Improved Identification Performance of Lysine Glycation PTM using PSI-BLAST

Protein is essential to the overall health of the human body which undergoes various enzymatic modifications referring as Post-translational modification (PTM) which forms a mature product of protein. Glycation is one of the 40 ptms that are discovered so far, a non-enzymatic covalent bond of sugar and protein or lipid. It is a bio-maker for renal failure, diabetes and implicated in other health issues as well, imprinting significant importance for its site identification in a protein sequence. Manual researches in the laboratory are quite expensive and prolonged. In modern times, computerized tools for ptm prediction is very popular and useful. In our experiment, we intended to improve Glycation prediction using an alternate feature extraction method, called Position-Specific Iterative Basic Local Alignment Search Tool (PSI-BLAST) deriving a position-specific scoring matrix (PSSM) and providing us 99% accuracy, 99.83% sensitivity, 99.15% specificity and 98.98% MCC by executing an Support vector machine (kernel=rbf) model outpacing the performance of an earlier developed tool GlyStruct.