Dear All,
 Our services at http://opentox.ntua.gr:3000 now provide RDF
representations for algorithms and trained models. Available algorithms
are listed at http://opentox.ntua.gr:3000/algorithm . You can get a list
of all svm models at
http://opentox.ntua.gr:3000/model?searchAlgorithm=svm and all mlr models
at http://opentox.ntua.gr:3000/model?searchAlgorithm=mlr . Please report
any bugs you might find at http://github.com/sopasakis/yaqp/issues 

I built some datasets with random entries (for testing purposes) which
are available at http://opentox.ntua.gr/files/ .

The source code is available at the public git repositories:
http://github.com/sopasakis/yaqp and
http://opentox.ntua.gr/git/yaqp.git 

However...

* When building a new model, the service has to generate a new feature
that will be used as a pointer to the predictions made by this model. Is
this operation implemented?

* When a client posts a dataset on a model to make a prediction, then
the service generates a new dataset which (according to the API) should
be posted to a dataset service. Is this operation available?

* How can I calculate a feature value for a certain compound URI? Is
there an example (e.g. curl command)?

Best Regards,
Pantelis