Modified particle swarm optimization algorithm for variable selection in MLR and PLS modeling: QSAR studies of antagonism of angiotensin II antagonists

被引：114
作者：
Shen, Q [1 ]
Jiang, JH [1 ]
Jiao, CX [1 ]
Shen, GL [1 ]
Yu, RQ [1 ]
机构：
[1] Hunan Univ, Coll Chem & Chem Engn, State Key Lab Chemobiosensing & Chemometr, Changsha 410082, Peoples R China
来源：
EUROPEAN JOURNAL OF PHARMACEUTICAL SCIENCES | 2004年 / 22卷 / 2-3期
基金：
中国国家自然科学基金;
关键词：
particle swarm optimization; quantitative structure-activity relationships; variable selection; antagonism;
D O I：
10.1016/j.ejps.2004.03.002
中图分类号：
R9 [药学];
学科分类号：
1007 ;
摘要：
A version of modified particle swarm optimization (PSO) algorithm has been proposed. The PSO algorithm has been modified to adopt to the discrete combinatorial optimization problem and reduce the probability of sinking into local optima. In the modified PSO algorithm, the velocity represents the probability of element in each particle taking value 1 or 0. The modified discrete PSO algorithm is proposed to select variables in MLR and PLS modeling and to predict antagonism of angiotensin 11 antagonists. The modified C(p) is employed as fitness function. The results were compared to those obtained by GAs. Experimental results have demonstrated that the modified PSO is a useful tool for variable selection which converges quickly towards the optimal position. (C) 2004 Elsevier B.V. All rights reserved.
引用
收藏
页码：145 / 152
页数：8
相关论文
共 25 条
[1]   NONPEPTIDE ANGIOTENSIN-II ANTAGONISTS DERIVED FROM 4H-1,2,4-TRIAZOLES AND 3H-IMIDAZO[1,2-B][1,2,4]TRIAZOLES [J].
ASHTON, WT ;
CANTONE, CL ;
CHANG, LL ;
HUTCHINS, SM ;
STRELITZ, RA ;
MACCOSS, M ;
CHANG, RSL ;
LOTTI, VJ ;
FAUST, KA ;
CHEN, TB ;
BUNTING, P ;
SCHORN, TW ;
KIVLIGHN, SD ;
SIEGL, PKS .
JOURNAL OF MEDICINAL CHEMISTRY, 1993, 36 (05) :591-609
[2]   Particle swarm optimization -: Mass-spring system analogon [J].
Brandstätter, B ;
Baumgartner, U .
IEEE TRANSACTIONS ON MAGNETICS, 2002, 38 (02) :997-1000
[3]  
Carlisle A, 2000, IC-AI'2000: PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 1-III, P429
[4]   Use of intelligent-particle swarm optimization in electromagnetics [J].
Ciuprina, G ;
Ioan, D ;
Munteanu, I .
IEEE TRANSACTIONS ON MAGNETICS, 2002, 38 (02) :1037-1040
[5]   The particle swarm - Explosion, stability, and convergence in a multidimensional complex space [J].
Clerc, M ;
Kennedy, J .
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION, 2002, 6 (01) :58-73
[6]   THE ELECTROTOPOLOGICAL STATE - STRUCTURE INFORMATION AT THE ATOMIC LEVEL FOR MOLECULAR GRAPHS [J].
HALL, LH ;
MOHNEY, B ;
KIER, LB .
JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES, 1991, 31 (01) :76-82
[7]   ELECTROTOPOLOGICAL STATE INDEXES FOR ATOM TYPES - A NOVEL COMBINATION OF ELECTRONIC, TOPOLOGICAL, AND VALENCE STATE INFORMATION [J].
HALL, LH ;
KIER, LB .
JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES, 1995, 35 (06) :1039-1045
[8]   QSAR study of the calcium channel antagonist activity of some recently synthesized dihydropyridine derivatives. An application of genetic algorithm for variable selection in MLR and PLS methods [J].
Hemmateenejad, B ;
Miri, R ;
Akhond, M ;
Shamsipur, M .
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2002, 64 (01) :91-99
[9]  
Kennedy J, 1997, IEEE SYS MAN CYBERN, P4104, DOI 10.1109/ICSMC.1997.637339
[10]  
Kennedy J, 1995, 1995 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS PROCEEDINGS, VOLS 1-6, P1942, DOI 10.1109/icnn.1995.488968
123