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.

Background & objectives: Dengue fever, caused by dengue virus (DENV), has become a serious threat to human lives. Phytochemicals are known to have great potential to eradicate viral, bacterial and fungal-borne diseases in human beings. This study was aimed at in silico drug development against nonstructural protein 4B (NS4B) of dengue virus 4 (DENV4). Methods: A total of 2750 phytochemicals from different medicinal plants were selected for this study. These plants grow naturally in the climate of Pakistan and India and have been used for the treatment of various pathologies in human for long-time. The ADMET studies, molecular docking and density functional theory (DFT) based analysis were carried out to determine the potential inhibitory properties of these phytochemicals. Results: The ADMET analysis and docking results revealed nine phytochemicals, i.e. Silymarin, Flavobion, Derrisin, Isosilybin, Mundulinol, Silydianin, Isopomiferin, Narlumicine and Oxysanguinarine to have potential inhibitory properties against DENV and can be considered for additional in vitro and in vivo studies to assess their inhibitory effects against DENV replication. They exhibited binding affinity ≥−8 kcal/mol against DENV4-NS4B. Furthermore, DFT based analysis revealed high reactivity for these nine phytochemicals in the binding pocket of DENV4-NS4B, based on E_LUMO, E_HOMO and band energy gap. Interpretation & conclusion: Five out of nine phytochemicals are reported for the first time as novel DENV inhibitors. These included three phytochemicals from Silybum marianum, i.e. Derrisin, Mundulinol, Isopomiferin, and two phytochemicals from Fumaria indica, i.e. Narlumicine and Oxysanguinarine. However, all the nine phytochemicals can be considered for in vitro and in vivo analysis for the development of potential DENV inhibitors.