Predicting pupylation sites in prokaryotic proteins using pseudo-amino acid composition and extreme learning machine

摘要

Pupylation is one of the most important post-translational modifications of prokaryotic proteins playing a key role in regulating a wild range of biological processes. Prokaryotic ubiquitin-like protein can attach to specific lysine residues of substrate proteins by forming isopeptide bonds for the selective degradation of proteins in Mycobacterium tuberculosis. In order to comprehensively understand these pupylation-related biological processes, identification of pupylation sites in the substrate protein sequence is the first step. The traditional wet-lab experimental approaches are both laborious and time-consuming. To timely and effectively discover pupylation sites when facing with the avalanche of new protein sequences emerging during the post-genomic Era, a novel computational predictor called PupS (pupylation site predictor) is proposed. PupS is constructed on the pseudo-amino acid composition and trained with extreme learning machine. The jackknife cross-validation results on the training dataset show that the area under an ROC Curve (AUC) value is 0.6483 by PupS, and an AUC of 0.6779 is obtained on the independent set. Our results also demonstrate that ELM is complementary to other algorithms and that constructing an ensemble classifier will generate better results.