A combined LS-SVM & MLR QSAR workflow for predicting the inhibition of CXCR3 receptor by quinazolinone analogs

Afantitis, A; Melagraki, G; Sarimveis, H; Koutentis, PA; Igglessi-Markopoulou, O; Kollias, G

dc.contributor.author	Afantitis, A	en
dc.contributor.author	Melagraki, G	en
dc.contributor.author	Sarimveis, H	en
dc.contributor.author	Koutentis, PA	en
dc.contributor.author	Igglessi-Markopoulou, O	en
dc.contributor.author	Kollias, G	en
dc.date.accessioned	2014-03-01T01:32:25Z
dc.date.available	2014-03-01T01:32:25Z
dc.date.issued	2010	en
dc.identifier.issn	1381-1991	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/20126
dc.subject	CXCR3	en
dc.subject	In silico predictions	en
dc.subject	Molecular modelling	en
dc.subject	QSAR	en
dc.subject.classification	Biochemistry & Molecular Biology	en
dc.subject.classification	Chemistry, Applied	en
dc.subject.classification	Chemistry, Medicinal	en
dc.subject.classification	Chemistry, Multidisciplinary	en
dc.subject.other	antiinflammatory agent	en
dc.subject.other	chemokine receptor CXCR3	en
dc.subject.other	quinazolinone derivative	en
dc.subject.other	article	en
dc.subject.other	computer model	en
dc.subject.other	IC 50	en
dc.subject.other	kernel method	en
dc.subject.other	least squares support vector machine	en
dc.subject.other	molecular model	en
dc.subject.other	pharmacophore	en
dc.subject.other	prediction	en
dc.subject.other	priority journal	en
dc.subject.other	quantitative structure activity relation	en
dc.subject.other	radial based function	en
dc.subject.other	receptor blocking	en
dc.subject.other	sensitivity and specificity	en
dc.subject.other	support vector machine	en
dc.subject.other	validation study	en
dc.subject.other	algorithm	en
dc.subject.other	chemical model	en
dc.subject.other	chemistry	en
dc.subject.other	drug antagonism	en
dc.subject.other	regression analysis	en
dc.subject.other	reproducibility	en
dc.subject.other	statistical model	en
dc.subject.other	Algorithms	en
dc.subject.other	Inhibitory Concentration 50	en
dc.subject.other	Least-Squares Analysis	en
dc.subject.other	Linear Models	en
dc.subject.other	Models, Chemical	en
dc.subject.other	Quantitative Structure-Activity Relationship	en
dc.subject.other	Quinazolinones	en
dc.subject.other	Receptors, CXCR3	en
dc.subject.other	Reproducibility of Results	en
dc.title	A combined LS-SVM & MLR QSAR workflow for predicting the inhibition of CXCR3 receptor by quinazolinone analogs	en
heal.type	journalArticle	en
heal.identifier.primary	10.1007/s11030-009-9163-7	en
heal.identifier.secondary	http://dx.doi.org/10.1007/s11030-009-9163-7	en
heal.language	English	en
heal.publicationDate	2010	en
heal.abstract	A novel QSAR workflow is constructed that combines MLR with LS-SVM classification techniques for the identification of quinazolinone analogs as "active" or "nonactive" CXCR3 antagonists. The accuracy of the LS-SVM classification technique for the training set and test was 100% and 90%, respectively. For the "active" analogs a validated MLR QSAR model estimates accurately their I-IP10 IC50 inhibition values. The accuracy of the QSAR model (R-2 = 0.80) is illustrated using various evaluation techniques, such as leave-one-out procedure (R-LOO(2) = 0.67) and validation through an external test set (R-pred(2) = 0.78). The key conclusion of this study is that the selected molecular descriptors, Highest Occupied Molecular Orbital energy ( HOMO), Principal Moment of Inertia along X and Y axes PMIX and PMIZ, Polar Surface Area (PSA), Presence of triple bond (PTrplBnd), and Kier shape descriptor ((1)kappa), demonstrate discriminatory and pharmacophore abilities.	en
heal.publisher	SPRINGER	en
heal.journalName	Molecular Diversity	en
dc.identifier.doi	10.1007/s11030-009-9163-7	en
dc.identifier.isi	ISI:000276521000003	en
dc.identifier.volume	14	en
dc.identifier.issue	2	en
dc.identifier.spage	225	en
dc.identifier.epage	235	en