Computational predictive toxicology draws knowledge from many independent sources, providing a rich support tool to assess a wide variety of toxicological properties. A key example would be for it to complement alternative testing methods. The integration of Bioclipse and OpenTox permits toxicity prediction based on the analysis of chemical structures, and visualization the substructure contributions to the toxicity prediction. OpenTox [1,2] is a semantic web framework, based on web services, which supports open data exchange and toxicology model building and validation. The representation of data and processing resources in W3C Resource Description Framework facilitates integrating the resources as Linked Data. By uploading datasets with chemical structures and arbitrary set of properties, they become automatically available online in several formats. The OpenTox services provide unified interfaces to chemical compounds and datasets, several descriptor calculation, machine learning and similarity searching algorithms, as well as to applicability domain and toxicity prediction models. OpenTox services could be used in various ways, for example as components in web applications or embedded in existing workflow systems. Despite the workflows flexibility, some users prefer simple user interfaces or software with predefined functionality, while some experts consider scripting languages more convenient for model development than graphical workflow builders. Bioclipse provides convenient solution for both groups of users, offering simultaneously GUI actions, visualisations and scripts. Bioclipse is a desktop bio- and cheminformatics platform, which combines a rich scriptable and graphical workbench environment. Bioclipse was recently extended to dynamically discover computational algorithms exposed via the OpenTox servers , using the OpenTox ontology service's SPARQL endpoint. This SPARQL endpoint functions as a registry of available computational services on the OpenTox network, similar to the role of BioCatalogue. Moreover, when a new descriptor algorithm or model is registered on the OpenTox ontology service, it will automatically be picked up by Bioclipse. Using this approach, Bioclipse has access to the most recent computational services running the latest predictive algorithms and models, while hiding technicalities by reusing a graphics-oriented workbench for the life sciences. The scripting functionality makes it easy to automate data workflows as do workflow applications but the combination with the rich Bioclipse user interface makes it possible at the same time to work with OpenTox interactively. Bioclipse-OpenTox interoperability for online descriptor calculation and data sharing , as well as accessing protected OpenTox datasets and calculation procedures via the adopted OpenSSO authenticaiton and authorisation solution had been demonstrated previous. This work extends the work by demonstrating how to add new models.