Monte Carlo method based QSAR modelling of natural lipase inhibitors using hybrid optimal descriptors

Obesity is one of the most provoking health burdens in the developed countries. One of the strategies to prevent obesity is the inhibition of pancreatic lipase enzyme. The aim of this study was to build QSAR models for natural lipase inhibitors by using the Monte Carlo method. The molecular structures were represented by the simplified molecular input line entry system (SMILES) notation and molecular graphs. Three sets – training, calibration and test set of three splits – were examined and validated. Statistical quality of all the described models was very good. The best QSAR model showed the following statistical parameters: r² = 0.864 and Q² = 0.836 for the test set and r² = 0.824 and Q² = 0.819 for the validation set. Structural attributes for increasing and decreasing the activity (expressed as pIC₅₀) were also defined. Using defined structural attributes, the design of new potential lipase inhibitors is also presented. Additionally, a molecular docking study was performed for the determination of binding modes of designed molecules.     

Experiences with the Application of QSAR in the Routine of the Notification Procedure

Abstract

On behalf of the Umweltbundesamt the Fraunhofer Gesellschaft has developed a software system (SAR-system) comprising more than 90 estimation models for endpoints relevant in environmental risk assessment. These estimation models are based on the approach of quantitative structure-activity relationships (QSAR). All models were checked for their validity and application range. In the last months the Umweltbundesamt started to test the applicability of some models concerning the endpoints fish acute toxicity, daphnia acute toxicity and ready (i.e., ultimate) biodegradability in the daily routine of the notification procedure. For testing these models the corresponding confidential data given in the dossiers of substances notified 1993 in Germany, were used. We were able to make calculations for 36% of the notified substances. For the remaining 64% of the chemicals it was impossible to accomplish SAR estimations due to several reasons, e.g., ionic structure of the compounds. Different results for the applicability of the mentioned endpoints are obtained. The predictions of the fish and Daphnia toxicity are in sufficient agreement with the experimental results, in case of the fish toxicity we receive 58% agreement, for the Daphnia toxicity 56% The corresponding values which were obtained in the US EPA/E.C. Joint Project on the evaluation of (quantitative) structure activity relationships were 82.3% and 70.9% About 300 different models were used for the calculations of these endpoints within the framework of the EPA/EC project. The SAR-system presented here contains 8 models for estimating the fish toxicity and 6 models for the Daphnia toxicity. For the prediction of the biodegradability the results obtained with the SAR-system are rather poor and have to be improved. Meanwhile the SAR-system is commercially available and can be ordered at the Fraunhofer Institute for Environmental Chemistry and Ecotoxicology, Schmallenberg (Germany).     

On further application of r as a metric for validation of QSAR models

Validation is a crucial aspect for quantitative structure–activity relationship (QSAR) model development. External validation is considered, in general, as the most conclusive proof of predictive capacity of a QSAR model. In the absence of truly external data set, external validation is usually performed on test set compounds, which are members of the original data set but not used in model development exercise. In the case of small data sets, QSAR researchers experience problem in model development due to the fact that the developed models may be less reliable on account of the small number of training set compounds and such models may also show poor external predictability because the models may not have captured all necessary features required for the particular structure–activity relationships. The present paper attempts to show that ‘true r_(LOO)’ statistic calculated based on the model derived from the undivided data set with application of variable selection strategy at each cycle of leave‐one‐out (LOO) validation may reflect external validation characteristics of the developed model thus obviating the requirement of splitting of the data set into training and test sets. This approach may be helpful in the case of small data sets as it uses all available data for model development and validation thus making the resulting model more reliable. Copyright © 2009 John Wiley & Sons, Ltd.     

U.S. EPA Regulatory Perspectives on the Use of QSAR for New and Existing Chemical Evaluations

Abstract

As testing is not required, ecotoxicity or fate data are available for ≈ 5% of the approximately 2,300 new chemicals/year (26,000 + total) submitted to the US-EPA. The EPA's Office of Pollution Prevention and Toxics (OPPT) regulatory program was forced to develop and rely upon QSARs to estimate the ecotoxicity and fate of most of the new chemicals evaluated for hazard and risk assessment. QSAR methods routinely result in ecotoxicity estimations of acute and chronic toxicity to fish, aquatic invertebrates, and algae, and in fate estimations of physical/chemical properties, degradation, and bioconcentration. The EPA's Toxic Substances Control Act (TSCA) Inventory of existing chemicals currently lists over 72,000 chemicals. Most existing chemicals also appear to have little or no ecotoxicity or fate data available and the OPPT new chemical QSAR methods now provide predictions and cross-checks of test data for the regulation of existing chemicals. Examples include the Toxics Release Inventory (TRI), the Design for the Environment (DfE), and the OECD/SIDS/HPV Programs. QSAR screening of the TSCA Inventory has prioritized thousands of existing chemicals for possible regulatory testing of: 1) persistent bioaccumulative chemicals, and 2) the high ecotoxicity of specific discrete organic chemicals.     

SMILES as an alternative to the graph in QSAR modelling of bee toxicity

Simplified Molecular Input Line Entry System (SMILES) nomenclature has been used as elucidating the molecular structure in construction of the quantitative structure-activity relationships (QSAR) for predicting bee toxicity. On the basis of the symbols used in the SMILES notation numerical parameters have been obtained, which are simple and fast to calculate. The method has been used to develop a QSAR model to predict toxicity of pesticides on bees. Results on a heterogeneous set of pesticides are good. Statistical characteristics of this model are: n=85, R2=0.68, s=0.82, F=180 (training set); n=20, R2=0.72, s=0.68, F=46 (test set).     

External validation of the biodegradability prediction model CATABOL using data sets of existing and new chemicals under the Japanese Chemical Substances Control Law

External validation of the biodegradability prediction model CATABOL was conducted using test data of 338 existing chemicals and 1123 new chemicals under the Japanese Chemical Substances Control Law. CATABOL predicts that 1089 chemicals will have a BOD?<?60% while 925 (85%) actually have an observed BOD<60%. The percentage of chemicals with an observed BOD value <60% tends to increase as the predicted BOD values decrease. In contrast, 340 chemicals were predicted to have a BOD?≥?60% and 234 (69%) actually had an observed BOD?≥?60%. The prediction of poor biodegradability was more accurate than the predictions of high biodegradability. The features of chemical structures affecting CATABOL predictability were also investigated.     

A new strategy of outlier detection for QSAR/QSPR

The crucial step of building a high performance QSAR/QSPR model is the detection of outliers in the model. Detecting outliers in a multivariate point cloud is not trivial, especially when several outliers coexist in the model. The classical identification methods do not always identify them, because they are based on the sample mean and covariance matrix influenced by the outliers. Moreover, existing methods only lay stress on some type of outliers but not all the outliers. To avoid these problems and detect all kinds of outliers simultaneously, we provide a new strategy based on Monte‐Carlo cross‐validation, which was termed as the MC method. The MC method inherently provides a feasible way to detect different kinds of outliers by establishment of many cross‐predictive models. With the help of the distribution of predictive residuals such obtained, it seems to be able to reduce the risk caused by the masking effect. In addition, a new display is proposed, in which the absolute values of mean value of predictive residuals are plotted versus standard deviations of predictive residuals. The plot divides the data into normal samples, y direction outliers and X direction outliers. Several examples are used to demonstrate the detection ability of MC method through the comparison of different diagnostic methods. © 2009 Wiley Periodicals, Inc. J Comput Chem, 2010