PLMLA: prediction of lysine methylation and lysine acetylation by combining multiple features

Abstract

Post-translational lysine methylation and acetylation are two major modifications of lysine residues. They play critical roles in various biological processes, especially in gene regulation. Identification of protein methylation and acetylation sites would be a foundation for understanding their modification dynamics and molecular mechanism. This work presents a method called PLMLA that incorporates protein sequence information, secondary structure and amino acid properties to predict methylation and acetylation of lysine residues in whole protein sequences. We apply an encoding scheme based on grouped weight and position weight amino acid composition to extract sequence information and physicochemical properties around lysine sites. The prediction accuracy for methyllysine and acetyllysine are 83.02% and 83.08%, respectively. Feature analysis reveals that methyllysine is likely to occur at the coil region and acetyllysine prefers to occur at the helix region of protein. The upstream residues away from the central site may be close to methylated lysine in three-dimensional structure and have a significant influence on methyllysine, while the positively charged residues may have a significant influence on acetyllysine. The online service is available at http://bioinfo.ncu.edu.cn/inquiries_PLMLA.aspx.

SIRT1 contributes to aldose reductase expression through modulating NFAT5 under osmotic stress: In vitro and in silico insights

“…10 different algorithms were used; KacePred [48], PAIL [49], ASEB [50,51], Predmod [52], BRABSB-PHKA [53], PSKAcePred [54], PLMLA [55], PHOSIDA [56], EnsemblePail [57] and Lys Acet [58], which are, to our knowledge, the most frequently and widely used/cited methods for prediction of lysine acetylation sites. Threshold values were taken as stringent as possible for all predictions (Supplementary Table 1).…”

Prediction of β-lactamase and its class by Chou’s pseudo-amino acid composition and support vector machine

“…It is widely used in pattern recognition and in various biological prediction problems viz. microarray gene expression data analysis (Brown et al, 2000), cancer tissue classification (Furey et al, 2000), protein secondary structure prediction (Hua and Sun, 2001), subcellular localization prediction (Chou and Cai, 2002;Kumar and Raghava, 2009;Kumar et al, 2014;Shen and Chou, 2007;Wang et al, 2004), protein-protein interaction prediction (Bock and Gough, 2001), translation initiation site recognition (Zien et al, 2000), post-translational modification prediction (Kumari et al, 2014;Shi et al, 2012;Shien et al, 2009), RNA (Kumar et al, 2008(Kumar et al, , 2010 and DNA binding protein prediction (Kumar et al, 2007) etc. A detailed description of SVM can be obtained from .…”

In silico prediction and characterization of protein post-translational modifications

“…Reproduced from Figure 1 (panel A), Figure 3 (panel B) and Figure 4 (panel C) in [119]. M A N U S C R I P T phosphorylation general and kinase-specific sites [7] kinase-specificity with indirect relationship [8] phosphorylation and conformational flexibility [9] association patterns around phosphorylation sites [10] random forests [11] relevance units machines [12] sequence with feature selection [13] in eukaryotes [14] in bacteria [15] lysine acetylation support vector machines [16,17] bi-relative adapted binomial score Bayes feature representation [18] logistic regression classifiers [19] solvent accessibility and acetylation [20] PTM crosstalk [21] combination of multiple features [22] position-specificity [23] sequence and functional features [24] characterization of KAT acetylation sites [25] proteome-wide prediction [26] lysine acetylation in context [27] prediction of KAT acetylation sites [28] lysine methylation combination of multiple features [22] conditional random field [29] composition of K-spaced amino acid pairs [30] glycosylation O-glycosylation [31] N-, O-and C-glycosites in eukaryotes [32] in evolutionarily distant eukaryotes [33] O-GlcNAc [34] amidation feature selection [35] -carboxylation random forest [36] scoring matrices based on evolutionary information [37] disulfides feature selection [38] S-glutathionylation protein sequence …”