Lysine acetylation sites prediction using an ensemble of support vector machine classifiers

Lysine acetylation is an essentially reversible and high regulated post-translational modification which regulates diverse protein properties. Experimental identification of acetylation sites is laborious and expensive. Hence, there is significant interest in the development of computational methods for reliable prediction of acetylation sites from amino acid sequences. In this paper we use an ensemble of support vector machine classifiers to perform this work. The experimentally determined acetylation lysine sites are extracted from Swiss-Prot database and scientific literatures. Experiment results show that an ensemble of support vector machine classifiers outperforms single support vector machine classifier and other computational methods such as PAIL and LysAcet on the problem of predicting acetylation lysine sites. The resulting method has been implemented in EnsemblePail, a web server for lysine acetylation sites prediction available at http://www.aporc.org/EnsemblePail/.     

Coupling dynamics and evolutionary information with structure to identify protein regulatory and functional binding sites

Binding sites in proteins can be either specifically functional binding sites (active sites) that bind specific substrates with high affinity or regulatory binding sites (allosteric sites), that modulate the activity of functional binding sites through effector molecules. Owing to their significance in determining protein function, the identification of protein functional and regulatory binding sites is widely acknowledged as an important biological problem. In this work, we present a novel binding site prediction method, Active and Regulatory site Prediction (AR-Pred), which supplements protein geometry, evolutionary, and physicochemical features with information about protein dynamics to predict putative active and allosteric site residues. As the intrinsic dynamics of globular proteins plays an essential role in controlling binding events, we find it to be an important feature for the identification of protein binding sites. We train and validate our predictive models on multiple balanced training and validation sets with random forest machine learning and obtain an ensemble of discrete models for each prediction type. Our models for active site prediction yield a median area under the curve (AUC) of 91% and Matthews correlation coefficient (MCC) of 0.68, whereas the less well-defined allosteric sites are predicted at a lower level with a median AUC of 80% and MCC of 0.48. When tested on an independent set of proteins, our models for active site prediction show comparable performance to two existing methods and gains compared to two others, while the allosteric site models show gains when tested against three existing prediction methods. AR-Pred is available as a free downloadable package at https://github.com/sambitmishra0628/AR-PRED_source .     

GPS-YNO2: computational prediction of tyrosine nitration sites in proteins

The last decade has witnessed rapid progress in the identification of protein tyrosine nitration (PTN), which is an essential and ubiquitous post-translational modification (PTM) that plays a variety of important roles in both physiological and pathological processes, such as the immune response, cell death, aging and neurodegeneration. Identification of site-specific nitrated substrates is fundamental for understanding the molecular mechanisms and biological functions of PTN. In contrast with labor-intensive and time-consuming experimental approaches, here we report the development of the novel software package GPS-YNO2 to predict PTN sites. The software demonstrated a promising accuracy of 76.51%, a sensitivity of 50.09% and a specificity of 80.18% from the leave-one-out validation. As an example application, we predicted potential PTN sites for hundreds of nitrated substrates which had been experimentally detected in small-scale or large-scale studies, even though the actual nitration sites had still not been determined. Through a statistical functional comparison with the nitric oxide (NO) dependent reversible modification of S-nitrosylation, we observed that PTN prefers to attack certain fundamental biological processes and functions. These prediction and analysis results might be helpful for further experimental investigation. Finally, the online service and local packages of GPS-YNO2 1.0 were implemented in JAVA and freely available at: .     

GPS: a novel group-based phosphorylation predicting and scoring method

Protein phosphorylation is an important reversible post-translational modification of proteins, and it orchestrates a variety of cellular processes. Experimental identification of phosphorylation site is labor-intensive and often limited by the availability and optimization of enzymatic reaction. In silico prediction may facilitate the identification of potential phosphorylation sites with ease. Here we present a novel computational method named GPS: group-based phosphorylation site predicting and scoring platform. If two polypeptides differ by only two consecutive amino acids, in particular when the two different amino acids are a conserved pair, e.g., isoleucine (I) and valine (V), or serine (S) and threonine (T), we view these two polypeptides bearing similar 3D structures and biochemical properties. Based on this rationale, we formulated GPS that carries greater computational power with superior performance compared to two existing phosphorylation sites prediction systems, ScanSite 2.0 and PredPhospho. With database in public domain, GPS can predict substrate phosphorylation sites from 52 different protein kinase (PK) families while ScanSite 2.0 and PredPhospho offer at most 30 PK families. Using PKA as a model enzyme, we first compared prediction profiles from the GPS method with those from ScanSite 2.0 and PredPhospho. In addition, we chose an essential mitotic kinase Aurora-B as a model enzyme since ScanSite 2.0 and PredPhospho offer no prediction. However, GPS offers satisfactory sensitivity (94.44%) and specificity (97.14%). Finally, the accuracy of phosphorylation on MCAK predicted by GPS was validated by experimentation, in which six out of seven predicted potential phosphorylation sites on MCAK (Q91636) were experimentally verified. Taken together, we have generated a novel method to predict phosphorylation sites, which offers greater precision and computing power over ScanSite 2.0 and PredPhospho.     

SUMOhydro: a novel method for the prediction of sumoylation sites based on hydrophobic properties

Sumoylation is one of the most essential mechanisms of reversible protein post-translational modifications and is a crucial biochemical process in the regulation of a variety of important biological functions. Sumoylation is also closely involved in various human diseases. The accurate computational identification of sumoylation sites in protein sequences aids in experimental design and mechanistic research in cellular biology. In this study, we introduced amino acid hydrophobicity as a parameter into a traditional binary encoding scheme and developed a novel sumoylation site prediction tool termed SUMOhydro. With the assistance of a support vector machine, the proposed method was trained and tested using a stringent non-redundant sumoylation dataset. In a leave-one-out cross-validation, the proposed method yielded an excellent performance with a correlation coefficient, specificity, sensitivity and accuracy equal to 0.690, 98.6%, 71.1% and 97.5%, respectively. In addition, SUMOhydro has been benchmarked against previously described predictors based on an independent dataset, thereby suggesting that the introduction of hydrophobicity as an additional parameter could assist in the prediction of sumoylation sites. Currently, SUMOhydro is freely accessible at http://protein.cau.edu.cn/others/SUMOhydro/.     

GPS-CCD: a novel computational program for the prediction of calpain cleavage sites

As one of the most essential post-translational modifications (PTMs) of proteins, proteolysis, especially calpain-mediated cleavage, plays an important role in many biological processes, including cell death/apoptosis, cytoskeletal remodeling, and the cell cycle. Experimental identification of calpain targets with bona fide cleavage sites is fundamental for dissecting the molecular mechanisms and biological roles of calpain cleavage. In contrast to time-consuming and labor-intensive experimental approaches, computational prediction of calpain cleavage sites might more cheaply and readily provide useful information for further experimental investigation. In this work, we constructed a novel software package of GPS-CCD (Calpain Cleavage Detector) for the prediction of calpain cleavage sites, with an accuracy of 89.98%, sensitivity of 60.87% and specificity of 90.07%. With this software, we annotated potential calpain cleavage sites for hundreds of calpain substrates, for which the exact cleavage sites had not been previously determined. In this regard, GPS-CCD 1.0 is considered to be a useful tool for experimentalists. The online service and local packages of GPS-CCD 1.0 were implemented in JAVA and are freely available at: http://ccd.biocuckoo.org/.     

FTSite: high accuracy detection of ligand binding sites on unbound protein structures

MOTIVATION: Binding site identification is a classical problem that is important for a range of applications, including the structure-based prediction of function, the elucidation of functional relationships among proteins, protein engineering and drug design. We describe an accurate method of binding site identification, namely FTSite. This method is based on experimental evidence that ligand binding sites also bind small organic molecules of various shapes and polarity. The FTSite algorithm does not rely on any evolutionary or statistical information, but achieves near experimental accuracy: it is capable of identifying the binding sites in over 94% of apo proteins from established test sets that have been used to evaluate many other binding site prediction methods. AVAILABILITY: FTSite is freely available as a web-based server at http://ftsite.bu.edu.     

Mass spectrometric identification of novel lysine acetylation sites in huntingtin

Huntingtin (Htt) is a protein with a polyglutamine stretch in the N-terminus and expansion of the polyglutamine stretch causes Huntington's disease (HD). Htt is a multiple domain protein whose function has not been well characterized. Previous reports have shown, however, that post-translational modifications of Htt such as phosphorylation and acetylation modulate mutant Htt toxicity, localization, and vesicular trafficking. Lysine acetylation of Htt is of particular importance in HD as this modification regulates disease progression and toxicity. Treatment of mouse models with histone deacetylase inhibitors ameliorates HD-like symptoms and alterations in acetylation of Htt promotes clearance of the protein. Given the importance of acetylation in HD and other diseases, we focused on the systematic identification of lysine acetylation sites in Htt23Q (1-612) in a cell culture model using mass spectrometry. Myc-tagged Htt23Q (1-612) overexpressed in the HEK 293T cell line was immunoprecipitated, separated by SDS-PAGE, digested and subjected to high performance liquid chromatography tandem MS analysis. Five lysine acetylation sites were identified, including three novel sites Lys-178, Lys-236, Lys-345 and two previously described sites Lys-9 and Lys-444. Antibodies specific to three of the Htt acetylation sites were produced and confirmed the acetylation sites in Htt. A multiple reaction monitoring MS assay was developed to compare quantitatively the Lys-178 acetylation level between wild-type Htt23Q and mutant Htt148Q (1-612). This report represents the first comprehensive mapping of lysine acetylation sites in N-terminal region of Htt.     

DeepNitro: Prediction of Protein Nitration and Nitrosylation Sites by Deep Learning

Protein nitration and nitrosylation are essential post-translational modifications(PTMs)involved in many fundamental cellular processes. Recent studies have revealed that excessive levels of nitration and nitrosylation in some critical proteins are linked to numerous chronic diseases.Therefore, the identification of substrates that undergo such modifications in a site-specific manner is an important research topic in the community and will provide candidates for targeted therapy. In this study, we aimed to develop a computational tool for predicting nitration and nitrosylation sites in proteins. We first constructed four types of encoding features, including positional amino acid distributions, sequence contextual dependencies, physicochemical properties, and position-specificscoring features, to represent the modified residues. Based on these encoding features, we established a predictor called DeepNitro using deep learning methods for predicting protein nitration and nitrosylation. Using n-fold cross-validation, our evaluation shows great AUC values for DeepNitro, 0.65 for tyrosine nitration, 0.80 for tryptophan nitration, and 0.70 for cysteine nitrosylation, respectively,demonstrating the robustness and reliability of our tool. Also, when tested in the independent dataset, DeepNitro is substantially superior to other similar tools with a 7%à42% improvement in the prediction performance. Taken together, the application of deep learning method and novel encoding schemes, especially the position-specific scoring feature, greatly improves the accuracy of nitration and nitrosylation site prediction and may facilitate the prediction of other PTM sites. DeepNitro is implemented in JAVA and PHP and is freely available for academic research at http://deepnitro.renlab.org.     

PRINTR: Prediction of RNA binding sites in proteins using SVM and profiles

Protein–RNA interactions play a key role in a number of biological processes such as protein synthesis, mRNA processing, assembly and function of ribosomes and eukaryotic spliceosomes. A reliable identification of RNA-binding sites in RNA-binding proteins is important for functional annotation and site-directed mutagenesis. We developed a novel method for the prediction of protein residues that interact with RNA using support vector machine (SVM) and position-specific scoring matrices (PSSMs). Two cases have been considered in the prediction of protein residues at RNA-binding surfaces. One is given the sequence information of a protein chain that is known to interact with RNA; the other is given the structural information. Thus, five different inputs have been tested. Coupled with PSI-BLAST profiles and predicted secondary structure, the present approach yields a Matthews correlation coefficient (MCC) of 0.432 by a 7-fold cross-validation, which is the best among all previous reported RNA-binding sites prediction methods. When given the structural information, we have obtained the MCC value of 0.457, with PSSMs, observed secondary structure and solvent accessibility information assigned by DSSP as input. A web server implementing the prediction method is available at the following URL: .     

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

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.     

CSS-Palm: palmitoylation site prediction with a clustering and scoring strategy (CSS)

SUMMARY: Palmitoylation is an important post-translational lipid modification of proteins. Unlike prenylation and myristoylation, palmitoylation is a reversible covalent modification, allowing for dynamic regulation of multiple complex cellular systems. However, in vivo or in vitro identification of palmitoylation sites is usually time-consuming and labor-intensive. So in silico predictions could help to narrow down the possible palmitoylation sites, which can be used to guide further experimental design. Previous studies suggested that there is no unique canonical motif for palmitoylation sites, so we hypothesize that the bona fide pattern might be compromised by heterogeneity of multiple structural determinants with different features. Based on this hypothesis, we partition the known palmitoylation sites into three clusters and score the similarity between the query peptide and the training ones based on BLOSUM62 matrix. We have implemented a computer program for palmitoylation site prediction, Clustering and Scoring Strategy for Palmitoylation Sites Prediction (CSS-Palm) system, and found that the program's prediction performance is encouraging with highly positive Jack-Knife validation results (sensitivity 82.16% and specificity 83.17% for cut-off score 2.6). Our analyses indicate that CSS-Palm could provide a powerful and effective tool to studies of palmitoylation sites. AVAILABILITY: CSS-Palm is implemented in PHP/PERL+MySQL and can be freely accessed at http://bioinformatics.lcd-ustc.org/css_palm/ CONTACT: yaoxb@ustc.edu.cn; xuyn@bmb.uga.edu SUPPLEMENTARY INFORMATION: Supplementary data are available at Bionformatics online.     

Identifying human kinase-specific protein phosphorylation sites by integrating heterogeneous information from various sources

Phosphorylation is an important type of protein post-translational modification. Identification of possible phosphorylation sites of a protein is important for understanding its functions. Unbiased screening for phosphorylation sites by in vitro or in vivo experiments is time consuming and expensive; in silico prediction can provide functional candidates and help narrow down the experimental efforts. Most of the existing prediction algorithms take only the polypeptide sequence around the phosphorylation sites into consideration. However, protein phosphorylation is a very complex biological process in vivo. The polypeptide sequences around the potential sites are not sufficient to determine the phosphorylation status of those residues. In the current work, we integrated various data sources such as protein functional domains, protein subcellular location and protein-protein interactions, along with the polypeptide sequences to predict protein phosphorylation sites. The heterogeneous information significantly boosted the prediction accuracy for some kinase families. To demonstrate potential application of our method, we scanned a set of human proteins and predicted putative phosphorylation sites for Cyclin-dependent kinases, Casein kinase 2, Glycogen synthase kinase 3, Mitogen-activated protein kinases, protein kinase A, and protein kinase C families (available at http://cmbi.bjmu.edu.cn/huphospho). The predicted phosphorylation sites can serve as candidates for further experimental validation. Our strategy may also be applicable for the in silico identification of other post-translational modification substrates.     

Analysis of acetylation stoichiometry suggests that SIRT3 repairs nonenzymatic acetylation lesions

Acetylation is frequently detected on mitochondrial enzymes, and the sirtuin deacetylase SIRT3 is thought to regulate metabolism by deacetylating mitochondrial proteins. However, the stoichiometry of acetylation has not been studied and is important for understanding whether SIRT3 regulates or suppresses acetylation. Using quantitative mass spectrometry, we measured acetylation stoichiometry in mouse liver tissue and found that SIRT3 suppressed acetylation to a very low stoichiometry at its target sites. By examining acetylation changes in the liver, heart, brain, and brown adipose tissue of fasted mice, we found that SIRT3‐targeted sites were mostly unaffected by fasting, a dietary manipulation that is thought to regulate metabolism through SIRT3‐dependent deacetylation. Globally increased mitochondrial acetylation in fasted liver tissue, higher stoichiometry at mitochondrial acetylation sites, and greater sensitivity of SIRT3‐targeted sites to chemical acetylation in vitro and fasting‐induced acetylation in vivo, suggest a nonenzymatic mechanism of acetylation. Our data indicate that most mitochondrial acetylation occurs as a low‐level nonenzymatic protein lesion and that SIRT3 functions as a protein repair factor that removes acetylation lesions from lysine residues.     

Phosphate binding sites identification in protein structures

Nearly half of known protein structures interact with phosphate-containing ligands, such as nucleotides and other cofactors. Many methods have been developed for the identification of metal ions-binding sites and some for bigger ligands such as carbohydrates, but none is yet available for the prediction of phosphate-binding sites. Here we describe Pfinder, a method that predicts binding sites for phosphate groups, both in the form of ions or as parts of other non-peptide ligands, in proteins of known structure. Pfinder uses the Query3D local structural comparison algorithm to scan a protein structure for the presence of a number of structural motifs identified for their ability to bind the phosphate chemical group. Pfinder has been tested on a data set of 52 proteins for which both the apo and holo forms were available. We obtained at least one correct prediction in 63% of the holo structures and in 62% of the apo. The ability of Pfinder to recognize a phosphate-binding site in unbound protein structures makes it an ideal tool for functional annotation and for complementing docking and drug design methods. The Pfinder program is available at http://pdbfun.uniroma2.it/pfinder.     

Identification of lysine acetyltransferase p300 substrates using 4-pentynoyl-coenzyme A and bioorthogonal proteomics

Proteomic studies have identified a plethora of lysine acetylated proteins in eukaryotes and bacteria. Determining the individual lysine acetyltransferases responsible for each protein acetylation mark is crucial for elucidating the underlying regulatory mechanisms, but has been challenging due to limited biochemical methods. Here, we describe the application of a bioorthogonal chemical proteomics method to profile and identify substrates of individual lysine acetyltransferases. Addition of 4-pentynoyl-coenzyme A, an alkynyl chemical reporter for protein acetylation, to cell extracts, together with purified lysine acetyltransferase p300, enabled the fluorescent profiling and identification of protein substrates via Cu(I)-catalyzed alkyne-azide cycloaddition. We identified several known protein substrates of the acetyltransferase p300 as well as the lysine residues that were modified. Interestingly, several new candidate p300 substrates and their sites of acetylation were also discovered using this approach. Our results demonstrate that bioorthogonal chemical proteomics allows the rapid substrate identification of individual protein acetyltransferases in vitro.