| Literature DB >> 11045823 |
Abstract
Data for 25 tropane analogues binding to the dopamine transporter were modeled using E-state molecular structure descriptors. Both E-state and hydrogen E-state descriptors appear in the model in both atom-level and atom-type descriptors. A statistically satisfactory four-variable model is obtained, and structure interpretation is given for each variable, emphasizing substituent influence on nonpolar parts of the molecule as well as the role of hydrogen bonding. A leave-group-out approach to model validation is presented in which each observation is removed from the data set three times in random groups of 20% of the whole data set. The average of the resulting predicted values constitutes consensus predictions for these data and supports the claim that the E-state model may be useful for prediction of pIC50 values for new compounds.Entities:
Mesh:
Substances:
Year: 2000 PMID: 11045823 DOI: 10.1021/ci000023x
Source DB: PubMed Journal: J Chem Inf Comput Sci ISSN: 0095-2338