中文摘要：

收集20种天然氨基酸的457种理化性质,按照疏水、电性特征、氢键贡献和立体特征分类后,对它们分别进行主成分分析（Principal component analysis,PCA）,得到一个新的氨基酸残基结构描述符SVHEHS.用该描述符分别对血管紧张素转化酶（Angiotensin Ⅰ converting enzyme,ACE）抑制二肽、三肽、四肽进行序列表征,并用来与生物活性建立偏最小二乘（Partial least square regression,PLS）模型.ACE抑制二肽、三肽、四肽模型的相关系数、交叉验证相关系数、均方根误差、外部验证相关系数分别为0.607,0.507,0.587,0.783;0.852,0.813,0.232,0.839;1,1,0,0.935.由此说明,采用SVHEHS描述符建立的PLS模型拟合、预测能力均较好,可用于血管紧张素转化酶抑制肽的定量构效关系研究.

英文摘要：

457 physicochemical properties indexes of 20 natural amino acids were collected and classified according to hydrophobic,electronic properties,hydrogen bonds contributions and steric properties.The new amino acid structure descriptor SVHEHS was obtained through principal component analysis of four panels of variables.The descriptor was used to characterize the structures of ACE inhibitory dipeptides,tripeptides and tetrapeptides,and partial least square regression（PLS） models with biological activities were achieved.The correlative coefficient（R2）,the cross-validation correlative coefficient（Q2LOO）,root mean square error（RMSE） and external validation correlative coefficient（Q2ext） of three models were 0.607,0.507,0.587,0.783;0.852,0.813,0.232,0.839;and 1,1,0,0.935,respectively.The results showed that the PLS models constructed by this descriptor had good fitting and predictive abilities,and could be used for quantitative structure activity relationship（QSAR） research of ACE inhibitory peptides.