There are several tools and information available to assess the uncertainty of a prediction inside and outside (by other software) the Toolbox. Whether you are aiming to perform a read-across or a trend analysis, several options are available within the Toolbox that help the user to analyse data quality. The most commons will be the statistical characteristics (R2, Q2, Cum. frequency...) for an analytical point of view and there are filters that can also be applied by test condition for example, in order to screen for adequate experimental data quality that best suits your prediction. The Toolbox does not provide a straight yes/no answer on whether your prediction is or is not adequate for your endpoint except for the applicability domain of the compound which will depend on the descriptor and analogues used in the prediction.The user should analyse the available information to reach a conclusion about its adequacy.
Does the QSAR Toolbox offer a way to analyze uncertainties for the obtained results based on QSAR or Read-across/Trend analysis? Print
Modified on: Wed, 31 Aug, 2016 at 11:49 AM
Did you find it helpful? Yes No
Send feedbackSorry we couldn't be helpful. Help us improve this article with your feedback.