‘CDD Models’ Case Studies

I just posted some examples of how the Bayesian models and Fingerprints described previously here, here and here, can be used in CDD to build models (here, here and here), generate predictions and be used (or not) to export the models.

For the test cases I used a few examples of public datasets. But the same approach could be taken with data in a private Vault. Bottom line it pretty simple to take a dataset, build the model, access it and then use to make predictions.

The models can then be exported to a mobile app like MMDS for running there on a phone or ipad too.

All of the data sets represent some biological data but that does not need to be the case as long as there is a binary endpoint. Even that may change as we develop new approaches for Bayesian modeling.



Leave a Reply

Your email address will not be published.

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <s> <strike> <strong>