Platform for ligand-based toxicity prediction

The in silico prediction of compound toxicity is a very important task, i.e. for the reduction of animal testing (http://www.bb3r.de/). In the previous course, we have implement first Python scripts for toxicity predictions using machine learning and similarity searches and we have developed a prototype of a webserver.

In this year’s project, we will continue working on the scripts and include other machine learning algorithms, different molecular descriptors as well as more data sets. Besides exhaustive evaluation of the models, the webservice will be enhanced in features and usability.

The goal is to make the web-server freely available to allow other researchers to predict the toxicity of their compound of interest. A potential publication would be desirable.

Used programming languages: Python (scikit-learn, RDKit), Webserver (django, json, jquery, …)

For further information on the research interests of the group see https://physiologie-ccm.charite.de/en/research_at_the_institute/team_volkamer/