Aizaz Akmal, Muhammad2017-11-292017-11-292017https://escholar.umt.edu.pk/handle/123456789/2251Supervised by:Dr. Yaser Daanial KhanProtein glycosylation is one of the most complex post translation modifications in eukaryote cells as most of the proteins are unable to perform their physiological functions without such modifications. Almost 50% of the human proteome is glycosylated as it plays a vital role in various biological functions such as antigen’s recognition, cell-cell communication and adhesion, expression of the genes and protein folding. It is a significant challenge to identify glycosylation sites in protein sequences as experimental methods are time taking and expensive. Therefore, reliable computational method is required for the identification of glycosylation sites. In this study, a comprehensive technique for the identification of N-linked and O-linked glycosylation for Serine and Threonine sites has been proposed using machine learning. The proposed predictors were trained using an up-to-date dataset through back propagation algorithm for multilayer neural network. The results of ten-fold cross-validation and other performance measures such as accuracy, sensitivity, specificity and Mathew’s correlation coefficient show that the accuracy of proposed tool is far better than the existing systems such as Glyomine, GlycoEP, Ensemble SVM, NetOglyc, CKSAAP-OGlySite and GPP.enphysiological functionsIdentify glycosylationMS ThesisThesis