Sequence-based Identification of Arginine Amidation Sites in Proteins Using Deep Representations of Proteins and PseAAC

Abstract

Background: Among all the major post-translational modifications, amidation seems to be a small change, where a peptide ends with an amide group (-NH 2), not a carboxyl group (-COOH). Thus, to study their physicochemical properties, identification of the amidation mechanism is very important. However, the in vitro, ex vivo and in vivo identification can be laborious, time-taking and costly. There is a dire need for an efficient and accurate computational model to help researchers and biologists identifying these sites, in an easy manner. Objectives: Herein, we propose a novel predictor for the identification of arginine amide (R-Amide) sites in proteins, by integrating the Chou’s Pseudo Amino Acid Composition (PseAAC) with deep features. Methods: We use well-known DNNs for both the tasks of learning a feature representation of peptide sequences and performing classifications. Methods: We use well-known DNNs for both the tasks of learning a feature representation of peptide sequences and performing classifications. Results: Among different DNNs, CNN showed the highest scores in terms of accuracy, and all other computed measures outperformed all the previously reported predictors. Conclusions: Based on these results, it is concluded that the proposed model can help identify arginine amidation in a very efficient and accurate manner, which can help scientists understand the mechanism of this modification in proteins.