Department of Computer Science
Permanent URI for this collection
Browse
Browsing Department of Computer Science by Subject "Additional stability"
Now showing 1 - 1 of 1
Results Per Page
Sort Options
Item Prediction of disulfide bonding sites in proteins using position and composition relative feature vectors(University of Management and Technolog, 2017) Jamil, MehreenThe presence of disulfide bonds in a protein confers an additional stability to protein against various threats. The formation of correct disulfide bonds between cysteine residues ensures proper folding of the protein during in vivo and in vitro folding process. Oxidation of these bonds may disturb the proper biological activity of a protein. Not all cysteines in a protein are involved in the formation of disulfide bonds,therefore prediction of accurate disulfide bonds is crucial for structural and functional relationship of a protein. Many neurodegenerative diseases are caused by the improper formation of disulfide bonds in the nervous system .The determination of fallacious S-S interaction is crucial for correct diagnosis of these disorders. In this study a novel method is used to predict the intra molecular disulfide bonding accurately using context based information. The surrounding amino acids of the cysteine, involved in disulfide bond, play a vital role in making disulfide bonds and used as feature vectors. The proposed method uses context-based data to calculate statistical moments. Statistical moments are very important as they are very sensitive regarding to position of data sequences. For prediction of intra molecular disulfide bonds, these moments are combined together to train neural networks. 10-fold validation on accumulative dataset gives us 87.52% accurate result. Estimation of accurate disulfide bonding against independent data set for 5-fold and 10-fold result in 82.4% and 88% respectively. The overall accuracy of system is 86.3% to sensitivity value 82.4% and specificity 93%.