Solving the Structure-Property Problem Using k-NN Classification

被引:0
作者
Perevoznikov, Aleksandr [1 ]
Shestov, Alexey [1 ]
Permiakov, Evgenii [1 ]
Kumskov, Mikhail [1 ]
机构
[1] Moscow MV Lomonosov State Univ, Fac Mech & Math, Dept Computat Math, Moscow 119991, Russia
来源
PATTERN RECOGNITION AND MACHINE INTELLIGENCE | 2011年 / 6744卷
关键词
Pattern Recognition; QSAR; QSPR; k-NN; DESCRIPTORS;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The solution of the "structure-property" based on the molecular graphs descriptors selection with k-NN classifier is proposed. The results of comparing the construction of predictive models using the search and without it are given. The stability of the classifier function construction quality is tested using the test sample.
引用
收藏
页码:49 / 53
页数:5
相关论文
共 8 条
[1]  
Clark M., 1990, TETRAHEDRON COMPUT M, V3, P47, DOI [DOI 10.1016/0898-5529(90)90120-W, 10.1016/0898-5529(90)90120-W]
[2]   Quantitative structure-activity relationship modeling of dopamine D1 antagonists using comparative molecular field analysis, genetic algorithms-partial least-squares, and K nearest neighbor methods [J].
Hoffman, B ;
Cho, SJ ;
Zheng, WF ;
Wyrick, S ;
Nichols, DE ;
Mailman, RB ;
Tropsha, A .
JOURNAL OF MEDICINAL CHEMISTRY, 1999, 42 (17) :3217-3226
[3]  
Hurst T, 1997, ABSTR PAP AM CHEM S, V213, P19
[4]  
Kohov V. A, 1994, IZVESTIYA RAN TECHNI, V5, P143
[5]  
KUMSKOV MI, 1994, DOKL AKAD NAUK+, V336, P64
[6]  
Svitanko I. V., 2007, 16 EUR S QUANT STRUC
[7]   QSAR modeling on the basis of 3D descriptors representing the electrostatic molecular surface (ambergris fragrances) [J].
Svitanko, Igor V. ;
Devetyarov, Dmitry A. ;
Tcheboukov, Dmitry E. ;
Dolmat, Maksirn S. ;
Zakharov, Alexey M. ;
Grigor'eva, Svetlana S. ;
Chichua, Viktoriya T. ;
Ponomareva, Lyudmila A. ;
Kumskov, Mikhail I. .
MENDELEEV COMMUNICATIONS, 2007, 17 (02) :90-91
[8]   Novel variable selection quantitative structure-property relationship approach based on the k-nearest-neighbor principle [J].
Zheng, WF ;
Tropsha, A .
JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES, 2000, 40 (01) :185-194