Browsing by Author "Aizaz Akmal, Muhammad"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Community (android app)
    (University of Management and Technology, 2014) Aizaz Akmal, Muhammad; Zahab Ahmed
    We are going to develop a Social application “Community” for android users initially. It is all about socializing people by just making small communities in it. So that people can knows eachother by using this app. Users just need to create their accounts on this app, while creating account user just need to provide some basic information like theirName, Country, City, Area, Institute and Company etc. With this information app create five different communities. People belonging to same community automatically add into that community and the social linking among people of same country, same city, same area, same institute and same company starts. Users can also create their own community according totheir need. So that he can invite friends from existing communities. So people can share their ideas, moods, talks, photos with other people who are in communities. Other people can like and comments on statuses and photos. This app also uses GPS location to locate people who are users of this app. If a person enters into Lahore who is using this app using GPS location this application add that person into the community of Lahore City. So this application can create interaction with those people who also from out of the community but currently they are present in the location of community they will be consider as the part of community till they are in the location of that community.
  • Thumbnail Image
    Item
    Prediction of N- and O-linked glycosylation sites using position relative features and statistical moments
    (University of Management and Technology Lahore, 2017) Aizaz Akmal, Muhammad
    Protein 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.