Helmholtz Zentrum München - German Research Center for Environmental Health (GmbH)

Helmholtz Zentrum München

The GSF, National Research Centre for Environment and Health, is a research institution of the Federal Government and the State of Bavaria within the Helmholtz Association of German Research Centres with approximately1700 associates in 24 institutes and departments (total budget 2006: 156,8 MEuro). The GSF contributes to the foundation of future medicine and health care as well as ecosystems.

The Research Team develops new methods to predict physico-chemical (lipophilicity, aqueous solubility, pKa, melting point, etc.) and biological endpoints (toxicity, skin sensitization and permeation rate, blood-brain barrier penetration, etc.) as well as methodology to estimate the accuracy of models for the human health and environmental studies. The group has significant expertise in Web and standalone software development and its extensive user support, exemplified by the Virtual Computational Chemistry Laboratory site (Tetko, et al., 2005). This site was started as an INTAS project (2001-2004) and it is visited by several thousands users per month now. The group is well known in the field of computational chemistry by its innovative methodological approaches to solve QSPR/QSAR problems. Early 90-ties the group was the first to introduce the neural network ensemble methods in chemistry (Tetko, et al., 1993, 1995). Later the group developed an Associative Neural Network method (Tetko, 2002). It was implemented in the ALOGPS program (Tetko and Tanchuk, 2002) which predicts lipophilicity and aqueous solubility of chemical compounds. The ALOGPS was tested in several pharmaceutical companies (LaRoche, BASF, AstraZeneca, Pfizer, etc.) and demonstrated a superior accuracy compared to the leading commercial methods. A new methodology to estimate the applicability domain of models was recently proposed and successfully validated (Tetko, et al., 2006). In October 2006 Dr Tetko was awarded a prestigious national Go-Bio grant (12 out of 176 projects were funded) for his works on Associative Neural networks. Dr. Tetko was a project coordinator of the VCCLAB INTAS grant and team leader in three other INTAS grants. He was also a recipient of International Human Frontier Science Program Organisation (HFSPO) fellowship, a team leader in NATO linkage grant, principal investigator and project director in Swiss National Science Foundation (SNSF) and Deutsche Forschungsgemeinschaft (DFG) grants. He is co-author of more than 60 papers in international peer-review journals and contributed about the same number of articles in proceedings of conference and national journals.

The main contribution of the group will be the development of the http://qspr-thesaurus.eu site and the implementation of methods developed by other groups in WP3/WP4 as on-line tools. These tools will be freely available for all users through the Web interface as well as a standalone version performing remote calculation at the site. The group will participate in the development of models and the estimation of their applicability domain in WP3, the creation of a database of experimental data in WP2 and the economic valuation of health and environmental damage due to chemicals in WP4. Within the project period the group will establish a SME (to be created as a spin-off of the GSF company within the framework of a national Go-Bio award to the group in Germany), which will provide sustainable support of the site and free WWW tools as well as a further development and distribution of the elaborated version of the standalone tools on a commercial basis after the termination of the project.

Selected list of publications:

1. Tetko, I. V., Prediction of physicochemical properties. In Computational Toxicology: Risk Assessment for Pharmaceutical and Environmental Chemicals, Ekins, S., Ed. John Wiley & Sons, Inc: New Jersey, 2007; Vol. 1, pp 241-275.

2. Tetko, I. V.; Bruneau, P.; Mewes, H. W.; Rohrer, D. C.; Poda, G. I., Can we estimate the accuracy of ADME-Tox predictions? Drug Discov. Today 2006, 11, (15-16), 700-707.

3. Balakin, K. V.; Savchuk, N. P.; Tetko, I. V., In silico approaches to prediction of aqueous and DMSO solubility of drug-like compounds: trends, problems and solutions. Curr. Med. Chem. 2006, 13, (2), 223-241.

4. Tetko, I. V., Computing chemistry on the web. Drug Discov. Today 2005, 10, (22), 1497-1500.

5. Tetko, I. V. et al Virtual computational chemistry laboratory - design and description. J. Comput.-Aided Mol. Des. 2005, 19, (6), 453-463.