| 有机化合物的陆地和水生环境毒性的计算机预测研究 |
| |
| 引用本文： | 程飞雄,沈杰,李卫华,Philip W.LEE,唐赟.有机化合物的陆地和水生环境毒性的计算机预测研究[J].农药学学报,2010,12(4):477-488. |
| |
| 作者姓名： | 程飞雄 沈杰 李卫华 Philip W.LEE 唐赟 |
| |
| 作者单位： | 1.华东理工大学 药学院 药物科学系,上海 200237 |
| |
| 基金项目： | Program for New Century Excellent Talents in University，the National S&T Major Project of china，the 111 Project |
| |
| 摘 要： | 采用子结构模式识别结合5种机器学习方法(包括支持向量机、C4.5决策树、k-最近邻法、随机森林法、和朴素贝叶斯法),分别构建了有机化合物对水生和陆地环境毒性评价的两个重要生物靶标——呆鲦鱼(Fathead minnow)和蜜蜂毒性的定性分类和定量回归预测模型。所有模型均通过独立测试集验证。其中,利用支持向量机分类算法得到的分类模型对呆鲦鱼和蜜蜂毒性测试集的整体预测准确度分别达到95.9%和95.0%。采用支持向量机回归算法得到的回归模型,对呆鲦鱼和蜜蜂毒性测试集的预测相关系数的平方(R2)分别达到0.878和0.663。最后,通过信息熵分析的方法,确定了一批能够代表性地表征呆鲦鱼和蜜蜂毒性的子结构模式,包括1,2-二酚、二烷基硫醚、二芳香醚和磷酸衍生物等。提出的方法为有毒化学品的生态风险评价提供了一种非常好的评价策略和可靠的工具。
|
| 关 键 词： | 呆鲦鱼毒性 蜜蜂毒性 定量结构-活性相关性(QSAR) 子结构模式识别 信息熵 支持向量机 |
| 收稿时间： | 2010/8/25 0:00:00 |
| 修稿时间： | 2010/9/21 0:00:00 |
In silico prediction of terrestrial and aquatic toxicities for organic chemicals |
| |
| CHENG Fei-xiong,SHEN Jie,LI Wei-hu,Philip W.LEE and TANG Yun.In silico prediction of terrestrial and aquatic toxicities for organic chemicals[J].Chinese Journal of Pesticide Science,2010,12(4):477-488. |
| |
| Authors: | CHENG Fei-xiong SHEN Jie LI Wei-hu Philip WLEE and TANG Yun |
| |
| Institution: | 1.Department of Pharmaceutical Sciences,School of Pharmacy,East China University of Science and Technology,130 Meilong Road,Shanghai 200237,China2.Graduate School of Agriculture,Kyoto University,Kitashirakawa Oiwake-cho,Sakyo-ku,Kyoto 606-8502,Japan |
| |
| Abstract: | Qualitative classification and quantitative regression models for fathead minnow and honey bee toxicity prediction were developed using different chemoinformatics techniques such as substructure pattern recognition and different machine learning methods.Specifically,methods include support vector machine,C4.5 decision tree,k-nearest neighbors,random forest and naive bayes.Reliable predictive models were developed and all models were validated by the independent test set.The overall predictive accuracy of the classification models using support vector machine were 95.9% for the fathead minnow test set and 95.0% for the honey bee test set.The square of correlation coefficient of regression models were 0.878 for the fathead minnow test set and 0.663 for the honey bee test set using support vector machine regression algorithm.At last,some representative substructure patterns for characterizing fathead minnow and honey bee toxicity compounds,such as 1,2-diphenol,dialkylthioether,diarylether and phosphoric_ acid_ derivative were also identified via the information gain analysis.The approaches provide a useful strategy and robust tools in the screening of ecotoxicological risk or environmental hazard potential of chemicals. |
| |
| Keywords: | fathead minnow toxicity honey bee toxicity quantitative structure-activity relationship(QSAR) substructure pattern recognition information gain support vector machine |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《农药学学报》浏览原始摘要信息 |
| 点击此处可从《农药学学报》下载免费的PDF全文 |
|
