RF-Hydroxysite: a random forest based predictor for hydroxylation sites

Abstract

Protein hydroxylation is an emerging posttranslational modification involved in both normal cellular processes and a growing number of pathological states, including several cancers. Protein hydroxylation is mediated by members of the hydroxylase family of enzymes, which catalyze the conversion of an alkyne group at select lysine or proline residues on their target substrates to a hydroxyl. Traditionally, hydroxylation has been identified using expensive and time-consuming experimental methods, such as tandem mass spectrometry. Therefore, to facilitate identification of putative hydroxylation sites and to complement existing experimental approaches, computational methods designed to predict the hydroxylation sites in protein sequences have recently been developed. Building on these efforts, we have developed a new method, termed RF-Hydroxysite, that uses random forest to identify putative hydroxylysine and hydroxyproline residues in proteins using only the primary amino acid sequence as input. RF-Hydroxysite integrates features previously shown to contribute to hydroxylation site prediction with several new features that we found to augment the performance remarkably. These include features that capture physicochemical, structural, sequence-order and evolutionary information from the protein sequences. The features used in the final model were selected based on their contribution to the prediction. Physicochemical information was found to contribute the most to the model. The present study also sheds light on the contribution of evolutionary, sequence order, and protein disordered region information to hydroxylation site prediction. The web server for RF-Hydroxysite is available online at http://bcb.ncat.edu/RF_hydroxy/.

MPTM: A tool for mining protein post-translational modifications from literature

“…6 A better understanding of the role of hydroxylation can help inform the development of drug for diseases. 7 At the same time, the latest study shows that myristoylation plays an important role in human immune response 8 and abnormal or irregular myristoylation on proteins can lead to several pathological changes in the cell. 9 GPI-anchored proteins are the major form of cell-surface proteins in humans.…”

“…34 MPTM has the following advantages: (1) it covers 11 common PTMs (phosphorylation, methylation, glycosylation, acetylation, amidation, hydroxylation, myristoylation, sulfation, GPI-anchor, disul¯de and ubiquitination). MPTM is the¯rst web server that provides literature mining service for hydroxylation, myristoylation and GPI-anchor due to their important biological signi¯cance [6][7][8][9][10][11] ; (2) by using an e±cient relation extraction method based on dependency parse trees 35 and a heuristic algorithm, it has good performance in both substrate and modi¯cation site detection; (3) it extracts not only basic PTM information including substrates and modi¯cation sites, but also comprehensive PTM-related information such as enzymes, Gene Ontology (GO) terms, organisms, diseases and crosstalk from literature. The web server is also accompanied by a precompiled collection of PTM information named MPTMDB with 435,433 PTM records, which enables versatile visualization of PTMs, substrates and interacting enzymes.…”

SVM-SulfoSite: A support vector machine based predictor for sulfenylation sites

“…High quality physicochemical indices were similar to those used to develop the hydroxylation site prediction tools, predHydroxy and RF-Hydroxysite 25 , 36 . Briefly, 8 indices describing various physicochemical properties corresponding to 8 groups were generated by grouping 544 associated amino acid properties in the AAIndex database using fuzzy clustering 43 .…”

“…Despite the significant progress that has been made over the past two years, there is still room for improvement in the performance of existing sulfenylation site prediction tools. For instance, many of the existing sulfenylation site prediction tools exhibit relatively low MCC scores compared to prediction tools for other posttranslational modifications, such as phosphorylation 24 , hydroxylation 25 and glycosylation 26 . While this is likely a function of the size of datasets available for training and/or the mode of modification ( i.e ., enzyme-mediated modification for phosphorylation, hydroxylation and glycosylation versus predominantly non-enzymatic modification for sulfenylation), it is also likely that other factors contribute to the relatively low MCC scores.…”

Faulty oxygen sensing disrupts angiomotin function in trophoblast cell migration and predisposes to preeclampsia

“…In vitro JMJD6 hydroxylation reaction. Protein sequences for AMOT 130 (NCBI Ref Seq: NP_001106962.1) and AMOT 80 (NCBI Ref Seq: NP_573572.1) were input into in silico RF-Hydroxysite Prediction software in FASTA format (39), and the probability of lysine hydroxylation of AMOT was assessed. The following parameters were set in the search: Residue = Lysine (K); Window size = 15; Score threshold = 0.6.…”