|
|
|
|
|
|
|
|
| Curt Breneman, Rensselaer Polytechnic Institute |
|
Curt Breneman was born in Santa Monica, California in 1956, and went on to earn a B.S. in Chemistry at UCLA in 1980 followed by a Ph.D. in Chemistry at UC Santa Barbara (with an emphasis on Physical Organic and Computational Chemistry) in 1987. Following two years of post-doctoral research at Yale University, Dr. Breneman joined the faculty of the Department of Chemistry at Rensselaer Polytechnic Institute (RPI) and began a program in molecular recognition and computational chemistry based on his concept of "Transferable Atom Equivalents", or TAEs, as building blocks for describing the electronic and reactive character of molecules. Dr. Breneman currently holds the rank of Full Professor in the RPI Department of Chemistry and Chemical Biology, and is taking a leading role in the Center for Biocomputation and Quantitation in Rensselaer's new Biotechnology and Interdisciplinary Studies.
The Breneman research group primarily specializes in the development of new molecular property descriptors and machine learning methods that can be applied to a diverse set of physical and biochemical problems. Of paramount interest are methods that can increase the information content of molecular descriptors, and machine learning techniques that can exploit this data for the creation of fully validated, predictive property models. Current application areas include pharmaceutical ADME prediction, virtual high-throughput screening of drug candidates, protein chromatography modeling (HIC and ion-exchange), as well as polymer property prediction.
|
|
Predictive ADME: How do I know if my predictions will be useful?
Curt Breneman, RPI Chemistry
Given the current capabilities of academic, commercial and semi-commercial statistical modeling tools and descriptor generators, there is a clear need to establish “best practice” methods and criteria for model validation - particularly in an area as complex as Predictive Toxicology. Different philosophies exist regarding the number and type of descriptors that can be used for generating predictive models, and the number of cases necessary for creating linear or non-linear models that can reliably cover important regions of chemical structure/activity space. To what extent does a model need to be interpretable in order to produce trusted predictions? What are the lower limits of training set size to address given types of problems? Is there a way to determine whether a given set of unknowns are within the domain of a particular model? These and other related questions will be discussed, along with examples of classification, regression and non-linear regression models of molecular ADME properties.
|
|
|
|
|
|
|
|
|
|
|
