Data-integration for Endpoints, Chemoinformatics and Omics


The first objective of this project is to develop a transparent framework that improves the prediction of the repeated dose toxicity of new chemicals by integrating chemoinformatic data with biological information from ‘omics’ and HTS technologies.

To create this framework, it is imperative to develop different integrative approaches (based both on unsupervised and supervised procedures) and thoroughly evaluate them, using a dataset of critical mass with limited number of gaps (i.e. substantial number of chemicals and sufficient data on each domain). Therefore, the second objective of this project, is to generate a high-quality database that contains for a large number of chemicals, its chemical properties, in vitro omics, in vivo omics, other toxicological assays considered relevant (e.g. ToxCast) and (in vivo) toxicological test results for the toxicity investigated within this project. Both existing data (in public and private databases) as well as newly generated data will be incorporated in a data infrastructure that is easily transferable and platform independent. The selected set of chemicals should be sufficiently large to allow development of the integrative approaches while allowing setting aside a sufficiently large validation set for evaluation.

The third objective of this project, is to develop and evaluate expert rules, useful for industry as well as regulators, that describe the 1) the exact conditions and boundaries under which the integrated approaches are valid and allow an improvement on chemical categorization, 2) to define requirements on the minimal information that is required within registration dossiers to justify conclusions made on the hazardous profile of a certain compound and 3) to make recommendations on what information should be stored in public databases to support the use of chemoinformatics, “omics” and HTS in future regulatory decision making.