LAceP: Lysine Acetylation Site Prediction Using Logistic Regression Classifiers

Ting Hou,Yixue Li,Chaochun Wei,Pingyu Zhang,Jing Li,Guangyong Zheng,Jia Jia,Lu Xie,Wei-Guo Zhu

doi:10.1371/journal.pone.0089575

Abstract

BackgroundLysine acetylation is a crucial type of protein post-translational modification, which is involved in many important cellular processes and serious diseases. However, identification of protein acetylated sites through traditional experiment methods is time-consuming and laborious. Those methods are not suitable to identify a large number of acetylated sites quickly. Therefore, computational methods are still very valuable to accelerate lysine acetylated site finding.ResultIn this study, many biological characteristics of acetylated sites have been investigated, such as the amino acid sequence around the acetylated sites, the physicochemical property of the amino acids and the transition probability of adjacent amino acids. A logistic regression method was then utilized to integrate these information for generating a novel lysine acetylation prediction system named LAceP. When compared with existing methods, LAceP overwhelms most of state-of-the-art methods. Especially, LAceP has a more balanced prediction capability for positive and negative datasets.ConclusionLAceP can integrate different biological features to predict lysine acetylation with high accuracy. An online web server is freely available at http://www.scbit.org/iPTM/.

Highlights

In the post-genomic era, one of the important goals of biological research is to explain genome contexts and understand the function of genetic information [1]
We present a lysine acetylation site prediction system named LAceP based on a logistic regression model
Data collection Our experimentally validated lysine acetylation sites are extracted from a database for post-translational modification (PTM) called SysPTM2 and the PhosphoSitePlus [35] database

Summary

Introduction

In the post-genomic era, one of the important goals of biological research is to explain genome contexts and understand the function of genetic information [1]. A vast scale of acetylated proteins in mammalian have been identified by proteomics methods, suggesting that acetylation may be as ubiquitous as phosphorylation [4,5]. It is reported by Van Damme [6] that ,85% of human proteins and 68% of yeast proteins were acetylated at N-terminus. Identification of protein acetylated sites through traditional experiment methods is time-consuming and laborious. Those methods are not suitable to identify a large number of acetylated sites quickly. Computational methods are still very valuable to accelerate lysine acetylated site finding

Methods

Results

Conclusion