Christoph,

AFAIK there are no descriptor calculation services at NTUA, the ones
available are at TUM and ours at

http://apps.ideaconsult.net:8080/ambit2/algorithm
or
http://ambit.uni-plovdiv.bg:8080/ambit2/algorithm

You might find useful the superservice at
http://apps.ideaconsult.net:8080/ambit2/algorithm/superservice
or
http://ambit.uni-plovdiv.bg:8080/ambit2/algorithm/superservice

If a model, requiring descriptors are submitted to the superservice,
it finds the descriptors , launches the calculations, if necessary and
only then launches model calculation.

Best regards,
Nina

On Mon, Aug 16, 2010 at 5:02 PM, Christoph Helma <helma at in-silico.ch> wrote:
> Pantelis,
>
> Excerpts from chung's message of Thu Jul 29 13:13:20 +0200 2010:
>> 3. Train an MLR model using a dataset resource with respect to some
>> target attribute:
>> curl -X POST -d
>> dataset_uri=http://apps.ideaconsult.net:8080/ambit2/dataset/54 -d
>> prediction_feature=http://apps.ideaconsult.net:8080/ambit2/feature/22200
>> 'http://opentox.ntua.gr:3000/algorithm/mlr?username=<YOUR_USERNAME>&password=<YOUR_PASS>' -H Accept:text/uri-list
>> The above curl command will return a (running) task which upon
>> completion points to the created model.
>
> Do you also have feature calculation services? If not, which one are you
> using to create input datasets?
>
> Can you send me username/password for your services?
>
> Thanks,
> Christoph
> _______________________________________________
> Development mailing list
> Development at opentox.org
> http://www.opentox.org/mailman/listinfo/development
>