Go back to the tab where you have ToxPredict open (if you closed that tab, navigate to http://toxpredict.org and login as user guest/guest). Use the menu on the right to go to BROWSE->Models, and make sure you select all of them, EXCEPT for the "MLR Model for ExpLogKow" and the "OpenTox model created with TUM's J48 model learning web service for Micronucleus Data"! (they take too long for this workshop). Once you have selected the models, go to BROWSE->Datasets.
In the "Datasets:" entry box, you can not only enter a dataset URI, but you can also enter a search URL as described in the previous step. For example, let's use the "safe" compounds according to Cramer rules: copy the URL
to the "Dataset:" field in ToxPredict and click "Enter". Then, click "Run models". How many (and which ones) would you keep for the next stage in your drug design initiative?
You can also take a look at the initial short list of toxic compounds to be eliminated from further studies based on the Verhaar scheme. Use the URL
in ToxPredict and calculate all the models. Would you eliminate all compounds? Or would you keep some despite the prediction obtained with the Verhaar scheme?
Step 1: Creation of an OpenTox dataset from a local file
Step 2: Selection of models available in OpenTox through ToxPredict
Step 3: Application of the selected models to the uploaded dataset
Step 4: Obtaining simple statistics for the predictions obtained for the uploaded dataset
Step 5: Adding the predicted values to a tabular view of the dataset and downloading the table
Step 6: Additional steps I) Applying an individual model to a dataset
Step 7: Additional steps II) Searching a dataset according to prediction values
Step 8: Additional steps III) Obtaining additional predictions
Step 9: Additional steps IV) Downloading data from other dataset services in OpenTox
Step 10: Complement your findings with predicted associations with hepatobiliary adverse events