两类促肾上腺皮质释放激素(CRH)拮抗剂的分子场分析

采用比较分子相似性指数分析方法(CoMSIA)及比较分子场分析方法(CoMSIA)研究了两组CRH拮抗剂结构与活性的关系。在两种方法中,都考虑了静电场、立体场以及氢键场对构效关系的影响,结果表明采用CoMSIA得到构效关系模型要明显优于采用CoMFA得到的构效关系模型,在CoMSIA计算中,当引入疏水场时,三维构效关系模型能得到明显的改善,通过这个三维构效关系模型,可以较为精确地预测化合物的活性。通过分析分子场等值面图在空间的分布,可以观察到叠合分子周围的立体、静电以及疏水特征对化合物活性的影响。     

咪唑啉酮类除草剂的三维构效关系研究

从三维角度出发,采取不同的构象搜索方法得到了咪唑酮类化合物分子的活性构象。利用比较分子场分析方法进一步证实了模板分子构象的正确性。并从静电场、立体场及活性关系等方面进行了三维定量构效关系研究,得到了具有较强预测能力的QSAR模型。     

化学势变化率对催眠药类化合物QSAR影响

为了改善定量构效关系研究中的相关性系数,更加精确地预测有关化合物的活性,我们引入化学势变化率作为量子化学反应性指数参与了QSAR计算。本文通过苯并二氮杂齛类化合物催眠性能的定量构效关系研究,发现引入了化学势变化率作为量子化学反应性指数后,QSAR相关性有所提高,大多数化合物的计算值与实验数据的误差减少。研究结果表明,在进行QSAR计算时,引入化学势变化率有助于提高苯并二氮杂齛类化合物催眠活性的预测能力。本研究基于这样一个假设:生物体内药物分子的化学势变化也将按比例地反映在生理反应或生物活性的变化中。为此,我们通过苯并二氮杂齛类化合物的定量构效关系研究进行了初步验证。     

褪黑激素受体拮抗剂的三维定量构效关系研究

采用两种分子场分析方法即比较分子场分析法（CoMFA）和比较分子相似因子分析法（CoMSIA）进行了37个褪黑激素受体拮抗剂的构效关系研究.计算结果表明，两种方法得到的构效关系模型都具有较好的预测能力.在计算中，还考察了不同格点距离和电荷计算方法对构效关系模型的影响.通过分析分子场等值面图在空间的分布，可以观察到叠合分子周围分子场特征对化合物活性的影响，为设计新的褪黑激素拮抗剂提供了一些理论依据.     

辨识药物定量构效关系的模糊神经网络方法研究

提出一种基于遗传算法的新型模糊神经网络方法,用于计算Benzodiazepines(BZs)类药物的定量构效关系.这类模糊神经网络综合了神经网络、遗传算法与模糊逻辑的各自优势,具有优良的定量构效关系辨识能力,其学习速度较快,不易陷入局部最小区域;网络知识以模糊语言变量的形式加以表达,不仅易于理解,而且能有效地利用已有的专家经验.一旦通过学习获得规律后,不仅能很好地预测化合物的活性,还能对后续的药物分子设计提供有益的理论指导.     

嘧啶硫代水杨酸衍生物的多元回归分析及神经网络法研究

通过量子化学方法计算了 1 4个新型嘧啶硫代水杨酸衍生物的量化参数 ,运用分子力学进行完全构象优化进而计算了分子几何形状等参数。对这些化合物抑制乙酰乳酸合成酶 (ALS)活性进行了QSAR分析 ,结果表明 ,空间因素及静电效应是影响构效关系的主要因素 ,神经网络法得到较优预测结果。     

取代喹啉类化合物抗菌活性的定量构效关系及分子设计

采用密度泛函理论(DFT)和逐步回归分析法对15种新合成的取代喹啉类化合物进行了定量构效关系(QSAR)研究. 在B3LYP/6-31G(d,p)水平上计算了取代喹啉的量子化学参数, 通过逐步多元回归分析筛选出影响抗菌活性的主要因素, 建立了定量构效关系方程, 并用留一法交叉分析了模型的稳定性及预测能力. 结果表明, C5的亲核电子密度fNC5及C9-N1的键级BC9-N1是影响喹啉类化合物抗金黄色葡萄球菌活性的主要因素, 所得模型对该类化合物抗菌活性有较好的预测效果. 同时基于QSAR研究结果设计了4个活性较高的新喹啉衍生物.     

神经网络方法在血管紧张素转换酶抑制剂定量构效关系建模中的应用

对20个ACEI化合物用量子化学方法进行结构优化并计算出10个参数,用9种不同隐含层节点数的BP神经网络研究了ACEI的定量构效关系,建立了节点为10/6/1的三层BP神经网络模型。结果表明:以量化理论计算所得参数可以构建合理的ACEI定量构效关系模型,神经网络模型M6的r2=0.995,S=0.050,6个验证集化合物的残差平方和为0.002,预测能力明显强于多元线形回归模型,亦优于同类文献报道,可作为ACEI研发领域中预测先导化合物活性的理论工具。     

一类新型N型钙通道阻滞剂的比较定量构效关系研究

使用结构和量子化学参数对一系列N取代N-甲基二肽衍生物的N型钙通道阻滞活性进行了定量构效关系研究, 并使用SOMFA方法建立了三维定量构效关系模型. 结果表明分子的范德华体积和最低未占据轨道能量是影响化合物生物活性的主要因素. N原子上取代基的溶剂可及面积也对化合物的钙通道阻滞活性有重要影响. 三维定量构效关系模型进一步支持了以上结果. 这些研究结果可为设计更高活性的N型钙通道阻滞剂提供有价值的参考信息.     

斑蝥素衍生物的量子化学研究

在112种合成的斑蝥素衍生物中,N-羟基斑蝥胺(2)、N-甲基斑蝥胺(3)、N-乙基斑蝥胺(4)、N-烯丙基斑蝥胺(5)具有抗肝癌活性,且毒副作用很小。其中N-羟基斑蝥胺和N-甲基斑蝥胺已用于临床试验,疗效较好。关于斑蝥素衍生物化学结构与抗肝癌活性之间的关系,已有报道,但尚未从电子结构方面系统考察构效因素。本文用CNDO/2法对五个活性和三个非活性斑蝥素衍生物分子,进行了量子化学计算,以探讨药物的构效关系。     

QSAR modelling using combined simple competitive learning networks and RBF neural networks

The aim of this study was to propose a QSAR modelling approach based on the combination of simple competitive learning (SCL) networks with radial basis function (RBF) neural networks for predicting the biological activity of chemical compounds. The proposed QSAR method consisted of two phases. In the first phase, an SCL network was applied to determine the centres of an RBF neural network. In the second phase, the RBF neural network was used to predict the biological activity of various phenols and Rho kinase (ROCK) inhibitors. The predictive ability of the proposed QSAR models was evaluated and compared with other QSAR models using external validation. The results of this study showed that the proposed QSAR modelling approach leads to better performances than other models in predicting the biological activity of chemical compounds. This indicated the efficiency of simple competitive learning networks in determining the centres of RBF neural networks.     

Parsimonious Optimization of Multitask Neural Network Hyperparameters

Neural networks are rapidly gaining popularity in chemical modeling and Quantitative Structure–Activity Relationship (QSAR) thanks to their ability to handle multitask problems. However, outcomes of neural networks depend on the tuning of several hyperparameters, whose small variations can often strongly affect their performance. Hence, optimization is a fundamental step in training neural networks although, in many cases, it can be very expensive from a computational point of view. In this study, we compared four of the most widely used approaches for tuning hyperparameters, namely, grid search, random search, tree-structured Parzen estimator, and genetic algorithms on three multitask QSAR datasets. We mainly focused on parsimonious optimization and thus not only on the performance of neural networks, but also the computational time that was taken into account. Furthermore, since the optimization approaches do not directly provide information about the influence of hyperparameters, we applied experimental design strategies to determine their effects on the neural network performance. We found that genetic algorithms, tree-structured Parzen estimator, and random search require on average 0.08% of the hours required by grid search; in addition, tree-structured Parzen estimator and genetic algorithms provide better results than random search.     

基于遗传算法的神经网络为苯乙酰胺类农药构效关系建模的研究

探讨用遗传算法训练神经网络,为苯乙酰胺类化合物的QSAR建模,效果良好,神经网络可以反映复杂的构效关系,而引入遗传算法又有助于多层前传网在训练过程中跳出局部最小点,使收敛速度大大提高,并在预报精度上有显著改善.     

Integration of genetic virtual screening patterns and latent multivariate modeling techniques for QSAR optimization based on combinations and/or interactions between peptides and proteins

Both the concept and the model of snug quantitative structure-activity relationship (QSAR) were pro-posed and developed for molecular design through constructing QSAR based on some known mode of receptor/ligand interactions. Many disadvantages of traditional models can be avoided by using the proposed method because the traditional models only determined upon molecular structural features in sample sets themselves. A genetic virtual screening of peptide/protein combinations (GVSPPC) is proposed for the first time by utilizing this idea to examine peptide/protein affinity activities. A genetic algorithm (GA) was developed for screening combinative targets with an interaction mode for virtual receptors. GVSPPC succeeds in disposing difficulties in rational QSAR,in order to search for the ligand/receptor interactions on conditions of unknown structures. Some bioactive oligo-/poly-peptide systems covering 58 angiotensin converting enzyme (ACE) inhibitors and 18 double site mutation residues in camel antibody protein cAb-Lys3 were investigated by GVSPPC with satisfactory results (R 2 cu>0.91,Q 2 cv > 0.86,ERMS=0.19-0.95),respectively,which demonstrates that GVSPPC is more inter-pretable in the ligand-receptor interaction than the traditional QSAR method.     

In silico rationalization of the structural and physicochemical requirements for photobiological activity in angelicine derivatives and their heteroanalogues

In PUVA (Psoralen plus UVA) chemotherapy 8-methoxypsoralen is the most widely used compound, although its efficacy is endowed with undesired side effects. In order to have an evident anti-proliferative activity with a reduced phototoxicity, many linear and angular derivatives have been synthesised. In this paper we describe a QSAR study in which, by means of the neural networks methodology, a useful model for predicting biological activity, expressed as ID₅₀ (the UVA dose that reduces to 50% the DNA synthesis in Ehrlich cells), has been derived. A decision tree that is able to discriminate between active and inactive compounds has been built based on recursive partitioning. The study shows the key structural features responsible for the activity and could be a helpful tool in the rational design of new, less toxic, photochemotherapeuthic agents.