3D QSAR methods: Phase and Catalyst compared

The programs Phase and Catalyst HypoGen are compared for their performance in determining three-dimensional quantitative structure-activity relationships. Eight sets of compounds with measured activity were collected from the public literature and partitioned into suitable training and test sets by an automated procedure. A range of models is built with each program, and suggested parameter variations are investigated. The models are assessed by their ability to predict the activity of compounds in the test set, and it is demonstrated that the performance of Phase is better than or equal to that of Catalyst HypoGen, with the data sets and parameters used here. Additionally, compounds in two of the data sets are overlaid on crystallographic structures of similar ligands in complex with the target receptor, in order to guide pharmacophore generation by the two programs, but the resulting models do not perform better.     

含氟农药的比较分子场分析研究

用比较分子场分析(CoMFA)方法对112种含氟农药分子的生物活性及毒性同时进行了定量构效关系研究。用78个化合物作为训练集,以距离比较方法(DISCO)确认的药效团为叠合规则构建CoMFA模型,发现影响活性的立体场与静电场的贡献分别为60.4%和39.6%,影响毒性的立体场与静电场的贡献分别为59.2%和40.8%。药效模型与毒效模型在交叉验证时的相关系数平方(R^2)分别为0.652和0.611,非交叉验证的R^2分别为0.982和0.977,方差比F(8,69)值分别为463.6及362.9,活性和毒性的标准偏差-极差比s/△γ值分别为3.6%和2.9%,表明模型具有较好的自预测能力。对测试组34个化合物进行了活性和毒性的预测,活性与毒性预测的标准偏差-极差比s/△γ值分别为10.4%和6.4%。最后,还建立了一个由97个化合物构建的扩大的模型,各种统计量得到了进一步提高。并预计了一个活性较高且毒性很低的新化合物。     

Experimental determination and prediction of bilitranslocase transport activity

The transport activity of a membrane protein, bilitranslocase (T.C. # 2.A.65.1.1), which acts as a transporter of bilirubin from blood to liver cells, was experimentally determined for a large set of various endogenous compounds, drugs, purine and pyrimidine derivatives. On these grounds, the structure-activity models were developed following the OECD principles of QSAR models and their predictive ability for new chemicals was evaluated. The applicability domain of the models was estimated by Euclidean distances criteria according to the applied modeling method. The selection of the most influential structural variables was an important stage in the adopted modeling methodology. The interpretation of selected variables was performed in order to get an insight into the mechanism of transport through the cell membrane via bilitranslocase. Validation of the optimized models was performed by a previously determined validation set. The classification model was build to separate active from inactive compounds. The resulting accuracy, sensitivity, and specificity were 0.73, 0.89, and 0.64, respectively. Only active compounds were used to develop a predictive model for bilitranslocase inhibition constants. The model showed good predictive ability; Root Mean Squared error of the validation set, RMS(V)=0.29 log units.     

A <Emphasis Type="Italic">k</Emphasis>-nearest neighbor classification of hERG K<Superscript>+</Superscript> channel blockers

A series of 172 molecular structures that block the hERG K⁺ channel were used to develop a classification model where, initially, eight types of PaDEL fingerprints were used for k-nearest neighbor model development. A consensus model constructed using Extended-CDK, PubChem and Substructure count fingerprint-based models was found to be a robust predictor of hERG activity. This consensus model demonstrated sensitivity and specificity values of 0.78 and 0.61 for the internal dataset compounds and 0.63 and 0.54 for the external (PubChem) dataset compounds, respectively. This model has identified the highest number of true positives (i.e. 140) from the PubChem dataset so far, as compared to other published models, and can potentially serve as a basis for the prediction of hERG active compounds. Validating this model against FDA-withdrawn substances indicated that it may even be useful for differentiating between mechanisms underlying QT prolongation.     

CoMFA 3D-QSAR analysis of HIV-1 RT nonnucleoside inhibitors, TIBO derivatives based on docking conformation and alignment

HIV-1 RT is one of the key enzymes in the duplication of HIV-1. Inhibitors of HIV-1 RT are classified as nonnucleoside RT inhibitors (NNRTIs) and nucleoside analogues. NNRTIs bind in a region not associated with the active site of the enzyme. Within the NNRTI category, there is a set of inhibitors commonly referred to as TIBO inhibitors. Fifty TIBO inhibitors were used in the work to build 3-D QSAR models. The two known crystal structures of complexes are used to investigate and validate the docking protocol. The results show that the docking simulations reproduce the crystal complexes very well with RMSDs of approximately 1 A and approximately 0.6 A for 1REV and 1COU, respectively. The alignment of molecules and "active" conformation selection are the key to a successful 3D-QSAR model by CoMFA. The flexible docking (Autodock3) was used on determination of "active" conformation and molecular alignment, and CoMFA and CoMSIA were used to develop 3D-QSAR models of 50 TIBOs in the work. The 3D-QSAR models demonstrate a good ability to predict the activity of studied compounds (r2 = 0.972, 0.944, q2 = 0.704, 0.776). It is shown that the steric and electrostatic properties predicted by CoMFA contours can be related to the binding structure of the complex. The results demonstrate that the combination of ligand-based and receptor-based modeling is a powerful approach to build 3D-QSAR models.     

机器学习方法用于二氢叶酸还原酶抑制剂的活性预测

分别采用支持向量学习机、人工神经网络、调节性逻辑回归和K-最临近等机器学习方法对761个二氢叶酸还原酶抑制剂建立了其活性分类预测模型. 采用组成描述符和拓扑描述符表征抑制剂的分子结构及物理化学性质, 使用Kennard-Stone方法进行训练集的设计, 并用Metropolis Monte Carlo模拟退火方法作变量选择. 结果表明, 支持向量学习机优于其它机器学习方法, 所得到的最优模型具有较好的预测结果, 其预测正确率为91.62%. 说明通过合适的训练集设计及变量选择, 支持向量学习机方法可以很好地用于二氢叶酸还原酶抑制剂的活性分类预测.     

Dissimilar chromatographic systems to indicate and identify antioxidants from Mallotus species

The genus of Mallotus contains several species commonly used as traditional medicines in oriental countries. A data set containing 39 Mallotus samples, differing in species, cultivation conditions, harvest season and/or part of the plant was used to develop fingerprints on two dissimilar chromatographic systems. An exploratory analysis with principal component analysis (PCA) was performed on both data sets individually. The results were also combined to obtain additional information on the unknown samples included in the data set. Furthermore, the antioxidant activity of the samples was measured and modelled as a function of the fingerprints using the orthogonal projections to latent structures (O-PLS) technique. The regression coefficients of the models were studied to indicate the peaks potentially responsible for the antioxidant activity. The indicated peaks were analyzed and identified by HPLC coupled to mass spectrometry (HPLC-MS). Because of the complexity of biological samples, it was aspired to separate co-eluting components based on the significant difference in chromatographic selectivity on the dissimilar systems and consequently obtain additional, complementary information on the contribution of the individual components to the antioxidant activity. The results illustrate the potential use of dissimilar chromatographic systems. Several initially co-eluting compounds could be separated on the dissimilar system. The corresponding regression coefficients provided complementary information on the potential antioxidant activity of the separated compounds.     

基于支撑向量机方法的有机化合物的生成Gibbs自由能的预测

基于支撑向量机方法的有机化合物的生成Gibbs自由能的预测;支撑向量机;多元线形回归;吉布斯自由能