ChEMBL

Drug development necessitates running in vivo toxicological studies for the assessment of potential untoward side effects. Toxicities may often limit the use of medicines, and sometimes prevent molecules to become drugs. Early selection of chemicals with a low probability of being toxic will improve the whole process, taking less time and resources, including the use of animals. Hence, early in silico prediction of in vivo toxicological results would increase the efficiency of the drug development process and reduce the number of animals to be used in preclinical studies.


The eTOX project aims to develop innovative methodological strategies and novel software tools to better predict the toxicological profiles of new molecular entities in early stages of the drug development pipeline. This is planned to be achieved by sharing and jointly exploiting legacy reports of toxicological studies from participating pharmaceutical companies The project will coordinate the efforts of specialists from industry and academia in the wide scope of disciplines that are required for a more reliable modelling of the complex relationships existing between molecular and in vitro information and the in vivo toxicity outcomes of drugs. The proposed strategy includes a synergetic integration of innovative approaches in the following areas:

Data sharing of previously unaccessible high quality data from toxicity legacy reports of the pharma companies.

Database building and management, including procedures and tools for protecting sensitive data.

Ontology and text mining techniques, with the purpose of facilitating knowledge extraction from legacy preclinical reports and biomedical literature.

Chemistry and structure-based approaches for the molecular description of the studied compounds, as well as of their interactions with the anti-targets responsible for the secondary pharmacologies.

Prediction of DMPK (Drug Metabolism and Pharmacokinetics) features since they are often related to the toxicological events.

Systems biology approaches in order to cope with the complex biological mechanisms which govern in vivo toxicological events.

Computational genomics and sophisticated statistical analysis tools required to derive multivariate QSAR models

Development and validation (according to the OECD principles) of QSARs, integrative models, expert systems and meta-tools.


The eTOX project will be carried out by a Consortium comprising 25 organisations (13 pharmaceutical companies, 7 academic groups (including EMBL-EBI) and 5 SMEs) with complementary expertises. The total budget of the project is 13 million Euro and the project will last for five years.

The website for the project is http://www.e-tox.net/