Applications of
Cheminformatics & Chemical Modelling
to Drug Discovery
Klon, A



SignUp
(to Register)

Login
User Name
Password

Forgot Password?

About Anthony Klon (Pharmacopeia Drug Discovery)
Doctor Anthony E. Klon received his B.S. in Biochemistry from the University of Washington in 1997. After graduation, he pursued graduate studies in the lab of Professor Stephen C. Harvey in the Department of Biochemistry and Molecular Genetics at the University of Alabama at Birmingham. His thesis research focused on modeling the structure and dynamics of high-density lipoprotein particles with an emphasis on the structure and function of apolipoprotein A-I bound to discoidal HDL particles. While pursuing his dissertation research, he also studied protein and small molecule x-ray crystallography with Dr. David W. Borhani at the Southern Research Institute where he solved the atomic resolution ternary structures of human dihydrofolate reductase complexed with lipophilic antifolates. After receiving his PhD in 2002, he pursued postdoctoral studies with Dr. John W. Davies in the Lead Discovery Center at the Novartis Institutes for Biomedical Research in Cambridge, Massachusetts. His postdoctoral work focused on the evaluation of high-throughput docking software against a variety of pharmaceutically relevant targets. While at Novartis, he developed novel methods of improving the scoring of docking results using a combination of machine learning algorithms and data fusion techniques. Since 2005 he has been a research scientist at Pharmacopeia in Princeton, New Jersey where he has supported a variety of drug discovery programs. His current research interests include virtual high-throughput screening techniques, modeling the dynamics of protein-ligand interactions and developing novel approaches for ADME property prediction.
Abstract
Bayesian Modeling of Numerical Data for ADME Property Prediction

Anthony E. Klon, Pharmacopeia Drug Discovery

We have implemented a naïve Bayesian classifier which models continuous numerical data using a Gaussian distribution. Several cases of interest in the area of ADME prediction are presented demonstrating that this approach is superior to implementations of Bayesian classifiers that model chemical descriptors with numerical values as binary data. We demonstrate that this enhanced performance, when compared with other implementations is independent of the descriptor sets chosen. We also compare the performance of three implementations of naïve Bayesian classifiers with previously published models.

News and Announcements
Advanced Training Week
Drug Discovery Design Methods
Hyderabad, 7-10 Dec 2009
Oxford, 20-24 July 2009
InterAction Meetings 2008
Advances in Drug Discovery Informatics
Philadelphia, 14-17 Oct. 2008
Hyderabad, 11-12 Dec 2009
InnovationWell
InnovationWell Workshops
Virtual Proceedings for Members
eCheminfo 2005 InterAction Meeting
eCheminfo 2004 Conference
Featured Talks for Visitors
Open Archives as a Route for the Capture, Dissemination and Access to Chemical Information – Simon Coles, University of Southampton
Cheminfostream Blog
Cheminformatics & Community News
Sponsors
Partners

© Copyright 2004-2007 Colayer 
Colayer