TY - JOUR
T1 - Bayesian neural nets for modeling in drug discovery
AU - Winkler, David A
AU - Burden, Frank R
PY - 2004/5
Y1 - 2004/5
N2 - Bayesian regularized artificial neural networks (BRANNs) are used in the development of quantitative SAR models. These networks have the potential to solve several problems that arise in QSAR modeling such as choice of model, robustness of model, choice of validation set, size of validation effort, and optimization of network architecture. The application of the methods to a wide range of problems, including target-based QSAR, ADMET modeling and eukaryotic promoter finding, is illustrated.
AB - Bayesian regularized artificial neural networks (BRANNs) are used in the development of quantitative SAR models. These networks have the potential to solve several problems that arise in QSAR modeling such as choice of model, robustness of model, choice of validation set, size of validation effort, and optimization of network architecture. The application of the methods to a wide range of problems, including target-based QSAR, ADMET modeling and eukaryotic promoter finding, is illustrated.
UR - http://www.scopus.com/inward/record.url?scp=12444281776&partnerID=8YFLogxK
U2 - 10.1016/S1741-8364(04)02393-5
DO - 10.1016/S1741-8364(04)02393-5
M3 - Review Article
SN - 1741-8364
VL - 2
SP - 104
EP - 111
JO - Drug Discovery Today: Biosilico
JF - Drug Discovery Today: Biosilico
IS - 3
ER -