论文部分内容阅读
采用支持向量机回归(SVR)方法研究了40个抗癌化合物-二取代[(吖啶-4-酰胺基)丙基]甲胺类衍生物的定量构效关系,基于留一法交叉验证的结果,其平均相对误差是6.56%。结果表明,所建SVR模型的精度高于逆传播人工神经网络(BPANN)、多元线性回归(MLR)和偏最小二乘法(PLS)所得的结果。
The quantitative structure-activity relationship of 40 anticancer compounds-disubstituted [(acridine-4-carboxamido) propyl] methylamine derivatives was studied by support vector machine regression (SVR) As a result, its average relative error was 6.56%. The results show that the accuracy of SVR model is higher than that of BPANN, MLR and PLS.