环境化学
周鹏,曾晖,周原,吴世仁,李志良.支持向量机用于芳烃类化合物对芳烃受体亲和性QSAR研究[J].环境科学学报,2006,26(1):124-129
支持向量机用于芳烃类化合物对芳烃受体亲和性QSAR研究
- QSAR study on applying support vector machine to binding affinity of Ah receptor with aromatic compounds
- 基金项目:国家"春晖计划"教育部启动基金(No:99-4-4,99-4-37);重庆应用基础研究基金(No:01-3-6);重庆大学创新基金及重点项目(No:03-5-6,06-1-A)
- 周鹏
- 1. 重庆大学 化学化工学院, 重庆 400044; 2. 重庆大学 生物医学工程教育部与重庆市重点实验室, 重庆 400044
- 曾晖
- 1. 重庆大学 化学化工学院, 重庆 400044; 2. 重庆大学 生物医学工程教育部与重庆市重点实验室, 重庆 400044
- 周原
- 1. 重庆大学 生物医学工程教育部与重庆市重点实验室, 重庆 400044; 2. 重庆大学 生物工程学院, 重庆 400044
- 吴世仁
- 1. 重庆大学 化学化工学院, 重庆 400044; 2. 重庆大学 生物医学工程教育部与重庆市重点实验室, 重庆 400044
- 李志良
- 1. 重庆大学 化学化工学院, 重庆 400044; 2. 重庆大学 生物医学工程教育部与重庆市重点实验室, 重庆 400044
- 摘要:尝试将支持向量机(SVM)应用于3种典型芳烃类环境毒物(PCDD,PCDF和PCB)定量构效关系研究,通过对芳烃受体亲和性考察,结果发现该组样本的生物活性在一定程度上与分子电性距离矢量具有非线性联系.SVM对内部和外部样本都具良好稳定性能和预测能力:所得模型拟合、交叉检验、外部预测复相关系数及均方根误差分别为R2cum=0.922、Q2cum=0.825、Q2ext=0.834和RMSext=0.531将其与文献报道及多元线性回归、偏最小二乘、人工神经网络进行比较,结果表明对小样本、非线性问题SVM具较强拓展性及泛化能力,故在环境毒物评价和控制中具有广阔应用前景.
- Abstract:Support vector machine (SVM) was employed to investigate quantitative structure-activity relationship (QSAR) of three typical kinds of aromatic compounds (PCDDs, PCDFs and PCBs). It was found that binding affinity of Ah receptor with the aromatic compounds was nonlinearly relative to molecular electronegativity distance vector (MEDV) at a given conditions. The established model by SVM was proved to be of stability and predictability since its correlation coefficients of fitting (R2cum), cross validation (Q2cum) and external prediction (Q2ext) and error root mean square errors (RMSext) were 0.922, 0.825, 0.834 and 0.531 respectively. Therefore, it was proved to do good to induct especially for nonlinear and small sampling questions through comparison among reference reports and different methods such as multiple linear regression (MLR), partial least square regression (PLS) and artificial neural network (ANN). Therefore, SVM is expected to have broad prospect in evaluating and controlling environmentally toxic compounds.