Protein acetylation is a widespread covalent modification in eukaryotes, transferring acetyl groups from acetyl coenzyme A (acetyl CoA) to either α-amino (N^α) group of amino-terminal residues or to the ε-amino group (N^ε) of internal lysines at specific sites (Glozak,MA et al., 2005;Kouzarides,T, 2000; Polevoda,B et al., 2000; Polevoda,B et al., 2002; Yang,XJ, 2004). As one of the most ubiquitous protein modifications, approximately 85% of eukaryotic proteins are N^α-terminal acetylated in a co-translational manner on several types of residues such as Serine, Alainine, and so on (Polevoda,B et al., 2000; Polevoda,B et al., 2002). And N^ε-lysine acetylation is less common, but probably more important. N^ε-acetylation of proteins in internal lysine residues is an essential and highly reversible type of post-translational modification (PTM), and orchestrates a variety of cellular processes, including transcription regulation (Faiola,F et al., 2005; Brunet,A et al., 2004), DNA repair (Murr,R et al., 2006), apoptosis (Subramanian,C et al., 2005; Cohen,HY et al., 2004), cytokine signaling (Yuan,ZL et al., 2005), and nuclear import (Bannister,AJ et al.,2000), etc. As a ‘loss-of-function’ mechanism proposed, N^ε-acetylation greatly alters the electrostatic properties of a protein by neutralizing the positive charge of the lysine residues. And formation of hydrogen bonds on lysine side-chains are also disrupted (Yang,XJ, 2004; Yang,XJ,2004b). In addition, lysine acetylation also creates a new interface for protein binding, as a ‘gain-of-function’ mechanism (Yang,XJ, 2004; Yang,XJ,2004b). Thus, N^ε-acetylation may modulate the protein function, such as of protein-protein interaction, DNA binding, enzymatic activity, stability and subcellular localization (Glozak,MA et al., 2005; Polevoda,B et al., 2002; Yang,XJ, 2004; Faiola,F et al., 2005; Brunet,A et al., 2004; Yuan,ZL et al., 2005; Bannister,AJ et al.,2000; Yang,XJ,2004b).

    In this work, we present a novel online predictor for protein acetylation sites prediction of PAIL, Prediction of Acetylation on Internal Lysines. We have manually mined scientific literature to collect 249 experimentally verified acetylation sites of 92 distinct proteins. Then the BDM (Bayesian Discriminant Method) algorithm has been employed. The window length of a potential acetylated peptide has been optimized as 13. The accuracy of PAIL is highly encouraging with 85.13%, 87.97% and 89.21% at low, medium and high thresholds, respectively. Both Jack-knife validation and n-fold (6-, 8-, and 10-fold) cross-validation have been performed to show that the PAIL is accurate and robust. In this regard, we propose that PAIL could be a useful tool for experimentalists. And the prediction results of PAIL might also be insightful for further experimental design. For convenience, we have implemented the prediction system in a web server, which is available at: http://bdmpail.biocuckoo.org/.