Prediction of N-linked glycosylation sites using position relative features and statistical moments.
Muhammad Aizaz AkmalNouman RasoolYaser Daanial KhanPublished in: PloS one (2017)
Glycosylation is one of the most complex post translation modification in eukaryotic cells. Almost 50% of the human proteome is glycosylated as glycosylation plays a vital role in various biological functions such as antigen's recognition, cell-cell communication, expression of genes and protein folding. It is a significant challenge to identify glycosylation sites in protein sequences as experimental methods are time taking and expensive. A reliable computational method is desirable for the identification of glycosylation sites. In this study, a comprehensive technique for the identification of N-linked glycosylation sites has been proposed using machine learning. The proposed predictor was 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 inferred that the accuracy of proposed tool is far better than the existing systems such as Glyomine, GlycoEP, Ensemble SVM and GPP.
Keyphrases
- neural network
- single cell
- induced apoptosis
- poor prognosis
- cell therapy
- endothelial cells
- bioinformatics analysis
- machine learning
- deep learning
- stem cells
- magnetic resonance imaging
- computed tomography
- cell death
- cell cycle arrest
- oxidative stress
- gene expression
- cell proliferation
- small molecule
- convolutional neural network
- long non coding rna
- signaling pathway
- high intensity
- pluripotent stem cells