Current time in Korea 09:22 Oct 24 (Tue) Year 2017 KCS KCS Publications
KCS Publications
My Journal Log In Register
HOME > Search > Browsing(BKCS) > Archives

Bulletin of the Korean Chemical Society (BKCS)

ISSN 0253-2964(Print)
ISSN 1229-5949(Online)
Volume 32, Number 7
BKCSDE 32(7)
July 20, 2011 

Development of kNN QSAR Models for 3-Arylisoquinoline Antitumor Agents  
Alexander Tropsha, Alexander Golbraikh, Won-Jea Cho*
Antitumor agents, 3-Arylisoquinolines, k nearest neighbor QSAR
Variable selection k nearest neighbor QSAR modeling approach was applied to a data set of 80 3- arylisoquinolines exhibiting cytotoxicity against human lung tumor cell line (A-549). All compounds were characterized with molecular topology descriptors calculated with the MolconnZ program. Seven compounds were randomly selected from the original dataset and used as an external validation set. The remaining subset of 73 compounds was divided into multiple training (56 to 61 compounds) and test (17 to 12 compounds) sets using a chemical diversity sampling method developed in this group. Highly predictive models characterized by the leave-one out cross-validated R2 (q2) values greater than 0.8 for the training sets and R2 values greater than 0.7 for the test sets have been obtained. The robustness of models was confirmed by the Y-randomization test: all models built using training sets with randomly shuffled activities were characterized by low q2 ≤ 0.26 and R2 ≤ 0.22 for training and test sets, respectively. Twelve best models (with the highest values of both q2 and R2) predicted the activities of the external validation set of seven compounds with R2 ranging from 0.71 to 0.93.
2397 - 2404
Full Text