|
|
|
|
|
|
| Gisbert Schneider, Johann Wolfgang Goethe-University |
|
| Gisbert Schneider studied biochemistry at the Free University (FU) of Berlin, Germany. From 1991 to 1994 he prepared his doctoral thesis on machine learning systems for peptide de novo design as a fellow of the Fonds der Chemischen Industrie. From 1994 to 1997 he performed post-doctoral research at the FU Berlin (design of artificial antigens), the University of Stockholm, Sweden (analysis of mitochondrial targeting sequences), the Massachusetts Institute of Technology, Cambridge, MA, USA (empirical potentials for protein folding simulation), and the Max-Planck-Institute of Biophysics in Frankfurt, Germany (sequence-based prediction of membrane proteins), which was supported by Boehringer-Ingelheim Fonds fellowships. During this time, a common theme of his work was the development and application of artificial neural network models and evolutionary algorithms for amino acid sequence analysis and peptide design. In 1997 he joined the pharmaceuticals division of F.Hoffmann-La Roche AG in Basel, Switzerland, where he became Head of Cheminformatics. Since 2002 he is a full professor of Chem- and Bioinformatics (Beilstein Endowed Chair of Cheminformatics) at Johann Wolfgang Goethe-University in Frankfurt, Germany, where he concentrates on the development and application of software methods for virtual screening and molecular design. He has published more than 100 scientific papers, co-edited three multi-author books, and co-authored a textbook on adaptive systems in molecular design. He is editor of the journal "QSAR and Combinatorial Science" and member of the editorial advisory board of the journal "Chembiochem". Milestones of his research include the combination of artificial neural networks as fitness functions for evolutionary molecular design, and the first automated ligand-based denovo design of a novel potassium channel blocker.
|
|
Alignment-free Potential Pharmacophore-Point Descriptors for "Informed" Similarity Searching
Gisbert Schneider, Johann Wolfgang Goethe-University, Beilstein Endowed Chair for Cheminformatics, Institute of Organic Chemistry & Chemical Biology, Marie-Curie-Str. 11, D-60439 Frankfurt, Germany
Correlation-vector representations of small molecules have been employed for similarity searching and the design of focused screening libraries. Potential pharmacophore points (PPP) were either placed on atom centres or constructed as probability distributions using local feature-densities. The latter results in a "fuzzy" PPP descriptor. Distances between PPP-pairs were calculated as shortest paths in the molecular graph and as spatial distances in three-dimensional molecular conformations. PPP weighting schemes were optimized. The resulting correlation-vectors represent a scaled histogram of PPP-pair frequencies. Such alignment-free descriptors were employed for rapid retrospective virtual screening, and compared to their binarized counterparts. Examples of prospective applications will be presented, and the potential of such molecular descriptors for "scaffold-hopping" will be discussed. PPP descriptors were also used as input of machine learning systems like artificial neural networks and Support Vector Machines (SVM). A method for pharmacophore feature extraction using SVM will be presented.
References
1. Fechner U, Franke L, Renner S, Schneider P, Schneider G. Comparison of correlation vector methods for ligand-based similarity searching. J. Comput. Aided Mol. Des. 2003, 17, 687-698.
2. Renner S, Schneider G. Fuzzy pharmacophore models from molecular alignments for correlation-vector-based virtual screening. J. Med. Chem. 2004, 47, 4653-4664.
3. Fechner U, Schneider G. Evaluation of distance metrics for ligand-based similarity searching. Chembiochem 2004, 5, 538-540.
4. Renner S, Noeske T, Parsons CG, Schneider P, Weil T, Schneider G. New allosteric modulators of metabotropic glutamate receptor 5 (mGluR5) found by ligand-based virtual screening. Chembiochem 2005, 6, 620-625.
5. Renner S, Ludwig V, Boden O, Scheffer U, Göbel M, Schneider G. New inhibitors of the Tat-TAR RNA interaction found with a "fuzzy" pharmacophore model. Chembiochem 2005, 6, 1119-1125.
6. Byvatov E, Schneider G. SVM-based feature selection for characterization of focused compound collections. J. Chem. Inf. Comput. Sci. 2004, 44, 993-999.
7. Byvatov E, Sasse BC, Stark H, Schneider G. From virtual to real screening for D3 dopamine receptor ligands. Chembiochem 2005, 6,997-999.
|
|
|
|
|
|
|
|
|
