Identification of Pharmacophoric Fragments of DYRK1A Inhibitors Using Machine Learning Classification Models

Dual-specific tyrosine phosphorylation regulated kinase 1 (DYRK1A) has been regarded as a potential therapeutic target of neurodegenerative diseases, and considerable progress has been made in the discovery of DYRK1A inhibitors. Identification of pharmacophoric fragments provides valuable information for structure- and fragment-based design of potent and selective DYRK1A inhibitors. In this study, seven machine learning methods along with five molecular fingerprints were employed to develop qualitative classification models of DYRK1A inhibitors, which were evaluated by cross-validation, test set, and external validation set with four performance indicators of predictive classification accuracy (CA), the area under receiver operating characteristic (AUC), Matthews correlation coefficient (MCC), and balanced accuracy (BA). The PubChem fingerprint-support vector machine model (CA = 0.909, AUC = 0.933, MCC = 0.717, BA = 0.855) and PubChem fingerprint along with the artificial neural model (CA = 0.862, AUC = 0.911, MCC = 0.705, BA = 0.870) were considered as the optimal modes for training set and test set, respectively. A hybrid data balancing method SMOTETL, a combination of synthetic minority over-sampling technique (SMOTE) and Tomek link (TL) algorithms, was applied to explore the impact of balanced learning on the performance of models. Based on the frequency analysis and information gain, pharmacophoric fragments related to DYRK1A inhibition were also identified. All the results will provide theoretical supports and clues for the screening and design of novel DYRK1A inhibitors.     

Three-dimensional quantitative structure-activity relationship (3D QSAR) and pharmacophore elucidation of tetrahydropyran derivatives as serotonin and norepinephrine transporter inhibitors

Three-dimensional quantitative structure-activity relationship (3D QSAR) using comparative molecular field analysis (CoMFA) was performed on a series of substituted tetrahydropyran (THP) derivatives possessing serotonin (SERT) and norepinephrine (NET) transporter inhibitory activities. The study aimed to rationalize the potency of these inhibitors for SERT and NET as well as the observed selectivity differences for NET over SERT. The dataset consisted of 29 molecules, of which 23 molecules were used as the training set for deriving CoMFA models for SERT and NET uptake inhibitory activities. Superimpositions were performed using atom-based fitting and 3-point pharmacophore-based alignment. Two charge calculation methods, Gasteiger-Hückel and semiempirical PM3, were tried. Both alignment methods were analyzed in terms of their predictive abilities and produced comparable results with high internal and external predictivities. The models obtained using the 3-point pharmacophore-based alignment outperformed the models with atom-based fitting in terms of relevant statistics and interpretability of the generated contour maps. Steric fields dominated electrostatic fields in terms of contribution. The selectivity analysis (NET over SERT), though yielded models with good internal predictivity, showed very poor external test set predictions. The analysis was repeated with 24 molecules after systematically excluding so-called outliers (5 out of 29) from the model derivation process. The resulting CoMFA model using the atom-based fitting exhibited good statistics and was able to explain most of the selectivity (NET over SERT)-discriminating factors. The presence of −OH substituent on the THP ring was found to be one of the most important factors governing the NET selectivity over SERT. Thus, a 4-point NET-selective pharmacophore, after introducing this newly found H-bond donor/acceptor feature in addition to the initial 3-point pharmacophore, was proposed.     

三维全息原子场作用矢量用于吡咯类抗艾滋病药物QSAR研究

采用三维全息原子场作用矢量(3D-HoVAIF)对32个吡咯类抗艾滋病药物进行结构参数化表征,并与其活性建立定量构效关系。分别采用多元线性回归(MLR)和偏最小二乘(PLS)进行建模,建模的复相关系数(R2cum)、交互校验复相关系数(Q2cum)和模型的标准偏差(SD)分别为R2cum=0.914、Q2cum=0.812、SD=0.236(MLR);R2cum=0.836、Q2cum=0.719、SD=0.314(PLS),结果均优于文献值(R2cum=0.667,Q2cum=0.581,SD=0.420)。所建模型具有良好的稳定性和预测能力,表明3D-HoVAIF能够较好地表征该类分子的结构,值得进一步推广应用。     

Semi-correlations as a tool to build up categorical (active/inactive) model of GABAA receptor modulator activity

The interpretation of mode of action for GABA_A receptor modulator activity is an important task of medicinal chemistry. The computational elucidation of the modulator activity is one of the ways to solve the above task. So-called semi-correlation is a tool for prediction of GABA_A receptor modulator activity. The semi-correlation is based on the Monte Carlo method. This approach is to build up categorical classification models into two classes: (i) active and (ii) inactive. The CORAL software (http://www.insilico.eu/coral) can be used to build up the semi-correlations. The statistical quality of models (for external validation sets) based on semi-correlation has the range of Matthews correlation coefficient (MCC) is 0.72–1.00 for 30 random splits of all available data (n?=?210) into the training and validation sets. In contrast to existing approaches, the predictive CORAL models give prediction using solely data on molecular architecture (represented by simplified molecular input-line entry system?=?SMILES) and available experimental data on endpoints. Suggested models for prediction of GABA_A receptor modulator activity are built up according to the OECD principles. Thus, the approach based on the semi-correlation can be a useful tool for studying of the GABA_A receptor modulators activity.

     

三维全息原子场作用矢量(3D-HoVAIF)用于神经氨酸酶抑制剂的结构表征与设计及定量构效关系(QSAR)研究

对100个神经氨酸酶抑制剂抗禽流感药物结构并与其活性建立定量构效关系模型。采用本实验室提出的三维全息原子场作用矢量(3D-HoVAIF)对100个神经氨酸酶抑制剂进行结构表征,然后采用逐步回归对变量进行筛选后,运用偏最小二乘建立3D-HoVAIF描述子与神经氨酸酶抑制剂活性之间的QSAR模型。结果表明:复相关系数(R),交互校验的复相关系数(Q2)和模型的标准偏差(SD)分别为R2=0.805、Q2=0.657和SD=0.936,模型具有良好的稳定性和预测能力,并对文献中23个药物和设计的32个化合物进行了预测。表明三维全息原子场作用矢量能较好表征该类分子结构信息值得进一步推广应用。     

DATA类逆转录酶抑制剂的三维定量构效关系

采用对接方法得到HIV-1抑制剂DATA(二芳基三嗪类)分子的活性构象, 进一步用比较分子场分析(CoMFA)和比较分子相似性分析(CoMSIA)法对DATA类逆转录酶抑制剂(RTIs)的三维定量构效关系(3D-QSAR)进行了研究, 建立3D-QSAR模型, 以指导进一步结构修饰. 用此模型预测了5个DATA类似物, 预测偏差较小, 表明了所建立的模型具有较强的预测能力.     

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.     

Pose prediction accuracy in docking studies and enrichment of actives in the active site of GSK-3beta

We present molecular docking studies on the inhibitors of GSK-3beta kinase in the enzyme binding sites of the X-ray complexes (1H8F, 1PYX, 1O9U, 1Q4L, 1Q5K, and 1UV5) using the Schr?dinger docking tool Glide. Cognate and cross-docking studies using standard precision (SP) and extraprecision (XP) algorithms have been carried out. Cognate docking studies demonstrate that docked poses similar to X-ray poses (root-mean-square deviations of less than 2 A) are found within the top four ranks of the GlideScore and E-model scores. However, cross-docking studies typically produce poses that are significantly deviated from X-ray poses in all but a couple of cases, implying potential for induced fit effects in ligand binding. In this light, we have also carried out induced fit docking studies in the active sites of 1O9U, 1Q4L, and 1Q5K. Specifically, conformational changes have been effected in the active sites of these three protein structures to dock noncognate ligands. Thus, for example, the active site of 1O9U has been induced to fit the ligands of 1Q4L, 1Q5K, and 1UV5. These studies produce ligand docked poses which have significantly lower root-mean-square deviations relative to their X-ray crystallographic poses, when compared to the corresponding values from the cross-docking studies. Furthermore, we have used an ensemble of the induced fit models and X-ray structures to enhance the retrieval of active GSK-3beta inhibitors seeded in a decoy database, normally used in Glide validation studies. Thus, our studies provide valuable insights into computational strategies useful for the identification of potential GSK-3beta inhibitors.     

An <Emphasis Type="BoldItalic">in silico</Emphasis> approach for screening flavonoids as P-glycoprotein inhibitors based on a Bayesian-regularized neural network

Summary P-glycoprotein (P-gp), an ATP-binding cassette (ABC) transporter, functions as a biological barrier by extruding cytotoxic agents out of cells, resulting in an obstacle in chemotherapeutic treatment of cancer. In order to aid in the development of potential P-gp inhibitors, we constructed a quantitative structure–activity relationship (QSAR) model of flavonoids as P-gp inhibitors based on Bayesian-regularized neural network (BRNN). A dataset of 57 flavonoids collected from a literature binding to the C-terminal nucleotide-binding domain of mouse P-gp was compiled. The predictive ability of the model was assessed using a test set that was independent of the training set, which showed a standard error of prediction of 0.146 ± 0.006 (data scaled from 0 to 1). Meanwhile, two other mathematical tools, back-propagation neural network (BPNN) and partial least squares (PLS) were also attempted to build QSAR models. The BRNN provided slightly better results for the test set compared to BPNN, but the difference was not significant according to F-statistic at p = 0.05. The PLS failed to build a reliable model in the present study. Our study indicates that the BRNN-based in silico model has good potential in facilitating the prediction of P-gp flavonoid inhibitors and might be applied in further drug design.     

基于药效团的BRD4靶向小分子抑制剂虚拟筛选

BRD4靶点和多种肿瘤密切相关,是具有良好成药性的热门靶点.本文选取活性较好且结构差异较大的BRD4小分子抑制剂作为训练集分子,基于配体小分子共同特征(HipHop)方法使用Discovery Studio 3.0分子模拟软件构建了药效团.药效团通过测试集验证、ROC曲线验证(SE(sensitivity)=0.937...     

QM/MM based 3D QSAR models for potent B-Raf inhibitors

Three dimensional (3D) quantitative structure-activity relationship studies of 37 B-Raf inhibitors, pyrazole-based derivatives, were performed. Based on the co-crystallized compound (PDB ID: 3D4Q), several alignment methods were utilized to derive reliable comparative molecular field analysis (CoMFA) and comparative molecular similarity indices analysis (CoMSIA) models. Receptor-guided alignment with quantum mechanics/molecular mechanics (QM/MM) minimization led to the best CoMFA model (q ² = 0.624, r ² = 0.959). With the same alignment, a statistically reliable CoMSIA model with steric, H-bond acceptor, and hydrophobic fields was also derived (q ² = 0.590, r ² = 0.922). Both models were validated with an external test set, which gave satisfactory predictive r ² values of 0.926 and 0.878, respectively. Contour maps from CoMFA and CoMSIA models revealed important structural features responsible for increasing biological activity within the active site and explained the correlation between biological activity and receptor-ligand interactions. New fragments were identified as building blocks which can replace R1-3 groups through combinatorial screening methods. By combining these fragments a compound with a high bioactivity level prediction was found. These results can offer useful information for the design of new B-Raf inhibitors.