Search

Nanotechnology is a branch of science and technology that comes with lots of industrial applications and potential benefits to the society. But the risk associated with the nanomaterials towards human health and environment is of major concern. Quantitative structure-activity relationship (QSAR) studies for modeling activities or properties of nanoparticles (nano-QSAR modeling) can be employed to study the factors governing the toxicity of nanomaterials. We have developed a variety of software tools under the NanoBRIDGES project ( http://nanobridges.eu/ ) which will assist in performing QSAR and nano-QSAR modeling. These user friendly tools are standalone, and openly accessible from NanoBRIDGES official website ( http://nanobridges.eu/software/ ), DTC laboratory website ( http://dtclab.webs.com/software-tools ) and Jadavpur University official website ( http://teqip.jdvu.ac.in/QSAR_Tools/ ). In this paper, we have described the theoretical background of each software tool including its algorithm and its applicability in the nano-QSAR modeling. [ABSTRACT FROM AUTHOR]

One of the important applications of quantitative structure-activity relationship (QSAR) models is to fill data gaps by predicting a given response property or activity from known molecular features or physicochemical properties of new compounds which might not have been tested experimentally. The general QSAR users are now already aware that the new compounds which will be predicted from a given QSAR model should be similar in structural and/or physicochemical property space to the training set compounds so as to be included in the chemical applicability domain of the model. It is also well-established, at least among some groups of QSAR scientists, that performance of a model should be evaluated based on the quality of predictions from the test set and not from the training set to obviate any overfitting problem. It is also important to analyze prediction errors of test set compounds in order to search for presence of any systematic error or bias in model predictions. A simple residual plot can provide sufficient information about the type of error present in model predictions. As the test set compounds are structurally and physico-chemically similar to the training set compounds, the model prediction errors for the test set also should obey, at least approximately, the basic assumptions of the least-squares regression under the best linear unbiased estimator (BLUE) framework, provided that a sufficient number of test set compounds is available allowing an acceptable degree of freedom. The present article explains the importance of analysis of prediction errors to check for the presence of systematic error and/or violation of basic assumptions of the least-squares regression models under the BLUE framework with suitable examples using real QSAR model-derived quantitative predictions for test sets and simulated prediction data. The intention of the present authors is neither to make a comparison of performances of different validation metrics for quantitative predictions (eventually favoring or disfavoring one or the other validation metric) nor to compare quality of different models but to indicate the situations where such comparison should not be made due to inappropriate functional form of a model making it unsuitable for quantitative predictions of a set of compounds and also due to the use of unrealistic and biased prediction pattern that never happens in real QSAR problems, thus making the situation unsuitable for making any generalized conclusion. This article also alerts the QSAR users to the importance of “statistical applicability domain” of QSAR models before their application for quantitative prediction of a response of test set compounds in order to compare performance of different validation approaches. [ABSTRACT FROM AUTHOR]

Validation is the most crucial concept for development and application of quantitative structure–activity relationship (QSAR) models. The validation process confirms the reliability of the developed QSAR models along with the acceptability of each step during model development such as assessing the quality of input data, dataset diversity, predictability on an external set, domain of applicability and mechanistic interpretability. External validation or validation using an independent test set is usually considered as the gold standard in evaluating the quality of predictions from a QSAR model. The external predictivity of QSAR models is commonly described by employing various validation metrics, which can be broadly categorized into two major classes, viz., R 2 based metrics namely R 2 test , Q 2 (ext_F1) , and Q 2 (ext_F2) , and purely error based measures like predicted residual sum of squares (PRESS), root mean square error (RMSE), and mean absolute error (MAE). The problem associated with the error based measures is the absence of any well-defined threshold for determining the quality of predictions making the R 2 based metrics more suitable for use due to easy comprehension. However, in this paper, we show the problems associated with the R 2 based validation metrics commonly used in QSAR studies, since their values are highly dependent on the range of the response values of the test set compounds and their distribution pattern around the training/test set mean. We also propose a guideline for determining the quality of predictions based on MAE and its standard deviation computed from the test set predictions after omitting 5% high residual data points in order to obviate the influence of any rarely occurring high prediction errors that may significantly obscure the quality of predictions for the whole test set. In this manner, we try to evaluate the prediction performance of a model on most (95%) of the data points present in the external set. An online tool (XternalValidationPlus) for computing the suggested MAE based criteria (along with other conventional metrics) for external validation has been made available at http://dtclab.webs.com/software-tools and http://teqip.jdvu.ac.in/QSAR_Tools/ . The MAE based criteria suggested here along with other commonly used validation metrics may be applied to evaluate predictive performance of QSAR models with a greater degree of confidence. [ABSTRACT FROM AUTHOR]