期刊文献+

有机化合物水生毒性作用模式的支持向量机分类研究 被引量:1

Study of Support Vector Machine Classification of Model of Toxicity Action of Organic Compounds
在线阅读 下载PDF
导出
摘要 采用正辛醇/水分配系数logKow、最低未占有轨道能ELUMO、最高占有轨道能EHOMO等参数为描述变量,结合支持向量机算法,选择具有最大(L eave-One-Out,LOO)交互检验识别率,兼顾支持向量样本数和边界支持向量样本数为标准进行支持向量机建模参数优化,建立3组化合物水生毒性作用模式的SVM分类模型,分别对样本数为190、221、88的化合物水生毒性作用模式进行分类研究。结果表明,选用RBF核函数和C-SVC方法,3组参数分别为C=512、γ=2.048,C=512、γ=2.048,C=512、γ=0.512时,建立3个体系的SVM分类模型对全部样本的错误误别个数分别为0、2、0个,训练集模型对全部样本的错误识别个数分别为9,17,7。分类的效果与化合物描述子的选择和数量有关,如果增加合适的分子描述子,其分类结果相应地会得到改善。 Taking the octanol-water partition coefficient logKow,the energy of the lowest unoccupied molecular orbital ELUMO, and the energy of the highest occupied molecular orbitl EHOMOas described variables,and the highest leave-one-out (LOO) rate and the lower number of support vector samples and bounded support vectors as criterion of searching the optimum parameters of SVM, a classification problem about the model of aquatic toxicity action of 3 sets organic compounds(the number of compounds are 190,221 and 88 respectively) has been built by the SVM)(Support Vector Machines) technique. The result shows that the misclassified numbers of 3 sets compounds are 0,2,0 for C-SVC with RBF kernel and 9,17,7 for train-set while the 3 sets of parameters are c = 512 γ= 2, c = 512 γ=0. 248 and c = 512 γ= 0. 512 respectively. The qualities of SVM's classification models are relation to the selection and number of descriptors and would be improved after adding the number of descriptors.
出处 《广西科学》 CAS 2006年第1期31-34,共4页 Guangxi Sciences
基金 广西新世纪十百千人才计划 广西高校百名中青年学科带头人资助项目(桂教人2003年97号文) 桂林工学院青年扶持基金(桂工院科〔2004〕8号文)联合资助。
关键词 有机化合物 毒性作用 分类 支持向量机 organic compounds, toxicity action, classification, support vector machine
  • 相关文献

参考文献16

  • 1VAPNIK V.Estimation of dependencies based on empirical data[M].New York:Springer,1982.
  • 2VAPNIK V.The nature of statistical learning theory[M].New York:Springer-Verlag,1995.
  • 3VAPNIK V N.Statistical learning theory[M].New York:Wiley Publishers Science,1998.
  • 4IVANCIUC O.Support vector machines for cancer diagnosis from the blood concentration of Zn,Ba,Mg,Ca,Cu and Se[J].Internet Electronic Journal of Molecular Design,2002,1(8):418-427.
  • 5BROWN M P S,GRUNDY W N,LIN D,et al.Knowledgebased analysis of microarray gene expression data by using support vector machines[J].Process Natural Academy Sciences,2000,97(1):163-267.
  • 6BOCK J R,GOUGH D A.Predicting protein-protein interactions from primary structure[J].Bioinformatics,2001,17(5):455-460.
  • 7IVANCIUC O.Support vector machine identification of the aquatic toxicity mechanism of organic compounds[J].Internet Electronic Journal of Molecular Design,2002,1(3):157-172.
  • 8IVANCIUC O.Support vector machine classification of the carcinogenic activity of polycyclic aromatic hydrocarbons[J].Internet Electronic Journal of Molecular Design,2002,1(4):203-218.
  • 9LIND P,MALTSEVA T.Support vector machines for the estimation of aqueous solubility[J].Journal Chemical Information Computer Sciences,2003,43:1855-1859.
  • 10瞿海斌,刘晓宣,程翼宇.中药材三七提取液近红外光谱的支持向量机回归校正方法[J].高等学校化学学报,2004,25(1):39-43. 被引量:46

二级参考文献3

共引文献45

同被引文献20

  • 1韩香云,郑清.有机磷农药对海洋扁藻毒性构效关系的密度泛涵理论研究[J].安全与环境学报,2007,7(2):21-23. 被引量:7
  • 2WANGLiansheng(王连生),HANShuokui(韩朔睽).Molecular structure-nature and activeness (分子结构、性质与活性)[M].Beijing: Chemical Industry Press, 1997:2 - 26.
  • 3GUOZongru(郭宗儒).Pharmaceutical chemistry(药物化学总论)[ M]. Beijing: Chinese Medicine Science and Technology Press, 2003: 151 - 237.
  • 4HUUSKONEN J. QSAR modeling with the electro topological state indices : predicting the toxicity of organic chemicals [ J ]. Chemosphere, 2003, 50(7): 949-953.
  • 5TAO S, XI X H, XU F L, et al. A QSAR model for predicting toxicity (LC50) to rainbow trout[ J]. Water Research, 2002, 36( 11 ) : 2926 - 2930.
  • 6ZHANGXu(张旭) YuXunmin(余训民).A novel connectivity index for QSPR/QSAR study of alcohol.化学研究,2003,13(1):49-57.
  • 7ZHAO C Y, ZHANG H X, ZHANG X Y, et al. Application of support vector machine (SVM) for prediction toxic activity of different data sets[J]. Toxicology, 2006, 217(2/3) : 105 - 119.
  • 8NIAZI A, SAEED J B, DAVOOD N S. Prediction of toxicity of nitrebenzenes using AB initio and least squares support vector machines [J]. Journal of Hazardous Materials, 2008, 151(2/3) : 603-609.
  • 9NORINDER U. Support vector machine models in drug design: applications to drug transport processes and QSAR using simplex optimizations and variable selection[J]. Neurocomputing, 2003, 55(1/2): 337 - 346.
  • 10RUSSOM C L, BRADBURY S P, BRODERIUS S J, et al. Predicting modes of action from chemical structure: acute toxicity in the fathead minnow (Pimephales Promelas) [ J ]. Environmental Toxicology and Chemistry, 1997, 16(5) : 948 -967.

引证文献1

二级引证文献3

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部