Selective descriptor pruning for QSAR/QSPR studies using artificial neural networks

被引:14
|
作者
Turner, JV [1 ]
Cutler, DJ
Spence, I
Maddalena, DJ
机构
[1] Univ Sydney, Fac Pharm, Sydney, NSW 2006, Australia
[2] Univ Sydney, Fac Med, Dept Pharmacol, Sydney, NSW 2006, Australia
关键词
ANN; QSAR/QSPR; pruning; rho parameter; signal : noise ratio;
D O I
10.1002/jcc.10148
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Selection of optimal descriptors in quantitative structure-activity-property relationship (QSAR/QSPR) studies has been a perennial problem. Artificial Neural Networks (ANNs) have been used widely in QSAR/QSPR studies but less widely in descriptor selection. The current study used ANNs to select an optimal set of descriptors using large numbers of input variables. The effects of clean, noisy, and random input descriptors with linear, nonlinear, and periodic data on synthetic and real data QSAR/QSPR sets were examined. The optimal set of descriptors could be determined using a signal-to-noise ratio method. The optimal values for the rho parameter, which relates sample size to network architecture, were found to vary with the type of data. ANNs were able to detect meaningful descriptors in the presence of large numbers of random false descriptors. (C) 2003 Wiley Periodicals, Inc.
引用
收藏
页码:891 / 897
页数:7
相关论文
共 50 条
  • [41] Decision tree pruning using backpropagation neural networks
    Kijsirikul, B
    Chongkasemwongse, K
    IJCNN'01: INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, PROCEEDINGS, 2001, : 1876 - 1880
  • [42] Pruning artificial neural networks: an example using land cover classification of multi-sensor images
    Kavzoglu, T
    Mather, PM
    INTERNATIONAL JOURNAL OF REMOTE SENSING, 1999, 20 (14) : 2787 - 2803
  • [43] QSPR Studies on n-Octanol/water Partition Coefficient of Polychlorinated Biphenyls by Using Artificial Neural Network
    Jiao, Long
    2011 INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS AND NEURAL COMPUTING (FSNC 2011), VOL III, 2011, : 470 - 472
  • [44] Comparative study of QSAR/QSPR correlations using support vector machines, radial basis function neural networks, and multiple linear regression
    Yao, XJ
    Panaye, A
    Doucet, JP
    Zhang, RS
    Chen, HF
    Liu, MC
    Hu, ZD
    Fan, BT
    JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES, 2004, 44 (04): : 1257 - 1266
  • [45] QSAR study of heparanase inhibitors activity using artificial neural networks and Levenberg-Marquardt algorithm
    Jalali-Heravi, M.
    Asadollahi-Baboh, A.
    Shahbazikhah, P.
    EUROPEAN JOURNAL OF MEDICINAL CHEMISTRY, 2008, 43 (03) : 548 - 556
  • [46] QSPR Studies on n-Octanol/water Partition Coefficient of Polychlorinated Biphenyls by Using Artificial Neural Network
    Jiao, Long
    FUTURE MATERIAL RESEARCH AND INDUSTRY APPLICATION, PTS 1 AND 2, 2012, 455-456 : 925 - 929
  • [47] Detection of Auditory Selective Attention Using Artificial Neural Networks: An Intersubject Analysis
    Torres Figueiredo Silva, Pedro Sergio
    Felix, Leonardo Bonato
    XXVI BRAZILIAN CONGRESS ON BIOMEDICAL ENGINEERING, CBEB 2018, VOL. 2, 2019, 70 (02): : 161 - 165
  • [48] Neural networks in QSAR studies of new potassium channel openers
    Martínez, A
    Castro, A
    Stud, M
    Rodriguez, J
    Cardelús, I
    Llenas, J
    Fernandez, A
    Palacios, JM
    MEDICINAL CHEMISTRY RESEARCH, 1998, 8 (03) : 171 - 180
  • [50] Prediction of the selectivity coefficients of a berberine selective electrode using artificial neural networks
    Xing, WL
    He, XW
    ANALYTICA CHIMICA ACTA, 1997, 349 (1-3) : 283 - 286