A New Feature Extraction Approach in Classification for Improving the Accuracy of Proteins

Abstract

Proteins play a vital role in life as essential macromolecules, consisting of linear heteromeric biopolymers formed by amino acids covalently bonded through peptide bonds. They contribute to cell development and bolster the body's defense mechanisms. Post-translational modification processes, such as glycosylation, are necessary for proteins to function optimally. Glycosylation involves adding sugar groups to proteins, playing a critical role in various protein folding processes. Dysregulation of protein glycosylation can lead to diseases like Alzheimer's and cancer. Manual classification of glycosylated proteins is time-consuming, necessitating a faster approach. This study aims to expedite glycosylated protein classification using novel methods like AAindex, CTD, SABLE, hydrophobicity, and PseAAC for increased accuracy, comparing them with existing approaches. The dataset comprises protein sequences sourced from the openly accessible UniProt database. Results demonstrate that glycosylated protein prediction achieved 100% accuracy, surpassing previous approaches. Several features contributed to this improvement, with Hydrophobicity making a significant contribution at 24%, and PseAAC making the most significant contribution at 40% among the five extraction methods developed.