论文部分内容阅读
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.
457 kinds of physical and chemical properties of 20 kinds of natural amino acids were collected and classified into hydrophobic, electrical, hydrogen bonding and stereoscopic features, and then they were respectively subjected to Principal Component Analysis (PCA) to obtain a new amino acid residue structure Descriptor SVHEHS.Using this descriptor, the dipeptide, tripeptide and tetrapeptide of angiotensin converting enzyme (ACE) were respectively sequence-characterized and used to establish partial least square regression, PLS) model.The correlation coefficients of ACE inhibitory dipeptide, tripeptide and tetrapeptide models, correlation coefficient of cross validation, root mean square error and external validation were 0.607,0.507,0.587,0.783,0.852,0.813,0.232 , 0.839, 1, 1, 0, 0. 935.Thus, the PLS model established by SVHEHS descriptor has better fitting and predictive ability and can be used to study the quantitative structure-activity relationship of angiotensin converting enzyme inhibitory peptide.