分析测试学报
分析測試學報
분석측시학보
JOURNAL OF INSTRUMENTAL ANALYSIS
2013年
5期
604-608
,共5页
血管紧张素转化酶抑制肽%定量构效关系%多元线性回归%偏最小二乘%人工神经网络
血管緊張素轉化酶抑製肽%定量構效關繫%多元線性迴歸%偏最小二乘%人工神經網絡
혈관긴장소전화매억제태%정량구효관계%다원선성회귀%편최소이승%인공신경망락
以自组建的血管紧张素转化酶(Angiotensin I-converting enzyme)抑制肽库为研究对象,采用氨基酸描述符SVHEHS(Scores vector of hydrophobic,electronic,hydrogen bonds and steric properties)对各肽样本进行结构表征后,进行自交叉协方差(Auto cross covariances,ACC)处理,并分别利用多元线性回归(Multiple linear regression,MLR)、偏最小二乘(Partial least square regression,PLS)、人工神经网络(Artificial neural networks,ANN)3种建模方法进行ACE抑制肽QSAR建模.结果显示,所得MLR、PLS与ANN模型的相关系数(Correlation coefficient,R2)分别为0.744、0.862、0.958,留一交叉验证相关系数(Leave-one-out cross-validated correlation coefficient,Q2Loo)分别为0.532、0.829、0.948,外部验证复相关系数(External validated correlation coefficient,Q2ex(t))分别为0.567、0.632、0.634.因此,SVHEHS结合上述3种建模方法均适用于ACE抑制肽的QSAR研究,其中ANN的建模效果最优.
以自組建的血管緊張素轉化酶(Angiotensin I-converting enzyme)抑製肽庫為研究對象,採用氨基痠描述符SVHEHS(Scores vector of hydrophobic,electronic,hydrogen bonds and steric properties)對各肽樣本進行結構錶徵後,進行自交扠協方差(Auto cross covariances,ACC)處理,併分彆利用多元線性迴歸(Multiple linear regression,MLR)、偏最小二乘(Partial least square regression,PLS)、人工神經網絡(Artificial neural networks,ANN)3種建模方法進行ACE抑製肽QSAR建模.結果顯示,所得MLR、PLS與ANN模型的相關繫數(Correlation coefficient,R2)分彆為0.744、0.862、0.958,留一交扠驗證相關繫數(Leave-one-out cross-validated correlation coefficient,Q2Loo)分彆為0.532、0.829、0.948,外部驗證複相關繫數(External validated correlation coefficient,Q2ex(t))分彆為0.567、0.632、0.634.因此,SVHEHS結閤上述3種建模方法均適用于ACE抑製肽的QSAR研究,其中ANN的建模效果最優.
이자조건적혈관긴장소전화매(Angiotensin I-converting enzyme)억제태고위연구대상,채용안기산묘술부SVHEHS(Scores vector of hydrophobic,electronic,hydrogen bonds and steric properties)대각태양본진행결구표정후,진행자교차협방차(Auto cross covariances,ACC)처리,병분별이용다원선성회귀(Multiple linear regression,MLR)、편최소이승(Partial least square regression,PLS)、인공신경망락(Artificial neural networks,ANN)3충건모방법진행ACE억제태QSAR건모.결과현시,소득MLR、PLS여ANN모형적상관계수(Correlation coefficient,R2)분별위0.744、0.862、0.958,류일교차험증상관계수(Leave-one-out cross-validated correlation coefficient,Q2Loo)분별위0.532、0.829、0.948,외부험증복상관계수(External validated correlation coefficient,Q2ex(t))분별위0.567、0.632、0.634.인차,SVHEHS결합상술3충건모방법균괄용우ACE억제태적QSAR연구,기중ANN적건모효과최우.
