caa a22 4500 445879106 CHVBK 20180317145536.0 cr unu---uuuuu 170323e20110501xx s 000 0 eng 10.1007/s11030-010-9238-5 doi (NATIONALLICENCE)springer-10.1007/s11030-010-9238-5 Quantitative structure-activity relationship study of antitubercular fluoroquinolones [Elektronische Daten] [Nikola Minovski, Marjan Vračko, Tom Šolmajer] Quantitative structure-activity relationship study on three diverse sets of structurally similar fluoroquinolones was performed using a comprehensive set of molecular descriptors. Multiple linear regression technique was applied as a preprocessing tool to find the set of relevant descriptors (10) which are subsequently used in the artificial neural networks approach (non-linear procedure). The biological activity in the series (minimal inhibitory concentration (μg/mL) was treated as negative decade logarithm, pMIC). Using the non-linear technique counter propagation artificial neural networks, we obtained good predictive models. All models were validated using cross validation leave-one-out procedure. The results (the best models: Assay1, R= 0.8108; Assay2, R= 0.8454, and Assay3, R= 0.9212) obtained on external, previously excluded test datasets show the ability of these models in providing structure-activity relationship of fluoroquinolones. Thus, we demonstrated the advantage of non-linear approach in prediction of biological activity in these series. Furthermore, these validated models could be proficiently used for the design of novel structurally similar fluoroquinolone analogues with potentially higher activity. Springer Science+Business Media B.V., 2010 Tuberculosis nationallicence Fluoroquinolones nationallicence DNA gyrase nationallicence QSAR nationallicence CP ANN nationallicence ATP : Adenosine triphosphate nationallicence MIC : Minimal inhibitory concentration nationallicence SAR : Structure-activity relationship nationallicence QSAR : Quantitative structure-activity relationship nationallicence CODESSA : Comprehensive descriptors for structural and statistical analysis nationallicence MLR : Multiple linear regression nationallicence NN : Neural networks nationallicence ANN : Artificial neural networks nationallicence CP ANN : Counter propagation artificial neural networks nationallicence KANN : Kohonen artificial neural networks nationallicence SOM : Self organizing maps nationallicence CVLOO : Cross validation leave-one-out nationallicence Minovski Nikola National Institute of Chemistry, Hajdrihova 19, 1001, Ljubljana, Slovenia aut Vračko Marjan National Institute of Chemistry, Hajdrihova 19, 1001, Ljubljana, Slovenia aut Šolmajer Tom National Institute of Chemistry, Hajdrihova 19, 1001, Ljubljana, Slovenia aut Molecular Diversity Springer Netherlands 15/2(2011-05-01), 417-426 1381-1991 15:2<417 2011 15 11030 https://doi.org/10.1007/s11030-010-9238-5 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/s11030-010-9238-5 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Minovski Nikola National Institute of Chemistry, Hajdrihova 19, 1001, Ljubljana, Slovenia aut NATIONALLICENCE 700 1- Vračko Marjan National Institute of Chemistry, Hajdrihova 19, 1001, Ljubljana, Slovenia aut NATIONALLICENCE 700 1- Šolmajer Tom National Institute of Chemistry, Hajdrihova 19, 1001, Ljubljana, Slovenia aut NATIONALLICENCE 773 0- Molecular Diversity Springer Netherlands 15/2(2011-05-01), 417-426 1381-1991 15:2<417 2011 15 11030 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer