Optimal neighbor selection in molecular similarity: comparison of arbitrary versus tailored prediction spaces

Three classes of arbitrary quantitative molecular similarity analysis (QMSA) methods have been computed using atom pairs (APs), topological indices (TIs), and principal components (PCs) derived from topological indices. Tailored QMSA models have been developed from TIs selected through ridge regression. K-nearest neighbor (kNN) based estimation has been applied to all of the methods to estimate normal vapor pressure (p(vap)) and water solubility (sol) for a set of 194 chemicals. Results show that the tailored QMSA methods are superior to arbitrary similarity methods in estimating both of these properties for the given set of chemicals.     

QSAR modeling based on the bias/variance compromise: a harmonious

Modeling quantitative structure-activity relationships (QSAR) is considered with an emphasis on prediction. An abundance of methods are available to develop such models. Using a harmonious approach that balances the bias and variance of predictions, the best calibration models are identified relative to the bias and variance criteria used. Criteria utilized to determine the adequacy of models are the root mean square error of calibration (RMSEC) and validation (RMSEV), respective R2 values, and the norm of the regression vector. QSAR data from the literature are used to demonstrate concepts. For these data sets and criteria used, it is suggested that models obtained by ridge regression (RR) are more harmonious and parsimonious than models obtained by partial least squares (PLS) and principal component regression (PCR) when the data is mean-centered. The most harmonious RR models have the best bias/variance tradeoff, reflected by the smallest RMSEC, RMSEV, and regression vector norms and the largest calibration and validation R2 values. The most parsimonious RR models have the smallest effective rank.     

QSAR modeling based on the bias/variance compromise: a harmonious

Modeling quantitative structure–activity relationships (QSAR) is considered with an emphasis on prediction. An abundance of methods are available to develop such models. Using a harmonious approach that balances the bias and variance of predictions, the best calibration models are identified relative to the bias and variance criteria used. Criteria utilized to determine the adequacy of models are the root mean square error of calibration (RMSEC) and validation (RMSEV), respective R ² values, and the norm of the regression vector. QSAR data from the literature are used to demonstrate concepts. For these data sets and criteria used, it is suggested that models obtained by ridge regression (RR) are more harmonious and parsimonious than models obtained by partial least squares (PLS) and principal component regression (PCR) when the data is mean-centered. The most harmonious RR models have the best bias/variance tradeoff reflected by the smallest RMSEC, RMSEV, and regression vector norms and the largest calibration and validation R ² values. The most parsimonious RR models have the smallest effective rank.     

基于机器学习方法的丙型肝炎病毒聚合酶NS5B非核苷抑制剂的定量构效关系研究

对89 个苯并异噻唑和苯并噻嗪类丙型肝炎病毒(HCV) NS5B聚合酶非核苷抑制剂进行了定量构效关系(QSAR)研究. 采用遗传算法组合偏最小二乘(GA-PLS)和线性逐步回归分析(LSRA)两种特征选择方法选择最优描述符子集, 然后建立多元线性回归和偏最小二乘线性回归模型. 并首次尝试使用遗传算法耦合支持向量机方法(GA-SVM)对两种特征选择方法所选的描述符子集分别建立非线性支持向量机回归模型. 三种机器学习方法所建模型均得到比较满意的预测效果. 采用LSRA所选的6 个描述符建立的三个QSAR模型对于测试集的相关系数为0.958-0.962, GA-SVM法给出最好的预测精度(0.962). 采用GA-PLS所选的7个描述符建立的三个QSAR模型对于测试集的相关系数为0.918-0.960, 偏最小二乘回归模型的结果最好(0.960). 本工作提供了一种有效的方法来预测丙型肝炎病毒抑制剂的生物活性, 该方法也可以扩展到其他类似的定量构效关系研究领域.     

Design of topological indices: computer-oriented approach

A novel method is suggested for constructing topological indices (TIs) of molecular graphs which models human logic. This method is described in terms of a block scheme, consisting of the mutually connected elementary blocks. In each block the simple transformations of a molecular graph are fulfilled. A variant of the transformation is selected from the list of possible variants. Every TI is obtained as a result of the sequential execution of a number of operations, corresponding to some ‘walk’ on the block scheme. This walk can be selected both randomly and by the investigator. The suggested method can serve as a basis for the development of the respective computer program which may be used for the automatic construction of any number of TIs of differing nature. By this process one can also obtain the TIs that are unlikely to be constructed manually, due to their complexity. The set of obtained TIs may be used for building the structure–property models. In the case of an unsatisfactory result the obtained set of TIs may be changed using the described generator of TIs. A number of examples of application of the suggested approach for the building QSAR/QSPR models is given.     

Considerations and recent advances in QSAR models for cytochrome P450-mediated drug metabolism prediction

Quantitative structure–activity relationships (QSAR) methods are urgently needed for predicting ADME/T (absorption, distribution, metabolism, excretion and toxicity) properties to select lead compounds for optimization at the early stage of drug discovery, and to screen drug candidates for clinical trials. Use of suitable QSAR models ultimately results in lesser time-cost and lower attrition rate during drug discovery and development. In the case of ADME/T parameters, drug metabolism is a key determinant of metabolic stability, drug–drug interactions, and drug toxicity. QSAR models for predicting drug metabolism have undergone significant advances recently. However, most of the models used lack sufficient interpretability and offer poor predictability for novel drugs. In this review, we describe some considerations to be taken into account by QSAR for modeling drug metabolism, such as the accuracy/consistency of the entire data set, representation and diversity of the training and test sets, and variable selection. We also describe some novel statistical techniques (ensemble methods, multivariate adaptive regression splines and graph machines), which are not yet used frequently to develop QSAR models for drug metabolism. Subsequently, rational recommendations for developing predictable and interpretable QSAR models are made. Finally, the recent advances in QSAR models for cytochrome P450-mediated drug metabolism prediction, including in vivo hepatic clearance, in vitro metabolic stability, inhibitors and substrates of cytochrome P450 families, are briefly summarized.     

Comparative study of topological indices of macro/supramolecular RNA complex networks

RNA function annotation is often based on alignment to a previously studied template. In contrast to the study of proteins, there are not many alignment-free methods to predict RNA functions if alignment fails. The use of topological indices (TIs) of RNA complex networks (CNs) to find quantitative structure-activity relationships (QSAR) may be an alternative to incorporate secondary structure or sequence-to-sequence similarity. Here, we introduce new QSAR-like techniques using RNA macromolecular CNs (mmCNs), where nodes are nucleotides, or RNA supramolecular CNs (smCNs), where nodes are RNA sequences. We studied a data set of 198 sequences including 18S-rRNAs (important phylogenetic molecular biomarkers). We constructed three types of RNA mmCNs: sequence-linear (SL), Cartesian-lattice (CL), and sequence-folding CNs (SF-CNs) and two smCNs: sequence-sequence disagreement CN (SSD) and sequence-sequence similarity (SSS-smCN). We reported the first comparative QSAR study with all these CIs and CNs, which includes: (i) spectral moments ( ( i )micro d ( w)) of SL-mmCNs (accuracy = 75.3%), (ii) electrostatic CIs (xi d ) of CL-mmCNs (>90%), (iii) thermodynamic parameters (Delta G, Delta H, Delta S, and T m) of SF-mmCNs (64.7%), (iv) disagreement-distribution moments ( M k ) of the SSD-smCN (79.3%), and (v) node centralities of the SSD-smCN (78.0%). Furthermore, we reported the experimental isolation of a new RNA sequence from Psidum guajava leaf tissue and its QSAR and BLAST prediction to illustrate the practical use of these methods. We also investigated the use of these CNs to explore rRNA diversity on bacteria, plants, and parasites from the Dactylogyrus genus. The HPL-mmCNs model was the best of all found. All the CNs and TIs, except SF-mmCNs, were introduced here by the first time for the QSAR study of RNA, which allowed a comparative study for RNA classification.     

Combinatorial QSAR modeling of chemical toxicants tested against Tetrahymena pyriformis

Selecting most rigorous quantitative structure-activity relationship (QSAR) approaches is of great importance in the development of robust and predictive models of chemical toxicity. To address this issue in a systematic way, we have formed an international virtual collaboratory consisting of six independent groups with shared interests in computational chemical toxicology. We have compiled an aqueous toxicity data set containing 983 unique compounds tested in the same laboratory over a decade against Tetrahymena pyriformis. A modeling set including 644 compounds was selected randomly from the original set and distributed to all groups that used their own QSAR tools for model development. The remaining 339 compounds in the original set (external set I) as well as 110 additional compounds (external set II) published recently by the same laboratory (after this computational study was already in progress) were used as two independent validation sets to assess the external predictive power of individual models. In total, our virtual collaboratory has developed 15 different types of QSAR models of aquatic toxicity for the training set. The internal prediction accuracy for the modeling set ranged from 0.76 to 0.93 as measured by the leave-one-out cross-validation correlation coefficient ( Q abs2). The prediction accuracy for the external validation sets I and II ranged from 0.71 to 0.85 (linear regression coefficient R absI2) and from 0.38 to 0.83 (linear regression coefficient R absII2), respectively. The use of an applicability domain threshold implemented in most models generally improved the external prediction accuracy but at the same time led to a decrease in chemical space coverage. Finally, several consensus models were developed by averaging the predicted aquatic toxicity for every compound using all 15 models, with or without taking into account their respective applicability domains. We find that consensus models afford higher prediction accuracy for the external validation data sets with the highest space coverage as compared to individual constituent models. Our studies prove the power of a collaborative and consensual approach to QSAR model development. The best validated models of aquatic toxicity developed by our collaboratory (both individual and consensus) can be used as reliable computational predictors of aquatic toxicity and are available from any of the participating laboratories.     

基于岭回归和SVM的高维特征选择与肽QSAR建模

岭回归估计权重绝对值在一定程度上体现了对应特征作用大小, 据此发展了基于岭回归(RR)和支持向量机(SVM)的高维特征选择算法. 对苦味二肽(BTT)和细胞毒性T淋巴细胞(CTL)表位9 肽两个肽体系, 以氨基酸的531 个物理化学性质参数直接表征肽结构, 各获得1062、4779 个初始特征; 对训练集, 初始特征以岭回归排序后序贯引入, 当SVM留一法交叉测试(LOOCV)的均方误差(MSE)显著上扬时终止, 最后以多轮末尾淘汰进一步精筛, 分别获得7、18个物理化学意义明确的保留特征. 基于保留特征与支持向量回归(SVR), 对训练集建立定量构效关系(QSAR)模型, 预测独立测试集, 其拟合精度、留一法交叉测试精度、独立预测精度均优于现有文献报道结果. 新方法运行速度快, 选取的特征物理化学意义明确, 解释性强, 在肽、蛋白质定量构效关系建模等高维数据回归预测领域有较广泛应用前景.