基于QSAR模型的有机磷化合物毒性预测

随着有机磷化合物(OPs)的广泛应用,其在越来越多的环境介质中被检测出来。大多数OPs具有毒性,但人们缺乏快速且有效的预测手段来对毒性进行评估。本文将结合E-Dragon软件计算的分子描述符,采用不同的QSAR模型对36个OPs的毒性进行预测。文中采用后退法作为描述符筛选方法,以均方根误差(RMSE)作为评价标准,共找到14个对线性核函数支持向量机(SVM)模型贡献较大的描述符;在最终得到的SVM模型交叉验证结果中,计算值与实际值的相关系数为0. 913,均方根误差为0. 388;外部测试验证结果中,平均相对误差为9. 10%。此外,采用多元线性回归(MLR)、人工神经网络(ANN)以及偏最小二乘回归(PLS)模型对OPs的毒性进行预测,交叉验证结果显示,三个模型的计算值与实际值的相关系数分别为0. 878、0. 686与0. 620,没有SVM模型的预测能力好。因此采用线性核函数的SVM模型对OPs进行毒性预测是一个行之有效的方法。     

分子距边矢量研究链烃与醛酮的定量构效关系

按碳原子及键合特性分类定义并计算了链烃包括烷、烯,炔,双烯,烯炔烃的分子距离－边数矢量（ＭＤＥ）,将１５３个链烃的ＭＤＥ矢量与相应的沸点相关联,得到良好的线性模型,复相关系数Ｒ＝０．９９７６,均方根误差０．９９７５、ＲＭＳ＝４．７２Ｋ和Ｒ＝０．９９７２、ＲＭＳ＝５．１３Ｋ。结果表明模型具有良好的稳定性和预测能力。进一步对杂原用染色因子进行标识,提出了一种适用于含杂原子体系分子结构描述的ＭＤＥ矢量,     

基于多元线性回归的血管紧张素转化酶抑制肽定量构效关系建模研究

利用氨基酸结构描述符SVHEHS分别对血管紧张素转化酶(Angiotensin I-converting Enzyme,ACE)竞争性抑制二肽、三肽、四肽序列表征后,建立结构与活性的多元线性回归(MLR)模型。ACE抑制二肽模型的相关系数、交叉验证相关系数、均方根误差、外部验证相关系数分别为0.851、0.781、0.327、0.792;三肽模型分别为0.805、0.717、0.339、0.817;四肽模型分别为0.792、0.553、0.393、0.630。研究表明,运用该描述符建立的ACE抑制肽MLR模型拟合、预测能力均较好,能较好解释ACE抑制肽的活性与结构间的关系。     

土壤总氮近红外光谱分析的波段优选

利用移动窗口偏最小二乘( MWPLS)和Savitzky-Golay(SG)平滑方法优选土壤总氮的近红外(NIR)光谱分析模型.从全部97个土壤样品中随机选出35个样品作为检验集;基于偏最小二乘交叉检验预测偏差(PLSPB),将余下62个样品划分为具有相似性的建模定标集(37个样品)、建模预测集(25个样品).最优波段为1692～2138 nm,SG平滑的导数阶数(OD)、多项式次数(DP)、平滑点数(NSP)分别为0,6,69,PLS因子数为11,建模预测均方根偏差(M-RMSEP)、建模预测相关系数(M-Rp)分别为0.015％,0.931,检验预测均方根偏差(V-RM-SEP)、检验预测相关系数(V-RP)分别为0.018％,0.882.其结果可为设计专用NIR仪器提供有价值的参考.     

Molecular Distance‐Edge Vector (μ) and Chromatographic Retention Index of Alkanes

A new method of quantitative structure‐retention relationship (QSRR) is proposed for estimating and predicting gas chromatographic retention indices of alkanes by using a novel molecular distance‐edge vector, called μ vector, containing 10 elements. The QSRR model (Ml), between the μ vector and chromatographic retention indices of 64 alkanes, was developed by using multiple linear regression (MLR) with the correlation coefficient being R = 0.9992 and the root mean square (RMS) error between the estimated and measured retention indices being RMS = 5.938. In order to explain the equation stability and prediction abilities of the M1 model, it is essential to perform a cross‐validation (CV) procedure. Satisfactory CV results have been obtained by using one external predicted sample every time with the average correlation coefficient being R = 0.9988 and average RMS = 7.128. If 21 compounds, about one third drawn from all 64 alkanes, construct an external prediction set and the 43 remaining construct an internal calibration set, the second QSRR model (M2) can be created by using calibration set data with statistics being R = 0.9993 and RMS = 5.796. The chromatographic retention indices of 21 compounds in the external testing set can be predicted by the M2 model and good prediction results are obtained with R = 0.9988 and RMS = 6.508.     

基于氨基酸描述符SVHEHS的ACE抑制肽QSAR研究

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(AngiotensinⅠconverting 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.     

Prediction of 31P nuclear magnetic resonance chemical shifts for phosphines

Quantitative relationships of the (31)P NMR chemical shifts of the phosphorus atoms in 291 phosphines with the atomic ionicity index (INI) and stereoscopic effect parameters (epsilon(alpha), epsilon(beta), epsilon(gamma)) were primarily investigated in this paper for modeling some fundamental quantitative structure-spectroscopy relationships (QSSR). The results indicated that the (31)P NMR chemical shifts of phosphines can be described as the quantitative equation by multiple linear regression (MLR): delta(p)(ppm)= -174.0197-2.6724INI+40.4755epsilon(alpha)+15.1141epsilon(beta)-3.1858epsilon(gamma), correlation coefficient R=0.9479, root mean square error (rms)=13.9, and cross-validated predictive correlation coefficient was found by using the leave-one-out procedure to be Q(2)=0.8919. Furthermore, through way of random sampling, the estimative stability and the predictive power of the proposed MLR model were examined by constructing data set randomly into both the internal training set and external test set of 261 and 30 compounds, respectively, and then the chemical shifts were estimated and predicted with the training correlation coefficient R=0.9467 and rms=13.4 and the external predicting correlation coefficient Q(ext)=0.9598 and rms=10.8. A partial least square model was developed that produced R=0.9466, Q=0.9407 and Q(ext)=0.9599, respectively. Those good results provided a new, simple, accurate and efficient methodology for calculating (31)P NMR chemical shifts of phosphines.     

Optimized partition of minimum spanning tree for piecewise modeling by particle swarm algorithm. QSAR studies of antagonism of angiotensin II antagonists

In quantitative structure-activity relationship (QSAR) modeling, when compounds in a training set exhibit a significant structural distinction between each other, in particular when chemicals of biological interest interacting on the receptor involve a different mechanism, it might be difficult to construct a single linear model for the whole population of compounds of interest with desired residuals. Developing a piecewise linear local model can be effective to circumvent the aforementioned problem. In this paper, piecewise modeling by the particle swarm optimization (PMPSO) approach is applied to QSAR study. The minimum spanning tree is used for clustering all compounds in the training set to form a tree, and the modified discrete PSO is applied to divide the tree to find satisfactory piecewise linear models. A new objective function is formulated for searching the appropriate piecewise linear models. The proposed PMPSO algorithm was used to predict the antagonism of angiotensin II. The results demonstrated that PMPSO is useful for improvement of the performance of regression models.     

QSAR and Docking Studies of Thiazolidine-4-carboxylic Acid Derivatives as Neuraminidase Inhibitors

In order to understand the chemical-biological interactions governing their activities toward neuraminidase(NA), QSAR models of 28 thiazolidine-4-carboxylic acid derivatives with inhibitory influenza A virus were developed. Here a quantitative structure activity relationship(QSAR) model was built by three-dimensional holographic atomic vector field(3 D-HoVAIF) and multiple linear regression(MLR). The estimation stability and prediction ability of the model were strictly analyzed by both internal and external validations. The correlation coefficient(R2) of established MLR model was 0.984, and the cross-validated correlation coefficient(Q2) of MLR model was 0.947. Furthermore, the cross-validated correlation coefficient for the test set(Qext2) was 0.967. The binding mode pattern of the compounds to the binding site of integrase enzyme was confirmed by docking studies. The results of present study indicated that this model can aid in designing more potent neuraminidase inhibitors.