Computational identification of microbial phosphorylation sites by the enhanced characteristics of sequence information

Abstract

Protein phosphorylation on serine (S) and threonine (T) has emerged as a key device in the control of many biological processes. Recently phosphorylation in microbial organisms has attracted much attention for its critical roles in various cellular processes such as cell growth and cell division. Here a novel machine learning predictor, MPSite (Microbial Phosphorylation Site predictor), was developed to identify microbial phosphorylation sites using the enhanced characteristics of sequence features. The final feature vectors optimized via a Wilcoxon rank sum test. A random forest classifier was then trained using the optimum features to build the predictor. Benchmarking investigation using the 5-fold cross-validation and independent datasets test showed that the MPSite is able to achieve robust performance on the S- and T-phosphorylation site prediction. It also outperformed other existing methods on the comprehensive independent datasets. We anticipate that the MPSite is a powerful tool for proteome-wide prediction of microbial phosphorylation sites and facilitates hypothesis-driven functional interrogation of phosphorylation proteins. A web application with the curated datasets is freely available at http://kurata14.bio.kyutech.ac.jp/MPSite/ .

Efficient computational model for identification of antitubercular peptides by integrating amino acid patterns and properties

“…A positional comparative analysis is useful to reveal the sequence preference of positional amino acid residue compositions in anti‐TB peptides . First, we generated the two sample sequence logos with respect to the first and second datasets .…”

“…Two well‐known supervised machine learning algorithms of SVM and RF were employed in this study. The RF algorithm has been widely used in medicine and computational biology fields . RF works on a large ensemble of classifiers and regression trees.…”

Importance of protein Ser/Thr/Tyr phosphorylation for bacterial pathogenesis

“…Numerous different prediction methods have been published, including some that focus on kinase-specific phosphorylation sites [199,200]. A few prediction tools have been specifically tailored to bacteria [201][202][203]. The first bacteria-specific phosphosite predictor, Net-PhosBac, was developed using neural network algorithms [201].…”

“…At that time though, only about 150 bacterial phosphosites, from just two species, were available as a training dataset. The MPSite web resource is a more recent and improved machine-learning predictor trained on more than 3000 unique bacterial pSer and pThr sites from the dbPSP database [153,203]. While these and most other methods are solely based on primary, and maybe secondary, structural features, a small predictive performance gain may be obtained by including phosphosite 3D-context information [204].…”

dbPSP 2.0, an updated database of protein phosphorylation sites in prokaryotes

“…After the publication of dbPSP 1.0, it has been visited more than 180,000 times and has served as a highly useful resource for studying prokaryotic phosphorylation 50,[52][53][54][55][56] . For example, Garcia-Garcia et al re-analyzed the phosphoproteomic datasets in dbPSP and found that phosphoproteins are essential for the regulation of the cell cycle and DNA-mediated processes in bacteria 52 55 . In addition, the phosphorylation data of representative prokaryotes from dbPSP was utilized for kinase motif enrichment analysis, and the results demonstrated that most eukaryotic phosphorylation motifs could not be recovered in prokaryotes 56 .…”