QSAR modeling with the electrotopological state indices: Corticosteroids

A structure-activity analysis of a series of steroids binding to corticosteroid-binding globulin was made using the electrotopological state index for each atom in the molecule. Two indices were found to correlate well with the binding affinity. The indices encode structural characteristics in the A and the D rings of the steroids in the study. One of the indices was formulated as the difference between two indices in the A ring. The two were not intercorrelated, suggesting that the composite index signals the influence of structure changes in or near the A ring that can be monitored by the composite index. This is a new observation using this structure-activity method. It is suggested that this model makes some contributions towards detection of the pharmacophore.     

有机化合物的疏水参数与拓扑指数相关性的研究

本文计算了50个芳烃类化合物的A~m指数与分子联接性指数, 并将其用于芳烃类化合物的结构与疏水参数lgP的相关性研究, 结果表明, 经改进的A~m指数能更好地反映这类化合物的结构特性。     

An index of electrotopological state for atoms in molecules

A new method for molecular structure quantitation is described, in which both electronic and topological attributes are united. The method uses the hydrogen-suppressed skeleton to represent the structure and leads to a graph invariant index for the individual atoms and hydride groups of the molecular skeleton. An intrinsic atom value is calculated for each atom asI = ( + 1)/, in which and are the counts of valence and sigma electrons of atoms in the molecular skeleton, that is, exclusive of bonds to hydrogen atoms. The electrotopological state valueS _i for an atomi is defined asS _i =I _i + I _i, where the influence of atom j on atom i, I _i, is given as (I _i-j _j)/r ²;r is the graph separation between atoms i and j, counted as number of atoms, includingi andj. The information in the electrotopological state values is revealed by examples of various types of organic structures, including chain branching and heteroatom variation. The relation of the E-state value to NMR chemical shift is demonstrated for a series of carbonyl compounds.     

Development of an automatic estimation system for both the partition coefficient and aqueous solubility

Summary A computer program has been developed for estimating both the partition coefficient between 1-octanol and water phases and the aqueous solubility from the structural formula. This system is an extended version of a previously described program entitled CHEMICALC for the automatic estimation of the partition coefficient. The aqueous solubility is estimated via two pathways. The first is based on the linear relationship between logarithms of the aqueous solubilities of 497 compounds and their estimated 1-octanol/water partition coefficients. In the second, combined handling of two available group contribution methods of Irmann [Chem. Ing. Tech., 37 (1965) 789] and Wakita et al. [Chem. Pharm. Bull., 34 (1986) 4663] is adopted according to compound type. Some revisions and extensions of the methods for estimating the aqueous solubility have been made in both pathways, and the accuracy of the estimated aqueous solubilities for 497 compounds is discussed.     

QSAR modeling of antiradical and antioxidant activities of flavonoids using electrotopological state (E-State) atom parameters

In the present paper QSAR modeling using electrotopological state atom (E-state) parameters has been attempted to determine the antiradical and the antioxidant activities of flavonoids in two model systems reported by Burda et al. (2001). The antiradical property of a methanolic solution of 1, 1-diphenyl-2-picrylhydrazyl (DPPH) and the antioxidant activity of flavonoids in a β-carotenelinoleic acid were the two model systems studied. Different statistical tools used in this communication are stepwise regression analysis, multiple linear regressions with factor analysis as the preprocessing step for variable selection (FA-MLR) and partial least squares analysis (PLS). In both the activities the best equation is obtained from stepwise regression analysis, considering, both equation statistics and predictive ability (antiradical activity: R ² = 0.927, Q² = 0.871 and antioxidant activity: R ² = 0.901, Q² = 0.841).      

Neural network studies : Part 3. Prediction of partition coefficients

In a previous paper (N. Bodor, A. Harget and M.-J. Huang, J. Am. Chem. Soc., 113 (1991) 9480) we demonstrated the utility of a neural network approach in the estimation of the aqueous solubility of organic compounds. This approach has now been extended to the prediction of partition coefficients. A training set of AM1 calculated properties and experimental values for 302 compounds was used and, after training, the neural network was tested for its ability to predict the partition coefficients of 21 compounds not included in the training set. We also tested six more compounds with molecular properties out of the training set property range. A comparison was made with the results obtained from a previous study which had used a regression analysis approach (N. Bodor and M.-J. Huang, J. Pharm. Sci., 81 (1992) 272). The neural network results compared favorably with those given by the regression analysis approach, both for the training set and for the new compounds.     

Neural network approach for modeling the performance of reverse osmosis membrane desalting

A neural network-based modeling approach with back-propagation and support vector regression algorithms was investigated as a mean of developing data-driven models for forecasting reverse osmosis (RO) plant performance and for potential use for operational diagnostics. The concept of plant “short-term memory” time-interval was introduced to capture the time-variability of plant performance since both a state of the plant model and standard time-series analyses for both flux decline and salt passage did not result in realistic predictive horizons for practical purposes. Past information of normalized permeate flux and salt passage were introduced as unique input variables along with process operating parameters to capture short-term plant performance variability. Sequential models, where the time-variation within each forecasting time-interval was also taken as input information, and marching forecasting models, where target values were predicted at fixed future times from past plant information, were developed. Models were trained, with normalized permeate flux and salt passage, for various model architectures, memory time-intervals and forecasting times using both back-propagation and support vector regression approaches. State of the plant models (without forecasting) were able to describe the relatively small permeate flux variations but were unable to capture salt passage trends (for any present time condition) since unsteady state phenomena could not be properly described without plant memory information. Forecasting of plant performance, with both sequential and marching models, yielded good predictive accuracy for short-term memory time-intervals in the range of 8–24 h for permeate flux and salt passage for forecasting times up to 24 h. Current work is ongoing to extend the approach for longer time scales and to incorporate data-driven forecasting models of RO plant into control strategies and process diagnostics.     

Boosting battery state of health estimation based on self-supervised learning

State of health(SoH) estimation plays a key role in smart battery health prognostic and management.However,poor generalization,lack of labeled data,and unused measurements during aging are still major challenges to accurate SoH estimation.Toward this end,this paper proposes a self-supervised learning framework to boost the performance of battery SoH estimation.Different from traditional data-driven methods which rely on a considerable training dataset obtained from numerous battery cells,the pro...     

Automatic log P estimation based on combined additive modeling methods

Summary A program for the automatic estimation of the logarithm of the partition coefficient between 1-octanol and water phases (log P) has been developed as a component of a system entitled CHEMICALC (Combined Handling of Estimation Methods Intended for Completely Automated Log P Calculation). Log P values are calculated based on additive group contributions to log P. Three sets of groups are defined, and their contributions have been derived from the experimental log P values of 1465 molecules. The system divides a structural formula of a compound of interest into the groups whose increments are provided and then calculates its log P value. All processing after structure input is fully automated. This system has been tested for predicting the log P values of 1686 compounds. The accuracy is sufficient for many practical purposes.     

基于DFT和分子连接性指数方法研究醇类化合物的水溶解度和分配系数

将DFT方法计算得到的量化参数和分子连接性指数联合应用到60个醇类化合物的溶解度和辛醇/水分配系数的QSPR研究中,分别通过逐步回归得到具有显著统计意义的4个参数和5个参数的QSPR方程.以此4个参数和5个参数分别作为输入参数,采用BPNN,RBFNN方法建立了QSPR预测模型,使用Latin-partition交叉验证方法评价模型的预测能力.BPNN,RBFNN模型对溶解度预测的相关系数分别为0.993和0.994,而对辛醇/水分配系数预测的相关系数分别0.990和0.997,结果令人满意.     

苯甲酰硫脲类化合物生物活性的QSAR模型和结构修饰的理论研究

基于分子拓扑邻接矩阵,计算了18种苯甲酰硫脲衍生物的原子类型电性拓扑状态指数(En)。通过多元线性逐步回归方法,建立了令人满意的En与苯甲酰硫脲衍生物对金黄色葡萄球菌的抑制活性(D)的定量结构-活性相关模型(QSAR)。该模型的相关系数(R2)、标准偏差(S)分别为0.861及1.273,该模型的计算值与相应实验值基本吻合。经Rcv2、VIF、FIT、AIC等指标检验,所建模型具有良好的预测能力与稳健性。利用该模型探讨了苯甲酰硫脲衍生物对金黄色葡萄球菌的抑制机理。根据进入模型的2个电性拓扑状态指数E1、E7可知,影响苯甲酰硫脲衍生物对金黄色葡萄球菌的抑制活性的主要因素是分子的二维结构特征-CH3和在芳环中=CH-等结构碎片。由结构修饰提出5种化合物,其中3种的抑菌活性均超出18mm,有待以后生物实验予以证实。     

Non-linear modeling of bioconcentration using partition coefficients for narcotic chemicals

Bioconcentration factors (BCFs) have traditionally been used to describe the tendency of chemicals to concentrate in aquatic organisms. A reexamination of the log-log QSAR between the BCF and K OW for non-congener narcotic chemicals is presented on the basis of recommended data for fish. The model is extended to give a simple correlation between BCF and the toxicity of highly, moderately and weakly hydrophilic chemicals. For the first time, in this study an equation for calculating BCF was applied in a QSAR model for predicting the acute toxicity of chemicals to aquatic organisms.