_9_30_2 e_1_2_9_10_2 e_1_2_9_12_2 e_1_2_9_31_2 e_1_2_9_11_2 e_1_2_9_32_2 e_1_2_9_14_2 e_1_2_9_13_2 e_1_2_9_16_2 Cristianini N (e_1_2_9_21_2) 2000 e_1_2_9_15_2 e_1_2_9_18_2 e_1_2_9_17_2 e_1_2_9_19_2 e_1_2_9_20_2 Schokopf B (e_1_2_9_22_2) 2002 e_1_2_9_23_2 e_1_2_9_7_2 e_1_2_9_6_2 e_1_2_9_5_2 e_1_2_9_4_2 e_1_2_9_3_2 e_1_2_9_2_2 e_1_2_9_9_2 e_1_2_9_8_2 e_1_2_9_25_2 e_1_2_9_24_2 e_1_2_9_27_2 e_1_2_9_26_2 e_1_2_9_29_2 e_1_2_9_28_2 |
| References_xml | – reference: Wu W, Massart DL, de Jong S. The kernel pca algorithms for wide data. part i: theory and algorithms. Chemom. Intell. Lab. Syst. 1997; 36(2): 165-172. DOI: 10.1016/S0169-7439(97)00010-5 – reference: Liu XQ, Kruger U, Littler T, Xie L, Wang SQ. Moving window kernel pca for adaptive monitoring of nonlinear processes. Chemom. Intell. Lab. Syst. 2009; 96(2): 132-143. – reference: Asikainen A, Kolehmainen M, Ruuskanen J, Tuppurainen K. Structure-based classification of active and inactive estrogenic compounds by decision tree, lvq and knn methods. Chemosphere 2006; 62(4): 658-673. – reference: Kaiser D, Terfloth L, Kopp S, Schulz J, de Laet R, Chiba P, Ecker GF, Gasteiger J. Self-organizing maps for identification of new inhibitors of p-glycoprotein. J. Med. Chem. 2007; 50(7): 1698-1702. DOI: 10.1021/jm060604z – reference: Gramatica P. Principles of QSAR models validation: internal and external. QSAR Comb. Sci. 2007; 26(5): 694-701. – reference: Li H, Sun J, Fan X, Sui X, Zhang L, Wang Y, He Z. Considerations and recent advances in qsar models for cytochrome p450-mediated drug metabolism prediction. J. Comput. Aided Mol. Des. 2008; 22(11): 843-855. DOI: 10.1007/s10822-008-9225-4 – reference: Vasanthanathan P, Taboureau O, Oostenbrink C, Vermeulen NPE, Olsen L, Jorgensen FS. Classification of cytochrome p450 1a2 inhibitors and noninhibitors by machine learning techniques. Drug Metab. Dispos. 2009; 37(3): 658-664. – reference: Guyon I, Weston J, Barnhill S, Vapnik V. Gene selection for cancer classification using support vector machines. Mach. Learn. 2002; 46(1-3): 389-422. – reference: Wang Y-H, Li Y, Yang S-L, Yang L. Classification of substrates and inhibitors of p-glycoprotein using unsupervised machine learning approach. J. Chem. Inf. Model. 2005; 45(3): 750-757. DOI: 10.1021/ci050041k – reference: Hou T, Wang J, Zhang W, Xu X. Adme evaluation in drug discovery. 7. prediction of oral absorption by correlation and classification. J. Chem. Inf. Model. 2006; 47(1): 208-218. DOI: 10.1021/ci600343x – reference: Scholkopf B, Mika S, Burges CJC, Knirsch P, Muller KR, Ratsch G, Smola AJ. Input space versus feature space in kernel-based methods. IEEE Trans. Neural Netw. 1999; 10(5): 1000-1017. – reference: Mangasarian O, Musicant D. Lagrangian support vector machines. J. Mach. Learn. Res. 2001; 1: 161-177. – reference: Xue Y, Yap CW, Sun LZ, Cao ZW, Wang JF, Chen YZ. Prediction of p-glycoprotein substrates by a support vector machine approach. J. Chem. Inf. Comput. Sci. 2004; 44(4): 1497-1505. – reference: Yuan YN, Zhang RS, Hu RJ, Ruan XF. Prediction of ccr5 receptor binding affinity of substituted 1-(3,3-diphenylpropyl)-piperidinyl amides and ureas based on the heuristic method, support vector machine and projection pursuit regression. Eur. J. Med. Chem. 2009; 44(1): 25-34. – reference: Rosipal R, Girolami M, Trejo LJ, Cichocki A. Kernel pca for feature extraction and de-noising in nonlinear regression. Neural Comput. Appl. 2001; 10(3): 231-243. – reference: Li JZ, Liu HX, Yao XJ, Liu MC, Hu ZD, Fan BT. Structure-activity relationship study of oxindole-based inhibitors of cyclin-dependent kinases based on least-squares support vector machines. Anal. Chim. Acta 2007; 581(2): 333-342. – reference: Willmann S, Schmitt W, Keldenich J, Lippert J, Dressman JB. A physiological model for the estimation of the fraction dose absorbed in humans. J. Med. Chem. 2004; 47(16): 4022-4031. DOI: 10.1021/jm030999b – reference: Leong MK, Chen YM, Chen TH. Prediction of human cytochrome p450 2b6-substrate interactions using hierarchical support vector regression approach. J. Comput. Chem. 2009; 30(12): 1899-1909. – reference: Askjaer S, Langgard M. Combining pharmacophore fingerprints and pls-discriminant analysis for virtual screening and sar elucidation. J. Chem. Inf. Model. 2008; 48(3): 476-488. – reference: Xue Y, Li ZR, Yap CW, Sun LZ, Chen X, Chen YZ. 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(5): 1630-1638. DOI: 10.1021/ci049869h – reference: Dong XW, Jiang CY, Hu HY, Yan JY, Chen J, Hu YZ. Qsar study of akt/protein kinase b (pkb) inhibitors using support vector machine. Eur. J. Med. Chem. 2009; 44(10): 4090-4097. – reference: Vapnik V. The Nature of Statistical Learning Theory. Springer: New York,USA, 1995. – reference: Darnag R, Schmitzer A, Belmiloud Y, Villemin D, Jarid A, Chait A, Seyagh M, Cherqaoui D. Qsar studies of hept derivatives using support vector machines. QSAR Comb. Sci. 2009; 28(6-7): 709-718. – reference: Cristianini N, Shawe-Taylor J (eds). An Introduction to Support Vector Machines. Cambridge University Press: Cambridge, 2000. – reference: Agatonovic-Kustrin S, Davies P, Turner JV. Structure-activity relationships for serotonin transporter and dopamine receptor selectivity. Med. Chem. 2009; 5(3): 271-278. – reference: Yuan H, Huang JP, Cao CZ. Prediction of skin sensitization with a particle swarm optimized support vector machine. Int. J. Mol. Sci. 2009; 10(7): 3237-3254. – reference: Schokopf B, Smola A (eds). Learning with Kernels. MIT Press: Cambridge, 2002. – reference: Bierman S, Steel S. Variable selection for support vector machines. Commun. Stat. Simul. Comput. 2009; 38(8): 1640-1658. – reference: Hansen P. Rank-deficient and Discrete Ill-posed Problems: Numerical Aspects of Linear Inversion. Society for Industrial Mathematics: Philadelphia, USA, 1998. – reference: Tropsha A, Gramatica P, Gombar V. The importance of being earnest: validation is the absolute essential for successful application and interpretation of QSPR models. QSAR Comb. Sci. 2003; 22(1): 69-77. – volume: 47 start-page: 208 issue: 1 year: 2006 end-page: 218 article-title: Adme evaluation in drug discovery. 7. prediction of oral absorption by correlation and classification publication-title: J. Chem. Inf. Model. – volume: 22 start-page: 843 issue: 11 year: 2008 end-page: 855 article-title: Considerations and recent advances in qsar models for cytochrome p450‐mediated drug metabolism prediction publication-title: J. Comput. Aided Mol. Des. – volume: 44 start-page: 25 issue: 1 year: 2009 end-page: 34 article-title: Prediction of ccr5 receptor binding affinity of substituted 1‐(3,3‐diphenylpropyl)‐piperidinyl amides and ureas based on the heuristic method, support vector machine and projection pursuit regression publication-title: Eur. J. Med. Chem. – volume: 46 start-page: 389 issue: 1–3 year: 2002 end-page: 422 article-title: Gene selection for cancer classification using support vector machines publication-title: Mach. Learn. – volume: 44 start-page: 1497 issue: 4 year: 2004 end-page: 1505 article-title: Prediction of p‐glycoprotein substrates by a support vector machine approach publication-title: J. Chem. Inf. Comput. Sci. – volume: 44 start-page: 4090 issue: 10 year: 2009 end-page: 4097 article-title: Qsar study of akt/protein kinase b (pkb) inhibitors using support vector machine publication-title: Eur. J. Med. Chem. – volume: 50 start-page: 1698 issue: 7 year: 2007 end-page: 1702 article-title: Self‐organizing maps for identification of new inhibitors of p‐glycoprotein publication-title: J. Med. Chem. – volume: 44 start-page: 1630 issue: 5 year: 2004 end-page: 1638 article-title: Effect of molecular descriptor feature selection in support vector machine classification of pharmacokinetic and toxicological properties of chemical agents publication-title: J. Chem. Inf. Comput. Sci. – volume: 10 start-page: 3237 issue: 7 year: 2009 end-page: 3254 article-title: Prediction of skin sensitization with a particle swarm optimized support vector machine publication-title: Int. J. Mol. Sci. – volume: 37 start-page: 658 issue: 3 year: 2009 end-page: 664 article-title: Classification of cytochrome p450 1a2 inhibitors and noninhibitors by machine learning techniques publication-title: Drug Metab. Dispos. – volume: 10 start-page: 231 issue: 3 year: 2001 end-page: 243 article-title: Kernel pca for feature extraction and de‐noising in nonlinear regression publication-title: Neural Comput. Appl. – volume: 45 start-page: 750 issue: 3 year: 2005 end-page: 757 article-title: Classification of substrates and inhibitors of p‐glycoprotein using unsupervised machine learning approach publication-title: J. Chem. Inf. Model. – year: 2000 – volume: 48 start-page: 476 issue: 3 year: 2008 end-page: 488 article-title: Combining pharmacophore fingerprints and pls‐discriminant analysis for virtual screening and sar elucidation publication-title: J. Chem. Inf. Model. – volume: 36 start-page: 165 issue: 2 year: 1997 end-page: 172 article-title: The kernel pca algorithms for wide data. part i: theory and algorithms publication-title: Chemom. Intell. Lab. Syst. – volume: 47 start-page: 4022 issue: 16 year: 2004 end-page: 4031 article-title: A physiological model for the estimation of the fraction dose absorbed in humans publication-title: J. Med. Chem. – volume: 28 start-page: 709 issue: 6–7 year: 2009 end-page: 718 article-title: Qsar studies of hept derivatives using support vector machines publication-title: QSAR Comb. Sci. – year: 1998 – start-page: 168 year: 2006 end-page: 171 – volume: 1 start-page: 161 year: 2001 end-page: 177 article-title: Lagrangian support vector machines publication-title: J. Mach. Learn. Res. – volume: 26 start-page: 694 issue: 5 year: 2007 end-page: 701 article-title: Principles of QSAR models validation: internal and external publication-title: QSAR Comb. Sci. – volume: 22 start-page: 69 issue: 1 year: 2003 end-page: 77 article-title: The importance of being earnest: validation is the absolute essential for successful application and interpretation of QSPR models publication-title: QSAR Comb. Sci. – year: 2002 – volume: 10 start-page: 1000 issue: 5 year: 1999 end-page: 1017 article-title: Input space versus feature space in kernel‐based methods publication-title: IEEE Trans. Neural Netw. – volume: 5 start-page: 271 issue: 3 year: 2009 end-page: 278 article-title: Structure‐activity relationships for serotonin transporter and dopamine receptor selectivity publication-title: Med. Chem. – year: 1995 – volume: 96 start-page: 132 issue: 2 year: 2009 end-page: 143 article-title: Moving window kernel pca for adaptive monitoring of nonlinear processes publication-title: Chemom. Intell. Lab. Syst. – volume: 581 start-page: 333 issue: 2 year: 2007 end-page: 342 article-title: Structure‐activity relationship study of oxindole‐based inhibitors of cyclin‐dependent kinases based on least‐squares support vector machines publication-title: Anal. Chim. Acta – volume: 30 start-page: 1899 issue: 12 year: 2009 end-page: 1909 article-title: Prediction of human cytochrome p450 2b6‐substrate interactions using hierarchical support vector regression approach publication-title: J. Comput. Chem. – volume: 38 start-page: 1640 issue: 8 year: 2009 end-page: 1658 article-title: Variable selection for support vector machines publication-title: Commun. Stat. Simul. Comput. – volume: 62 start-page: 658 issue: 4 year: 2006 end-page: 673 article-title: Structure‐based classification of active and inactive estrogenic compounds by decision tree, lvq and knn methods publication-title: Chemosphere – ident: e_1_2_9_24_2 doi: 10.1162/15324430152748218 – ident: e_1_2_9_15_2 doi: 10.1023/A:1012487302797 – ident: e_1_2_9_6_2 doi: 10.1016/j.aca.2006.08.031 – ident: e_1_2_9_32_2 doi: 10.1002/qsar.200390007 – ident: e_1_2_9_19_2 doi: 10.1109/72.788641 – ident: e_1_2_9_23_2 doi: 10.1007/978-1-4757-2440-0 – ident: e_1_2_9_4_2 doi: 10.1016/j.chemosphere.2005.04.115 – ident: e_1_2_9_16_2 doi: 10.1021/ci049869h – ident: e_1_2_9_8_2 doi: 10.1016/j.ejmech.2008.03.004 – ident: e_1_2_9_29_2 doi: 10.1021/ci050041k – ident: e_1_2_9_17_2 doi: 10.1016/j.chemolab.2009.01.002 – ident: e_1_2_9_14_2 doi: 10.1080/03610910903072391 – volume-title: Learning with Kernels year: 2002 ident: e_1_2_9_22_2 – ident: e_1_2_9_18_2 doi: 10.1007/s521-001-8051-z – ident: e_1_2_9_5_2 doi: 10.1021/ci700356w – ident: e_1_2_9_9_2 doi: 10.1002/qsar.200810166 – ident: e_1_2_9_2_2 doi: 10.1007/s10822‐008‐9225‐4 – ident: e_1_2_9_3_2 doi: 10.2174/157340609788185927 – ident: e_1_2_9_13_2 doi: 10.3390/ijms10073237 – ident: e_1_2_9_28_2 doi: 10.1021/jm060604z – ident: e_1_2_9_27_2 doi: 10.1021/jm030999b – ident: e_1_2_9_7_2 doi: 10.1109/IGARSS.2006.48 – ident: e_1_2_9_12_2 doi: 10.1124/dmd.108.023507 – ident: e_1_2_9_30_2 doi: 10.1021/ci049971e – ident: e_1_2_9_26_2 doi: 10.1021/ci600343x – ident: e_1_2_9_25_2 doi: 10.1137/1.9780898719697 – ident: e_1_2_9_10_2 doi: 10.1016/j.ejmech.2009.04.050 – volume-title: An Introduction to Support Vector Machines year: 2000 ident: e_1_2_9_21_2 – ident: e_1_2_9_31_2 doi: 10.1002/qsar.200610151 – ident: e_1_2_9_20_2 doi: 10.1016/S0169‐7439(97)00010‐5 – ident: e_1_2_9_11_2 doi: 10.1002/jcc.21190 |
| SSID | ssj0009934 |
| Score | 2.0221252 |
| Snippet | In this paper, a two‐step nonlinear classification algorithm is proposed to model the structure–activity relationship (SAR) between bioactivities and molecular... In this paper, a two-step nonlinear classification algorithm is proposed to model the structure-activity relationship (SAR) between bioactivities and molecular... |
| SourceID | proquest pascalfrancis crossref wiley istex |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 92 |
| SubjectTerms | Algorithms Biochemistry Chemistry Classification Comparative analysis de-noising Exact sciences and technology General and physical chemistry General. Nomenclature, chemical documentation, computer chemistry kernel methods kernel principal component analysis (KPCA) Kernels Mathematical models Molecular structure Nonlinearity Performance evaluation Principal components analysis structure-activity relationship (SAR) Support vector machines support vector machines (SVMs) Synthetic aperture radar Theory of reactions, general kinetics. Catalysis. Nomenclature, chemical documentation, computer chemistry |
| Title | Combination of kernel PCA and linear support vector machine for modeling a nonlinear relationship between bioactivity and molecular descriptors |
| URI | https://api.istex.fr/ark:/67375/WNG-0HKV7CV3-X/fulltext.pdf https://onlinelibrary.wiley.com/doi/abs/10.1002%2Fcem.1364 https://www.proquest.com/docview/856034647 https://www.proquest.com/docview/901670625 |
| Volume | 25 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Lb9QwELZQe4ALlJdYCpWREJzSpvEzxypqWYGoEKJlJQ6Wk9iiWvahZLeq-BP9y52xk5RFICFOWSmTZNYe298kn78h5LXXNcSKs4mouEyQd5FomfsktXkunAIQUQe2xakcn_H3EzHpWJW4FybqQwwv3HBkhPkaB7gt24Nb0dDKzZCjhVKgeEA89PlWOQqWXR4BpExyyMJ63dk0O-gv3FiJtrFRr5AZaVtoHB-rWmzAzl_Ba1h9Th6Qb73fkXQy3V-vyv3q52-Sjv_3x3bI_Q6U0qMYRQ_JHTd_RO4WfS24x-Qapg1IoUMv0oWnU9fAU-in4ojaeU3xmbah7XqJaJ5ehi8BdBZ4mo56_I0Fd2CVpJbOo49g3_REvO8XS9oRxmh5scC9FljSItx71tfvpbWLU9yiaZ-Qs5PjL8U46Uo5JBUAMJ4ALvGOMe8sq2zpMyactpr7kjFAQF4c1pAZAZLwea0VL1H0nmW6FsrlXjip2VOyBe65Z4TqzGepzZzKwZKp1CrvuYBEi2WHEuxH5G3frabqdM6x3MYPExWaMwMNbLCBR-TVYLmM2h5_sHkTImMwsM0UuXBKmK-n70w6_nCuinNmJiOytxE6wwWAiZSUKfi128eS6eaJ1mgAnIxLrkaEDmehb_GrjZ27xbo1OW4USSFNBVdC2PzVV1Mcf8Tj83813CX34ityZOe8IFurZu1eAsZalXthNN0AOpIkFg |
| linkProvider | Wiley-Blackwell |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3fb9MwED6N7WG88ButGwwjIXjKlsVOnIinKWwUtlUIbaMPSJaT2GLq-kNJixD_BP8yd3aTUQQS4qmVemku9tn-zvn8HcALm1YYK0YHcSmSgHgXQZpkNgh1lsVGIoioHNtikPQvxPthPFyD1-1ZGK8P0W240chw8zUNcNqQ3r9RDS3NmEha4hZsCMQZlHm9-XijHYULr_AQMgkyzMNa5dkw2m-vXFmLNqhZvxE3UjfYPNbXtVgBnr_CV7f-HN-Fz63nnnYy2lvMi73y-2-ijv_5aPfgzhKXskMfSPdhzUwewGbeloN7CD9w5sAs2nUkm1o2MjXehn3ID5meVIxuqmvWLGYE6NlX9zKAjR1V0zBL36nmDi6UTLOJdxLt65aL9-VqxpacMVZcTem4BVW1cP89bkv4ssr4WW5aN4_g4vjoPO8Hy2oOQYkYTAQITazh3BrNS13YiMcm1amwBecIgmx8UGFyhGDCZlUqRUG69zxKq1iazMYmSfljWEf3zBawNLJRqCMjM7TkMtTSWhFjrsWjgwTte_Cq7VdVLqXOqeLGtfIizZHCBlbUwD143lnOvLzHH2xeutDoDHQ9IjqcjNWnwVsV9k8uZX7J1bAHuyux012AsEgmSYh-7bTBpJZTRaNSxJxcJEL2gHW_Yt_Sixs9MdNFozI6KxJipoquuLj5q68qPzqjz-1_NXwGm_3zs1N1-m5wsgO3_Y45kXWewPq8XpinCLnmxa4bWj8BZQ0oNQ |
| linkToPdf | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3bbtQwELWglYAX7hVLoRgJwVPaNL4lj1XoslBYVYiWlXiwnMQW1bIXJbsI8RP8MjN2krIIJMTTRtpJMrHH9pnk-Awhz1xaQaxYE4mSywh5F1EqMxfFJsuEVQAiKs-2GMvRGX8zEZOWVYl7YYI-RP_CDUeGn69xgC8rd3ApGlraGXK0-FWyzSUACQRE7y-lo2Dd5QFByiiDNKwTno2Tg-7MjaVoG1v1G1IjTQOt40JZiw3c-St69cvP8Bb51DkeWCfT_fWq2C-__6bp-H9PdpvcbFEpPQphdIdcsfO75HreFYO7R37AvAE5tO9GunB0amu4Cz3Nj6iZVxTvaWrarJcI5-lX_ymAzjxR01KHx1hxB5ZJaug8-Aj2dcfE-3yxpC1jjBYXC9xsgTUt_LVnXQFfWtkwxy3q5j45Gx5_yEdRW8shKgGB8QiAibOMOWtYaQqXMGFTk3JXMAYQyInDClIjgBIuq1LFC1S9Z0laCWUzJ6xM2Q7ZAvfsA0LTxCWxSazKwJKp2CjnuIBMiyWHEuwH5EXXrbpshc6x3sYXHSSaEw0NrLGBB-Rpb7kM4h5_sHnuI6M3MPUUyXBK6I_jVzoenZyr_JzpyYDsbYROfwKAIiVlDH7tdrGk24mi0SkgTsYlVwNC-3-hb_GzjZnbxbrRGe4UiSFPBVd82PzVV50fv8Pfh_9q-IRcO3051G9fj092yY3wuhyZOo_I1qpe28eAt1bFnh9YPwHXOibk |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Combination+of+kernel+PCA+and+linear+support+vector+machine+for+modeling+a+nonlinear+relationship+between+bioactivity+and+molecular+descriptors&rft.jtitle=Journal+of+chemometrics&rft.au=Fu%2C+Guang-Hui&rft.au=Cao%2C+Dong-Sheng&rft.au=Xu%2C+Qing-Song&rft.au=Li%2C+Hong-Dong&rft.date=2011-02-01&rft.issn=1099-128X&rft.volume=25&rft.issue=2&rft.spage=92&rft.epage=99&rft_id=info:doi/10.1002%2Fcem.1364&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0886-9383&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0886-9383&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0886-9383&client=summon |