Kinase-specific Phosphorylation Sites Research Articles

GPS 6.0: an updated server for prediction of kinase-specific phosphorylation sites in proteins.

Protein phosphorylation, catalyzed by protein kinases (PKs), is one of the most important post-translational modifications (PTMs), and involved in regulating almost all of biological processes. Here, we report an updated server, Group-based Prediction System (GPS) 6.0, for prediction of PK-specific phosphorylation sites (p-sites) in eukaryotes. First, we pre-trained a general model using penalized logistic regression (PLR), deep neural network (DNN), and Light Gradient Boosting Machine (LightGMB) on 490762 non-redundant p-sites in 71407 proteins. Then, transfer learning was conducted to obtain 577 PK-specific predictors at the group, family and single PK levels, using a well-curated data set of 30043 known site-specific kinase-substrate relations in 7041 proteins. Together with the evolutionary information, GPS 6.0 could hierarchically predict PK-specific p-sites for 44046 PKs in 185 species. Besides the basic statistics, we also offered the knowledge from 22 public resources to annotate the prediction results, including the experimental evidence, physical interactions, sequence logos, and p-sites in sequences and 3D structures. The GPS 6.0 server is freely available at https://gps.biocuckoo.cn. We believe that GPS 6.0 could be a highly useful service for further analysis of phosphorylation.

GPS 6.0: an updated server for prediction of kinase-specific phosphorylation sites in proteins

GPS 6.0: an updated server for prediction of kinase-specific phosphorylation sites in proteins

Holistic similarity-based prediction of phosphorylation sites for understudied kinases.

Phosphorylation is an essential mechanism for regulating protein activities. Determining kinase-specific phosphorylation sites by experiments involves time-consuming and expensive analyzes. Although several studies proposed computational methods to model kinase-specific phosphorylation sites, they typically required abundant experimentally verified phosphorylation sites to yield reliable predictions. Nevertheless, the number of experimentally verified phosphorylation sites for most kinases is relatively small, and the targeting phosphorylation sites are still unidentified for some kinases. In fact, there is little research related to these understudied kinases in the literature. Thus, this study aims to create predictive models for these understudied kinases. A kinase-kinase similarity network was generated by merging the sequence-, functional-, protein-domain- and 'STRING'-related similarities. Thus, besides sequence data, protein-protein interactions and functional pathways were also considered to aid predictive modelling. This similarity network was then integrated with a classification of kinase groups to yield highly similar kinases to a specific understudied type of kinase. Their experimentally verified phosphorylation sites were leveraged as positive sites to train predictive models. The experimentally verified phosphorylation sites of the understudied kinase were used for validation. Results demonstrate that 82 out of 116 understudied kinases were predicted with adequate performance via the proposed modelling strategy, achieving a balanced accuracy of 0.81, 0.78, 0.84, 0.84, 0.85, 0.82, 0.90, 0.82 and 0.85, for the 'TK', 'Other', 'STE', 'CAMK', 'TKL', 'CMGC', 'AGC', 'CK1' and 'Atypical' groups, respectively. Therefore, this study demonstrates that web-like predictive networks can reliably capture the underlying patterns in such understudied kinases by harnessing relevant sources of similarities to predict their specific phosphorylation sites.

KinasePhos 3.0: Redesign and Expansion of the Prediction on Kinase-specific Phosphorylation Sites

The purpose of this work is to enhance KinasePhos, a machine learning-based kinase-specific phosphorylation site prediction tool. Experimentally verified kinase-specific phosphorylation data were collected from PhosphoSitePlus, UniProtKB, the GPS 5.0, and Phospho.ELM. In total, 41,421 experimentally verified kinase-specific phosphorylation sites were identified. A total of 1380 unique kinases were identified, including 753 with existing classification information from KinBase and the remaining 627 annotated by building a phylogenetic tree. Based on this kinase classification, a total of 771 predictive models were built at the individual, family, and group levels, using at least 15 experimentally verified substrate sites in positive training datasets. The improved models demonstrated their effectiveness compared with other prediction tools. For example, the prediction of sites phosphorylated by the protein kinase B, casein kinase 2, and protein kinase A families had accuracies of 94.5%, 92.5%, and 90.0%, respectively. The average prediction accuracy for all 771 models was 87.2%. For enhancing interpretability, the SHapley Additive exPlanations (SHAP) method was employed to assess feature importance. The web interface of KinasePhos 3.0 has been redesigned to provide comprehensive annotations of kinase-specific phosphorylation sites on multiple proteins. Additionally, considering the large scale of phosphoproteomic data, a downloadable prediction tool is available at https://awi.cuhk.edu.cn/KinasePhos/download.html or https://github.com/tom-209/KinasePhos-3.0-executable-file.

A Pretrained ELECTRA Model for Kinase-Specific Phosphorylation Site Prediction.

Phosphorylation plays a vital role in signal transduction and cell cycle. Identifying and understanding phosphorylation through machine-learning methods has a long history. However, existing methods only learn representations of a protein sequence segment from a labeled dataset itself, which could result in biased or incomplete features, especially for kinase-specific phosphorylation site prediction in which training data are typically sparse. To learn a comprehensive contextual representation of a protein sequence segment for kinase-specific phosphorylation site prediction, we pretrained our model from over 24 million unlabeled sequence fragments using ELECTRA (Efficiently Learning an Encoder that Classifies Token Replacements Accurately). The pretrained model was applied to kinase-specific site prediction of kinases CDK, PKA, CK2, MAPK, and PKC. The pretrained ELECTRA model achieves 9.02% improvement over BERT and 11.10% improvement over MusiteDeep in the area under the precision-recall curve on the benchmark data.

PhosIDN: an integrated deep neural network for improving protein phosphorylation site prediction by combining sequence and protein-protein interaction information.

MotivationPhosphorylation is one of the most studied post-translational modifications, which plays a pivotal role in various cellular processes. Recently, deep learning methods have achieved great success in prediction of phosphorylation sites, but most of them are based on convolutional neural network that may not capture enough information about long-range dependencies between residues in a protein sequence. In addition, existing deep learning methods only make use of sequence information for predicting phosphorylation sites, and it is highly desirable to develop a deep learning architecture that can combine heterogeneous sequence and protein–protein interaction (PPI) information for more accurate phosphorylation site prediction. ResultsWe present a novel integrated deep neural network named PhosIDN, for phosphorylation site prediction by extracting and combining sequence and PPI information. In PhosIDN, a sequence feature encoding sub-network is proposed to capture not only local patterns but also long-range dependencies from protein sequences. Meanwhile, useful PPI features are also extracted in PhosIDN by a PPI feature encoding sub-network adopting a multi-layer deep neural network. Moreover, to effectively combine sequence and PPI information, a heterogeneous feature combination sub-network is introduced to fully exploit the complex associations between sequence and PPI features, and their combined features are used for final prediction. Comprehensive experiment results demonstrate that the proposed PhosIDN significantly improves the prediction performance of phosphorylation sites and compares favorably with existing general and kinase-specific phosphorylation site prediction methods.Availability and implementationPhosIDN is freely available at https://github.com/ustchangyuanyang/PhosIDN.Supplementary information Supplementary data are available at Bioinformatics online.

DeepPS: a transformer model for predicting general and kinase-specific phosphorylation sites

DeepPS: a transformer model for predicting general and kinase-specific phosphorylation sites

GPS 5.0: An Update on the Prediction of Kinase-specific Phosphorylation Sites in Proteins

In eukaryotes, protein phosphorylation is specifically catalyzed by numerous protein kinases (PKs), faithfully orchestrates various biological processes, and reversibly determines cellular dynamics and plasticity. Here we report an updated algorithm of Group-based Prediction System (GPS) 5.0 to improve the performance for predicting kinase-specific phosphorylation sites (p-sites). Two novel methods, position weight determination (PWD) and scoring matrix optimization (SMO), were developed. Compared with other existing tools, GPS 5.0 exhibits a highly competitive accuracy. Besides serine/threonine or tyrosine kinases, GPS 5.0 also supports the prediction of dual-specificity kinase-specific p-sites. In the classical module of GPS 5.0, 617 individual predictors were constructed for predicting p-sites of 479 human PKs. To extend the application of GPS 5.0, a species-specific module was implemented to predict kinase-specific p-sites for 44,795 PKs in 161 eukaryotes. The online service and local packages of GPS 5.0 are freely available for academic research at http://gps.biocuckoo.cn.

Methylation determines the extracellular calcium sensitivity of the leak channel NALCN in hippocampal dentate granule cells

The sodium leak channel NALCN is a key player in establishing the resting membrane potential (RMP) in neurons and transduces changes in extracellular Ca2+ concentration ([Ca2+]e) into increased neuronal excitability as the downstream effector of calcium-sensing receptor (CaSR). Gain-of-function mutations in the human NALCN gene cause encephalopathy and severe intellectual disability. Thus, understanding the regulatory mechanisms of NALCN is important for both basic and translational research. This study reveals a novel mechanism for NALCN regulation by arginine methylation. Hippocampal dentate granule cells in protein arginine methyltransferase 7 (PRMT7)-deficient mice display a depolarization of the RMP, decreased threshold currents, and increased excitability compared to wild-type neurons. Electrophysiological studies combined with molecular analysis indicate that enhanced NALCN activities contribute to hyperexcitability in PRMT7−/− neurons. PRMT7 depletion in HEK293T cells increases NALCN activity by shifting the dose-response curve of NALCN inhibition by [Ca2+]e without affecting NALCN protein levels. In vitro methylation studies show that PRMT7 methylates a highly conserved Arg1653 of the NALCN gene located in the carboxy-terminal region that is implicated in CaSR-mediated regulation. A kinase-specific phosphorylation site prediction program shows that the adjacent Ser1652 is a potential phosphorylation site. Consistently, our data from site-specific mutants and PKC inhibitors suggest that Arg1653 methylation might modulate Ser1652 phosphorylation mediated by CaSR/PKC-delta, leading to [Ca2+]e-mediated NALCN suppression. Collectively, these data suggest that PRMT7 deficiency decreases NALCN methylation at Arg1653, which, in turn, decreases CaSR/PKC-mediated Ser1652 phosphorylation, lifting NALCN inhibition, thereby enhancing neuronal excitability. Thus, PRMT7-mediated NALCN inhibition provides a potential target for the development of therapeutic tools for neurological diseases.

DeepPhos: prediction of protein phosphorylation sites with deep learning.

MotivationPhosphorylation is the most studied post-translational modification, which is crucial for multiple biological processes. Recently, many efforts have been taken to develop computational predictors for phosphorylation site prediction, but most of them are based on feature selection and discriminative classification. Thus, it is useful to develop a novel and highly accurate predictor that can unveil intricate patterns automatically for protein phosphorylation sites.ResultsIn this study we present DeepPhos, a novel deep learning architecture for prediction of protein phosphorylation. Unlike multi-layer convolutional neural networks, DeepPhos consists of densely connected convolutional neuron network blocks which can capture multiple representations of sequences to make final phosphorylation prediction by intra block concatenation layers and inter block concatenation layers. DeepPhos can also be used for kinase-specific prediction varying from group, family, subfamily and individual kinase level. The experimental results demonstrated that DeepPhos outperforms competitive predictors in general and kinase-specific phosphorylation site prediction.Availability and implementationThe source code of DeepPhos is publicly deposited at https://github.com/USTCHIlab/DeepPhos.Supplementary information Supplementary data are available at Bioinformatics online.

Quokka: a comprehensive tool for rapid and accurate prediction of kinase family-specific phosphorylation sites in the human proteome

Kinase-regulated phosphorylation is a ubiquitous type of post-translational modification (PTM) in both eukaryotic and prokaryotic cells. Phosphorylation plays fundamental roles in many signalling pathways and biological processes, such as protein degradation and protein-protein interactions. Experimental studies have revealed that signalling defects caused by aberrant phosphorylation are highly associated with a variety of human diseases, especially cancers. In light of this, a number of computational methods aiming to accurately predict protein kinase family-specific or kinase-specific phosphorylation sites have been established, thereby facilitating phosphoproteomic data analysis. In this work, we present Quokka, a novel bioinformatics tool that allows users to rapidly and accurately identify human kinase family-regulated phosphorylation sites. Quokka was developed by using a variety of sequence scoring functions combined with an optimized logistic regression algorithm. We evaluated Quokka based on well-prepared up-to-date benchmark and independent test datasets, curated from the Phospho.ELM and UniProt databases, respectively. The independent test demonstrates that Quokka improves the prediction performance compared with state-of-the-art computational tools for phosphorylation prediction. In summary, our tool provides users with high-quality predicted human phosphorylation sites for hypothesis generation and biological validation. The Quokka webserver and datasets are freely available at http://quokka.erc.monash.edu/. Supplementary data are available at Bioinformatics online.

PhosContext2vec: a distributed representation of residue-level sequence contexts and its application to general and kinase-specific phosphorylation site prediction

Phosphorylation is the most important type of protein post-translational modification. Accordingly, reliable identification of kinase-mediated phosphorylation has important implications for functional annotation of phosphorylated substrates and characterization of cellular signalling pathways. The local sequence context surrounding potential phosphorylation sites is considered to harbour the most relevant information for phosphorylation site prediction models. However, currently there is a lack of condensed vector representation for this important contextual information, despite the presence of varying residue-level features that can be constructed from sequence homology profiles, structural information, and physicochemical properties. To address this issue, we present PhosContext2vec which is a distributed representation of residue-level sequence contexts for potential phosphorylation sites and demonstrate its application in both general and kinase-specific phosphorylation site predictions. Benchmarking experiments indicate that PhosContext2vec could achieve promising predictive performance compared with several other existing methods for phosphorylation site prediction. We envisage that PhosContext2vec, as a new sequence context representation, can be used in combination with other informative residue-level features to improve the classification performance in a number of related bioinformatics tasks that require appropriate residue-level feature vector representation and extraction. The web server of PhosContext2vec is publicly available at http://phoscontext2vec.erc.monash.edu/.

Computational Prediction and Analysis for Tyrosine Post-Translational Modifications via Elastic Net.

The tyrosine residue has been identified as suffering three major post-translational modifications (PTMs) including nitration, sulfation, and phosphorylation, which could be involved in different physiological and pathological processes. Multiple tyrosine residues of the whole protein may be modified concurrently, where PTM of a single tyrosine may affect modification of other neighboring tyrosine residues. Hence, it is significant and beneficial to predict nitration, sulfation, and phosphorylation of tyrosine residues in the whole protein sequence. Here, we introduce elastic net to perform feature selection and develop a predictor named TyrPred for predicting nitrotyrosine, sulfotyrosine, and kinase-specific tyrosine phosphorylation sites on the basis of support vector machine. We critically evaluate the performance of TyrPred and compare it with other existing tools. The satisfying results show that using elastic net to mine important features for training can considerably improve the prediction performance. Feature optimization indicates that evolutionary information is significant and contributes to the prediction model. The online tool is established at http://computbiol.ncu.edu.cn/TyrPred . We anticipate that TyrPred can provide useful complements to the existing approaches in this field.

MusiteDeep: a deep-learning framework for general and kinase-specific phosphorylation site prediction.

Computational methods for phosphorylation site prediction play important roles in protein function studies and experimental design. Most existing methods are based on feature extraction, which may result in incomplete or biased features. Deep learning as the cutting-edge machine learning method has the ability to automatically discover complex representations of phosphorylation patterns from the raw sequences, and hence it provides a powerful tool for improvement of phosphorylation site prediction. We present MusiteDeep, the first deep-learning framework for predicting general and kinase-specific phosphorylation sites. MusiteDeep takes raw sequence data as input and uses convolutional neural networks with a novel two-dimensional attention mechanism. It achieves over a 50% relative improvement in the area under the precision-recall curve in general phosphorylation site prediction and obtains competitive results in kinase-specific prediction compared to other well-known tools on the benchmark data. MusiteDeep is provided as an open-source tool available at https://github.com/duolinwang/MusiteDeep. xudong@missouri.edu. Supplementary data are available at Bioinformatics online.

PhosphoPredict: A bioinformatics tool for prediction of human kinase-specific phosphorylation substrates and sites by integrating heterogeneous feature selection

Protein phosphorylation is a major form of post-translational modification (PTM) that regulates diverse cellular processes. In silico methods for phosphorylation site prediction can provide a useful and complementary strategy for complete phosphoproteome annotation. Here, we present a novel bioinformatics tool, PhosphoPredict, that combines protein sequence and functional features to predict kinase-specific substrates and their associated phosphorylation sites for 12 human kinases and kinase families, including ATM, CDKs, GSK-3, MAPKs, PKA, PKB, PKC, and SRC. To elucidate critical determinants, we identified feature subsets that were most informative and relevant for predicting substrate specificity for each individual kinase family. Extensive benchmarking experiments based on both five-fold cross-validation and independent tests indicated that the performance of PhosphoPredict is competitive with that of several other popular prediction tools, including KinasePhos, PPSP, GPS, and Musite. We found that combining protein functional and sequence features significantly improves phosphorylation site prediction performance across all kinases. Application of PhosphoPredict to the entire human proteome identified 150 to 800 potential phosphorylation substrates for each of the 12 kinases or kinase families. PhosphoPredict significantly extends the bioinformatics portfolio for kinase function analysis and will facilitate high-throughput identification of kinase-specific phosphorylation sites, thereby contributing to both basic and translational research programs.

Disease-associated extracellular loop mutations in the adhesion G protein-coupled receptor G1 (ADGRG1; GPR56) differentially regulate downstream signaling

Mutations to the adhesion G protein-coupled receptor ADGRG1 (G1; also known as GPR56) underlie the neurological disorder bilateral frontoparietal polymicrogyria. Disease-associated mutations in G1 studied to date are believed to induce complete loss of receptor function through disruption of either receptor trafficking or signaling activity. Given that N-terminal truncation of G1 and other adhesion G protein-coupled receptors has been shown to significantly increase the receptors' constitutive signaling, we examined two different bilateral frontoparietal polymicrogyria-inducing extracellular loop mutations (R565W and L640R) in the context of both full-length and N-terminally truncated (ΔNT) G1. Interestingly, we found that these mutations reduced surface expression of full-length G1 but not G1-ΔNT in HEK-293 cells. Moreover, the mutations ablated receptor-mediated activation of serum response factor luciferase, a classic measure of Gα12/13-mediated signaling, but had no effect on G1-mediated signaling to nuclear factor of activated T cells (NFAT) luciferase. Given these differential signaling results, we sought to further elucidate the pathway by which G1 can activate NFAT luciferase. We found no evidence that ΔNT activation of NFAT is dependent on Gαq/11-mediated or β-arrestin-mediated signaling but rather involves liberation of Gβγ subunits and activation of calcium channels. These findings reveal that disease-associated mutations to the extracellular loops of G1 differentially alter receptor trafficking, depending on the presence of the N terminus, and differentially alter signaling to distinct downstream pathways.

Prediction of kinase-specific phosphorylation sites through an integrative model of protein context and sequence

Identifying kinase substrates and the specific phosphorylation sites they regulate is an important factor in understanding protein function regulation and signalling pathways. Computational prediction of kinase targets – assigning kinases to putative substrates, and selecting from protein sequence the sites that kinases can phosphorylate – requires the consideration of both the cellular context that kinases operate in, as well as their binding affinity. This consideration enables investigation of how phosphorylation influences a range of biological processes.We report here a novel probabilistic model for classifying kinase-specific phosphorylation sites from sequence across three model organisms: human, mouse and yeast. The model incorporates position-specific amino acid frequencies, and counts of co-occurring amino acids from kinase binding sites. We show how this model can be seamlessly integrated with protein interactions and cell-cycle abundance profiles. When evaluating the prediction accuracy of our method, PhosphoPICK, on an independent hold-out set of kinase-specific phosphorylation sites, it achieved an average specificity of 97%, with 32% sensitivity. We compared PhosphoPICK's ability, through cross-validation, to predict kinase-specific phosphorylation sites with alternative methods, and show that at high levels of specificity PhosphoPICK obtains greater sensitivity for most comparisons made.We investigated the relationship between kinase-specific phosphorylation sites and nuclear localisation signals. We show that kinases PKA, Akt1 and AurB have an over-representation of predicted binding sites at particular positions downstream from predicted nuclear localisation signals, demonstrating an important role for these kinases in regulating the nuclear import of proteins.PhosphoPICK is freely available as a web-service at http://bioinf.scmb.uq.edu.au/phosphopick.

PhosphoPICK: Predicting kinase-specific phosphorylation sites through protein context and sequence

PhosphoPICK: Predicting kinase-specific phosphorylation sites through protein context and sequence

A grammar inference approach for predicting kinase specific phosphorylation sites.

Kinase mediated phosphorylation site detection is the key mechanism of post translational mechanism that plays an important role in regulating various cellular processes and phenotypes. Many diseases, like cancer are related with the signaling defects which are associated with protein phosphorylation. Characterizing the protein kinases and their substrates enhances our ability to understand the mechanism of protein phosphorylation and extends our knowledge of signaling network; thereby helping us to treat such diseases. Experimental methods for predicting phosphorylation sites are labour intensive and expensive. Also, manifold increase of protein sequences in the databanks over the years necessitates the improvement of high speed and accurate computational methods for predicting phosphorylation sites in protein sequences. Till date, a number of computational methods have been proposed by various researchers in predicting phosphorylation sites, but there remains much scope of improvement. In this communication, we present a simple and novel method based on Grammatical Inference (GI) approach to automate the prediction of kinase specific phosphorylation sites. In this regard, we have used a popular GI algorithm Alergia to infer Deterministic Stochastic Finite State Automata (DSFA) which equally represents the regular grammar corresponding to the phosphorylation sites. Extensive experiments on several datasets generated by us reveal that, our inferred grammar successfully predicts phosphorylation sites in a kinase specific manner. It performs significantly better when compared with the other existing phosphorylation site prediction methods. We have also compared our inferred DSFA with two other GI inference algorithms. The DSFA generated by our method performs superior which indicates that our method is robust and has a potential for predicting the phosphorylation sites in a kinase specific manner.

Benchmarking multiple fragmentation methods on an orbitrap fusion for top-down phospho-proteoform characterization.

Top-down analysis of intact proteins by mass spectrometry provides an ideal platform for comprehensive proteoform characterization, in particular, for the identification and localization of post-translational modifications (PTM) co-occurring on a protein. One of the main bottlenecks in top-down proteomics is insufficient protein sequence coverage caused by incomplete protein fragmentation. Based on previous work on peptides, increasing sequence coverage and PTM localization by combining sequential ETD and HCD fragmentation in a single fragmentation event, we hypothesized that protein sequence coverage and phospho-proteoform characterization could be equally improved by this new dual fragmentation method termed EThcD, recently been made available on the Orbitrap Fusion. Here, we systematically benchmark the performance of several (hybrid) fragmentation methods for intact protein analysis on an Orbitrap Fusion, using as a model system a 17.5 kDa N-terminal fragment of the mitotic regulator Bora. During cell division Bora becomes multiply phosphorylated by a variety of cell cycle kinases, including Aurora A and Plk1, albeit at distinctive sites. Here, we monitor the phosphorylation of Bora by Aurora A and Plk1, analyzing the generated distinctive phospho-proteoforms by top-down fragmentation. We show that EThcD and ETciD on a Fusion are feasible and capable of providing richer fragmentation spectra compared to HCD or ETD alone, increasing protein sequence coverage, and thereby facilitating phosphosite localization and the determination of kinase specific phosphorylation sites in these phospho-proteoforms. Data are available via ProteomeXchange with identifier PXD001845.