QSAR and k-nearest neighbor classification analysis of selective cyclooxygenase-2 inhibitors using topologically-based numerical descriptors

被引:111
作者
Kauffman, GW [1 ]
Jurs, PC [1 ]
机构
[1] Penn State Univ, Dept Chem, Davey Lab 152, University Pk, PA 16802 USA
来源
JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES | 2001年 / 41卷 / 06期
关键词
D O I
10.1021/ci010073h
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Experimental IC50 data for 314 selective cyclooxygenase-2 (COX-2) inhibitors are used to develop quantitation and classification models as a potential screening mechanism for larger libraries of target compounds. Experimental log(IC50) values ranged from 0.23 to greater than or equal to 5.00. Numerical descriptors encoding solely topological information are calculated for all structures and are used as inputs for linear regression, computational neural network, and classification analysis routines. Evolutionary optimization algorithms are then used to search the descriptor space for information-rich subsets which minimize the rms error of a diverse training set of compounds. An eight-descriptor model was identified as a robust predictor of experimental log(IC50) values, producing a root-mean-square error of 0.625 log units for an external prediction set of inhibitors which took no part in model development. A k-nearest neighbor classification study of the data set discriminating between active and inactive members produced a nine-descriptor model able to accurately classify 83.3% of the prediction set compounds correctly.
引用
收藏
页码:1553 / 1560
页数:8
相关论文
共 51 条
  • [11] EXPRESSION AND SELECTIVE-INHIBITION OF THE CONSTITUTIVE AND INDUCIBLE FORMS OF HUMAN CYCLOOXYGENASE
    GIERSE, JK
    HAUSER, SD
    CREELY, DP
    KOBOLDT, C
    RANGWALA, SH
    ISAKSON, PC
    SEIBERT, K
    [J]. BIOCHEMICAL JOURNAL, 1995, 305 : 479 - 484
  • [12] Inducible cyclooxygenase may have anti-inflammatory properties
    Gilroy, DW
    Colville-Nash, PR
    Willis, D
    Chivers, J
    Paul-Clark, MJ
    Willoughby, DA
    [J]. NATURE MEDICINE, 1999, 5 (06) : 698 - 701
  • [13] A FAMILY OF VARIABLE-METRIC METHODS DERIVED BY VARIATIONAL MEANS
    GOLDFARB, D
    [J]. MATHEMATICS OF COMPUTATION, 1970, 24 (109) : 23 - &
  • [14] Molecular search of new active drugs against Toxoplasma gondii
    Gozalbes, R
    Gálvez, J
    García-Domenech, R
    Derouin, F
    [J]. SAR AND QSAR IN ENVIRONMENTAL RESEARCH, 1999, 10 (01) : 47 - 60
  • [15] Superpendentic index: A novel topological descriptor for predicting biological activity
    Gupta, S
    Singh, M
    Madan, AK
    [J]. JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES, 1999, 39 (02): : 272 - 277
  • [16] Quantitative structure-activity relationship (QSAR) studies on non steroidal anti-inflammatory drugs (NSAIDs)
    Hadjipavlou-Litina, D
    [J]. CURRENT MEDICINAL CHEMISTRY, 2000, 7 (04) : 375 - 388
  • [17] Hall L. H., 1991, The Molecular Connectivity Chi Index and Kappa Shape Indices in Structure-Property Modeling
  • [18] Quantitative structure-activity relationship modeling of dopamine D1 antagonists using comparative molecular field analysis, genetic algorithms-partial least-squares, and K nearest neighbor methods
    Hoffman, B
    Cho, SJ
    Zheng, WF
    Wyrick, S
    Nichols, DE
    Mailman, RB
    Tropsha, A
    [J]. JOURNAL OF MEDICINAL CHEMISTRY, 1999, 42 (17) : 3217 - 3226
  • [19] Artificial neural network applied to prediction of fluorquinolone antibacterial activity by topological methods
    Jaén-Oltra, J
    Salabert-Salvador, T
    García-March, FJ
    Pérez-Giménez, F
    Tomás-Vert, F
    [J]. JOURNAL OF MEDICINAL CHEMISTRY, 2000, 43 (06) : 1143 - 1148
  • [20] JURS PC, 1979, COMPUTER ASSISTED DR