Description Usage Arguments Value Examples
The Validator evaluates the performance of the model by comparing the predicted response Foreseen to the reported, true response from the TestObject's Annotation.
1 | Validator(Foreseen, TestObject, Evaluation)
|
Foreseen |
Predicted drug response of the TestObject obtained by applying the ForeseeModel. |
TestObject |
Object that contains all data that the model is to be tested on, especially the true, measured drug response. |
Evaluation |
Measure for evaluating the model performance, such as ROC-Curve, AUC or p-value of ROC-Curve, Rsquared, MSE, Correlation, F-Test, etc. The option 'fpvalue' calculates the p value of an F test on a linear model between predictions and the actual annotations, The option 'mse' calculates the mean square error of a linear model between predictions and the actual annotations, The option 'pearson' calculates the pearson correlation between predictions and the actual annotations, The option 'prauc' calculates the AUC of the precision-recall curve The option 'rocauc' calculates the AUC of the ROC curve The option 'rocpvalue' calculates the t.test p value of the ROC curve AUC versus 10000 permutated annotation values, The option 'rsquared' calculates the fraction of variance explained by a linear model between predictions and actual annotations, The option 'rsquared_adjusted' calculates the fraction of variance explained by a linear model between predictions and actual annotations, corrected the p-value of F-test, The option 'spearman'. calculates the spearman correlation between predictions and the actual annotations. The function 'listInputOptions("Validator")' returns a list of the possible options. Instead of choosing one of the implemented options, a user-defined function can be used as an input. |
Performance |
Evaluation Measure of the Predictability of the ForeseeModel trained on the TrainObject and tested on the TestObject. |
1 |
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.