Quantitative molecular similarity analysis (QMSA) methods for property estimation: A comparison of property-based,arbitrary, and tailored similarity spaces

Three classes of arbitrary quantitative molecular similarity analysis (QMSA) methods have been computed using atom pairs, topological indices, and physicochemical properties. Tailored QMSA models have been developed using a selected number of TIs chosen by ridge regression. The methods have been applied to the K -nearest neighbor based estimation of log P of two sets of chemicals. Results show that the property-based and tailored QMSA methods are superior to the arbitrary similarity methods in estimating log P of both sets of chemicals     

On some novel extended topochemical atom (ETA) parameters for effective encoding of chemical information and modelling of fundamental physicochemical properties

Extended topochemical atom (ETA) indices developed by our group have been extensively applied in our previous reports for toxicity and ecotoxicity modelling in the field of quantitative structure–activity relationships (QSARs). In the present study these indices have been further explored by defining additional novel parameters to model n-octanol–water partition coefficient (two data sets; n?=?168 and 139), water solubility (n?=?193), molar refractivity (n?=?166), and aromatic substituent constants π, MR, σ _m, and σ _p (n?=?99). All the models developed in the present study have undergone rigorous internal and external validation tests and the models have high statistical significance and prediction potential. In terms of Q ² and r ² values the models developed for the datasets of whole molecules are better than those previously reported, with topochemically arrived unique (TAU) indices on the same datasets of chemicals. An attempt has also been made to develop models using non-ETA topological and information indices. Interestingly, ETA and non-ETA models have been found to have similar predictive capacity.     

Quantitative molecular similarity analysis (QMSA) methods for property estimation: a comparison of property-based,arbitrary, and tailored similarity spaces

Three classes of arbitrary quantitative molecular similarity analysis (QMSA) methods have been computed using atom pairs, topological indices, and physicochemical properties. Tailored QMSA models have been developed using a selected number of TIs chosen by ridge regression. The methods have been applied to the K-nearest neighbor based estimation of log P of two sets of chemicals. Results show that the property-based and tailored QMSA methods are superior to the arbitrary similarity methods in estimating log P of both sets of chemicals     

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.     

Decision tree SAR models for developmental toxicity based on an FDA/TERIS database

Humans are exposed to thousands of environmental chemicals for which no developmental toxicity information is available. Structure-activity relationships (SARs) are models that could be used to efficiently predict the biological activity of potential developmental toxicants. However, at this time, no adequate SAR models of developmental toxicity are available for risk assessment. In the present study, a new developmental database was compiled by combining toxicity information from the Teratogen Information System (TERIS) and the Food and Drug Administration (FDA) guidelines. We implemented a decision tree modeling procedure, using Classification and Regression Tree software and a model ensemble approach termed bagging. We then assessed the empirical distributions of the prediction accuracy measures of the single and ensemble-based models, achieved by repeating our modeling experiment many times by repeated random partitioning of the working database. The decision tree developmental SAR models exhibited modest prediction accuracy. Bagging tended to enhance the accuracy of prediction. Also, the model ensemble approach reduced the variability of prediction measures compared to the single model approach. Further research with data derived from animal species- and endpoint-specific components of an extended and refined FDA/TERIS database has the potential to derive SAR models that would be useful in the developmental risk assessment of the thousands of untested chemicals.     

Prediction of pesticide acute toxicity using two-dimensional chemical descriptors and target species classification

Previous modelling of the median lethal dose (oral rat LD₅₀) has indicated that local class-based models yield better correlations than global models. We evaluated the hypothesis that dividing the dataset by pesticidal mechanisms would improve prediction accuracy. A linear discriminant analysis (LDA) based-approach was utilized to assign indicators such as the pesticide target species, mode of action, or target species - mode of action combination. LDA models were able to predict these indicators with about 87% accuracy. Toxicity is predicted utilizing the QSAR model fit to chemicals with that indicator. Toxicity was also predicted using a global hierarchical clustering (HC) approach which divides data set into clusters based on molecular similarity. At a comparable prediction coverage (~94%), the global HC method yielded slightly higher prediction accuracy (r² = 0.50) than the LDA method (r² ~ 0.47). A single model fit to the entire training set yielded the poorest results (r² = 0.38), indicating that there is an advantage to clustering the dataset to predict acute toxicity. Finally, this study shows that whilst dividing the training set into subsets (i.e. clusters) improves prediction accuracy, it may not matter which method (expert based or purely machine learning) is used to divide the dataset into subsets.     

Books Section

Abstract

The availability of validated and characterized SAR models of toxicological phenomena provides a method to apply SAR technology to a variety of environmental, public health and industrial situations. These include (i) the prioritization of environmental pollutants for control and or regulation, (ii) the design of multi-action optimized therapeutics from which the potential for unwanted side-effects have been engineered out, (iii) the development of SAR-based computer-driven screening procedure to identify candidate therapeutics based upon combinatorial chemistry or compilations of molecular structures, (iv) the generation of toxicological profiles to be used in the selection of benign chemicals in the early stages of product development.     

Qualitative and quantitative structure–activity relationship modelling for predicting blood-brain barrier permeability of structurally diverse chemicals

In this study, structure–activity relationship (SAR) models have been established for qualitative and quantitative prediction of the blood–brain barrier (BBB) permeability of chemicals. The structural diversity of the chemicals and nonlinear structure in the data were tested. The predictive and generalization ability of the developed SAR models were tested through internal and external validation procedures. In complete data, the QSAR models rendered ternary classification accuracy of >98.15%, while the quantitative SAR models yielded correlation (r²) of >0.926 between the measured and the predicted BBB permeability values with the mean squared error (MSE) <0.045. The proposed models were also applied to an external new in vitro data and yielded classification accuracy of >82.7% and r² > 0.905 (MSE < 0.019). The sensitivity analysis revealed that topological polar surface area (TPSA) has the highest effect in qualitative and quantitative models for predicting the BBB permeability of chemicals. Moreover, these models showed predictive performance superior to those reported earlier in the literature. This demonstrates the appropriateness of the developed SAR models to reliably predict the BBB permeability of new chemicals, which can be used for initial screening of the molecules in the drug development process.     

Isentropic compressibilities of chlorobenzene + n-hexane + (n-undecane or n-dodecane) at 298.15 K

In this study, the applicability of the Free Length and the Collision Factor theories to predict multicomponent changes of isentropic compressibilities is analysed and compared. To this end, appropriated expansions for ternary mixtures were derived from the original studies where these theories are developed, and then applied to a mixture containing unlike compounds in terms of functional molecular groups. Experimental data of excess molar volumes from open literature and new experimental isentropic compressibilities of the mixture chlorobenzene?+?n-hexane?+?(n-undecane or n-dodecane) were used to compute the parameters. A good accuracy was obtained when ternary prediction is attempted in this partially soluble mixture at different temperatures by the both methods. These results show the versatility of the models for estimation in complex multicomponent mixtures.     

Decision tree SAR models for developmental toxicity based on an FDA/TERIS database

Humans are exposed to thousands of environmental chemicals for which no developmental toxicity information is available. Structure-activity relationships (SARs) are models that could be used to efficiently predict the biological activity of potential developmental toxicants. However, at this time, no adequate SAR models of developmental toxicity are available for risk assessment. In the present study, a new developmental database was compiled by combining toxicity information from the Teratogen Information System (TERIS) and the Food and Drug Administration (FDA) guidelines. We implemented a decision tree modeling procedure, using Classification and Regression Tree software and a model ensemble approach termed bagging. We then assessed the empirical distributions of the prediction accuracy measures of the single and ensemble-based models, achieved by repeating our modeling experiment many times by repeated random partitioning of the working database. The decision tree developmental SAR models exhibited modest prediction accuracy. Bagging tended to enhance the accuracy of prediction. Also, the model ensemble approach reduced the variability of prediction measures compared to the single model approach. Further research with data derived from animal species- and endpoint-specific components of an extended and refined FDA/TERIS database has the potential to derive SAR models that would be useful in the developmental risk assessment of the thousands of untested chemicals.     

An in silico expert system for the identification of eye irritants

This report describes development of an in silico, expert rule-based method for the classification of chemicals into irritants or non-irritants to eye, as defined by the Draize test. This method was developed to screen data-poor cosmetic ingredient chemicals for eye irritancy potential, which is based upon exclusion rules of five physicochemical properties – molecular weight (MW), hydrophobicity (log P), number of hydrogen bond donors (HBD), number of hydrogen bond acceptors (HBA) and polarizability (Pol). These rules were developed using the ADMET Predictor software and a dataset of 917 eye irritant chemicals. The dataset was divided into 826 (90%) chemicals used for training set and 91 (10%) chemicals used for external validation set (every 10th chemical sorted by molecular weight). The sensitivity of these rules for the training and validation sets was 72.3% and 71.4%, respectively. These rules were also validated for their specificity using an external validation set of 2011 non-irritant chemicals to the eye. The specificity for this validation set was revealed as 77.3%. This method facilitates rapid screening and prioritization of data poor chemicals that are unlikely to be tested for eye irritancy in the Draize test.     

Fracture behavior of triglyceride‐based adhesives

The use of natural plant oils in the production of adhesives has been the focus of much research because natural oils are a renewable resource which have environmental and economic advantages over the petroleum‐derived chemicals used in traditional adhesives. The network formation and the stress–strain behavior of these plant oil–based adhesives is studied using a combination of simulation techniques. An off‐lattice Monte Carlo simulation has been developed to model the formation of these networks via the free‐radical copolymerization of the triglycerides present in natural oils. Networks of systems representing the triglycerides found in soybean oil, linseed oil, and olive oil are generated, as are networks made from other “theoretical” natural oils. The structure of the networks is characterized by percolation analysis. The stress–strain behavior of these networks is studied using large‐scale molecular dynamics simulations. Tensile strains are applied to the networks and it is observed that with increasing n the failure stress increases but the failure strain decreases. Also, for systems with low values of n, large voids form while the system is strained and then the system fails cohesively. However, for large n, no significant voiding is observed and the system fails close to the interface. The simulation results are shown to be consistent with the vector percolation theoretical prediction for how the failure stress relates to n. © 2004 Wiley Periodicals, Inc. J Polym Sci Part B: Polym Phys 42: 3333–3343, 2004     

Comparison of Estrogen Receptor α and β Subtypes Based on Comparative Molecular Field Analysis (CoMFA)

Abstract

A substantial body of evidence indicates that both humans and wildlife suffer adverse health effects from exposure to environmental chemicals that are capable of interacting with the endocrine system. The recent cloning of the estrogen receptor β subtype (ER-β) suggests that the selective effects of estrogenic compounds may arise in part by the control of different subsets of estrogen-responsive promoters by the two ER subtypes, ER-α and ER-β. In order to identify the structural prerequisites for ligand-ER binding and to discriminate ER-α and ER-3 in terms of their ligand-binding specificities, Comparative Molecular Field Analysis (CoMFA) was employed to construct a three-dimensional Quantitative Structure-Activity Relationship (3D-QSAR) model on a data set of 31 structurally-diverse compounds for which competitive binding affinities have been measured against both ER-α and ER-β. Structural alignment of the molecules in CoMFA was achieved by maximizing overlap of their steric and electrostatic fields using the Steric and Electrostatic ALignment (SEAL) algorithm. The final CoMFA models, generated by correlating the calculated 3D steric and electrostatic fields with the experimentally observed binding affinities using partial least-squares (PLS) regression, exhibited excellent self-consistency (r ² > 0.99) as well as high internal predictive ability (q ² > 0.65) based on cross-validation. CoMFA-predicted values of RBA for a test set of compounds outside of the training set were consistent with experimental observations. These CoMFA models can serve as guides for the rational design of ER ligands that possess preferential binding affinities for either ER-α or ER-β. These models can also prove useful in risk assessment programs to identify real or suspected EDCs.     

脂质体电动色谱用于预测皮肤渗透性的定量保留活性关系的建立

脂质体电动色谱 （Liposome electrokinetic chromatography,LEKC）是一种简单快速的评价药物与生物膜相互作用的方法。本文建立了脂质体电动色谱作为高通量筛选皮肤渗透性的体外分析方法。将脂质体电动色谱中保留因子的对数值（log k）作为自变量建立了定量保留活性关系式。采用SPSS分析软件对于16种结构不同的化合物进行分析,结果表明log k与皮肤渗透性常数线性相关性良好( R²=0.886)。采用交互验证评价了该模型的预测能力。在定量保留活性关系中的一个变量和传统定量构效关系中的三个变量可解释的能力( R² =0.704)相似。文中建立的定量保留活性关系模型对于新化合物早期的筛选可提供一种有效快捷的方法。