Models through ToxPredict, Step 2

Selection of models available in OpenTox
through ToxPredict

To apply a number of models simultaneously, we will use some nice features of the ToxPredict application of OpenTox. Go to a new tab of your browser and navigate to At the top right of the page, find the Login link (there were some occurrences of problems with displaying ToxPredict properly on some versions of Internet explorer. If you can't find "Login" in the menu on the right, use this link:

Log in as user guest (password=guest).

Once logged in, in the menu on the right navigate to BROWSE->Models (if you cannot see the menu, use the following link: You can select/deselect models to be applied to a dataset here. For this exercise, start by de-selecting all models (by clicking on the check box "Select/Unselect" next to the "Endpoints" dropdown list at the top of the page.

Now, select the following models:

ToxTree: Structural Alerts for the in vivo micronucleus assay in rodents (
START biodegradation and persistence plug-in (
ECOSAR LC50 fish (
ToxTree: Verhaar scheme for predicting toxicity mode of action (
ToxTree: Cramer rules (
ToxTree: Benigni/Bossa rules for carcinogenicity and mutagenicity (
ToxTree: Skin irritation (
ToxTree: Skin sensitisation alerts (M. Cronin) (
ToxTree: Eye irritation (

You can select additional models if you like. However, make sure you keep unticked the following models (for matters of simplicity, or because they are taking too long to run, or because have made problems otherwise):

Any model whose URI does not begin with
MLR model for ExpLogKow
The “OpenTox model created with TUM’s kNNregression model learning web service”
The three “” models

Any of the other models feel free to use. Try to see what kind of information is provided with the models by clicking the "Show" links presented along with the model names. Once you're done, go through the list of your selected models, and note down their URIs (written in gray beneath the models' names. For convenience, the model URIs are also listed above. However, if you have selected additional models not in the above list, record their URIs.). We will use these model URIs in a next step.


Application of the selected models to the uploaded dataset

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


BACK TO Build a Weight of Evidence for Drug Candidate Molecules