QSAR Analysis Of Yellow Fever
Introduction: Yellow fever is an acute viral hemorrhagic disease transmitted to humans and other vertebrate hosts by the bite of infected mosquitoes. The name “Yellow” is explained by jaundice that affect some patients with symptoms’ like yellow skin and yellow eyes(http://www.who.int/csr/disease/yellowfev/en/) The YF virus is the causative agent for Yellow fever and it belongs to the virus family Flaviviridae. Single stranded RNA (11kb) present in Flavi viruses .YF virus responsible for number of disease in humans, the symptoms may be mild illness to fatal conditions. Clinical symptoms are divided into two phase, the first phase (period of infection) and second phase (the toxic phase). First phase having symptoms like sudden onset of
…show more content…
So the QSAR model developed from training set should be validated by new chemical entities for judgment of the predictivity of the models. For most of the cases appropriate external data set is not available for prediction, consequently the original data set is divided into training and test sets. so the selection of training set is crucial in QSAR analysis. We have divided the whole data set (n=20) into training set (n=15/16) and test set (n=4/5) by different splitting techniques such as Activity/property based, Kennard stone method and Euclidean distance based. And for the development of QSAR model we exclusively used statistical technique GFA (Genetic Function …show more content…
Equation 1 could explain 76.4 % variance (adjusted coefficient of variance) and the LOO-predicted variance was found to be 73.9%.The value of R2(pred) and Rm2 are 0.711 and 0.664 respectively. Among the three descriptor SpMin7_Bhe shows negative contribution while SpMax2_Bhp and VR1_Dzp shows positive contribution towards the activity against yellow fever virus. as the value of SpMax2_Bhp increases the potency of compound (20,19,17,15,14,13,12) increases and same like SpMax2_Bhp, as the value of VR1_Dzp increase it also add positive contribution in biological activity of the compound ( 9,18,17,15,12,16 )but in case of SpMin7_Bhe for the better activity the value of SpMin7_Bhe should be
So the QSAR model developed from training set should be validated by new chemical entities for judgment of the predictivity of the models. For most of the cases appropriate external data set is not available for prediction, consequently the original data set is divided into training and test sets. so the selection of training set is crucial in QSAR analysis. We have divided the whole data set (n=20) into training set (n=15/16) and test set (n=4/5) by different splitting techniques such as Activity/property based, Kennard stone method and Euclidean distance based. And for the development of QSAR model we exclusively used statistical technique GFA (Genetic Function …show more content…
Equation 1 could explain 76.4 % variance (adjusted coefficient of variance) and the LOO-predicted variance was found to be 73.9%.The value of R2(pred) and Rm2 are 0.711 and 0.664 respectively. Among the three descriptor SpMin7_Bhe shows negative contribution while SpMax2_Bhp and VR1_Dzp shows positive contribution towards the activity against yellow fever virus. as the value of SpMax2_Bhp increases the potency of compound (20,19,17,15,14,13,12) increases and same like SpMax2_Bhp, as the value of VR1_Dzp increase it also add positive contribution in biological activity of the compound ( 9,18,17,15,12,16 )but in case of SpMin7_Bhe for the better activity the value of SpMin7_Bhe should be