Application of BCUT Metrics and Genetic Algorithm in Binary QSAR Analysis

Hua Gao
2001 Journal of chemical information and computer sciences  
The application of three-dimensional H-suppressed BCUT metrics (BCUTs) in binary QSAR analysis was investigated using carbonic anhydrase II inhibitors and estrogen receptor ligands as test cases. Variable selection was accomplished with a genetic algorithm (GA). Highly predictive binary QSAR models were obtained for both sets of compounds within 200 GA generations. The derived binary QSAR models were validated with two sets of compounds not included in the training sets. The results indicate
more » ... results indicate that BCUTs are very useful molecular descriptors, and the genetic algorithm is a very efficient variable selection tool in binary QSAR analysis. † Corresponding author
doi:10.1021/ci000306p pmid:11277729 fatcat:wiurwvzxvfbzdlau2xjpnuwbae