QSAR analysis of 1,4-dihydro-4-oxo-1-(2-thiazolyl)-1,8-naphthyridines exhibiting anticancer activity by optimal SMILES-based descriptors

摘要

A predictive model of the anticarcinogenic activity of a 1,4-dihydro-4-oxo-1-(2-thiazolyl)-1,8-naphthyridines series has been built, with statistical quality: n = 75, r 2 = 0.7688, s = 0.48, F = 243 (training set); n = 25, r 2 = 0.8025, s = 0,49, F = 93 (test set). The robustness of this model has been tested in three random splits into training set and test set. Correlation weights (the analogue of the contributions of substituents) of molecular attributes expressed by symbols in the simplified molecular input line entry system (SMILES) notation are able to serve as informative indicators in the search for new anticancer agents. Keywords SMILES - QSAR - Optimal descriptor - Anticancer activity