PPSP: prediction of PK-specific phosphorylation site with Bayesian decision theory

Identifying Protein Phosphorylation Site-Disease Associations Based on Multi-Similarity Fusion and Negative Sample Selection by Convolutional Neural Network

As one of the most important post-translational modifications (PTMs), protein phosphorylation plays a key role in a variety of biological processes. Many studies have shown that protein phosphorylation is associated with various human diseases. Therefore, identifying protein phosphorylation site-disease associations can help to elucidate the pathogenesis of disease and discover new drug targets. Networks of sequence similarity and Gaussian interaction profile kernel similarity were constructed for phosphorylation sites, as well as networks of disease semantic similarity, disease symptom similarity and Gaussian interaction profile kernel similarity were constructed for diseases. To effectively combine different phosphorylation sites and disease similarity information, random walk with restart algorithm was used to obtain the topology information of the network. Then, the diffusion component analysis method was utilized to obtain the comprehensive phosphorylation site similarity and disease similarity. Meanwhile, the reliable negative samples were screened based on the Euclidean distance method. Finally, a convolutional neural network (CNN) model was constructed to identify potential associations between phosphorylation sites and diseases. Based on tenfold cross-validation, the evaluation indicators were obtained including accuracy of 93.48%, specificity of 96.82%, sensitivity of 90.15%, precision of 96.62%, Matthew's correlation coefficient of 0.8719, area under the receiver operating characteristic curve of 0.9786 and area under the precision-recall curve of 0.9836. Additionally, most of the top 20 predicted disease-related phosphorylation sites (19/20 for Alzheimer's disease; 20/16 for neuroblastoma) were verified by literatures and databases. These results show that the proposed method has an outstanding prediction performance and a high practical value.

In silico analysis of alpha-synuclein protein variants and posttranslational modifications related to Parkinson's disease

Parkinson's disease (PD) is among the most prevalent neurodegenerative disorders, affecting over 10 million people worldwide. The protein encoded by the SNCA gene, alpha-synuclein (ASYN), is the major component of Lewy body (LB) aggregates, a histopathological hallmark of PD. Mutations and posttranslational modifications (PTMs) in ASYN are known to influence protein aggregation and LB formation, possibly playing a crucial role in PD pathogenesis. In this work, we applied computational methods to characterize the effects of missense mutations and PTMs on the structure and function of ASYN. Missense mutations in ASYN were compiled from the literature/databases and underwent a comprehensive predictive analysis. Phosphorylation and SUMOylation sites of ASYN were retrieved from databases and predicted by algorithms. ConSurf was used to estimate the evolutionary conservation of ASYN amino acids. Molecular dynamics (MD) simulations of ASYN wild-type and variants A30G, A30P, A53T, and G51D were performed using the GROMACS package. Seventy-seven missense mutations in ASYN were compiled. Although most mutations were not predicted to affect ASYN stability, aggregation propensity, amyloid formation, and chaperone binding, the analyzed mutations received relatively high rates of deleterious predictions and predominantly occurred at evolutionarily conserved sites within the protein. Moreover, our predictive analyses suggested that the following mutations may be possibly harmful to ASYN and, consequently, potential targets for future investigation: K6N, T22I, K34E, G36R, G36S, V37F, L38P, G41D, and K102E. The MD analyses pointed to remarkable flexibility and essential dynamics alterations at nearly all domains of the studied variants, which could lead to impaired contact between NAC and the C-terminal domain triggering protein aggregation. These alterations may have functional implications for ASYN and provide important insight into the molecular mechanism of PD, supporting the design of future biomedical research and improvements in existing therapies for the disease.

IFI16 phase separation via multi-phosphorylation drives innate immune signaling

The interferon inducible protein 16 (IFI16) is a prominent sensor of nuclear pathogenic DNA, initiating innate immune signaling and suppressing viral transcription. However, little is known about mechanisms that initiate IFI16 antiviral functions or its regulation within the host DNA-filled nucleus. Here, we provide in vitro and in vivo evidence to establish that IFI16 undergoes liquid-liquid phase separation (LLPS) nucleated by DNA. IFI16 binding to viral DNA initiates LLPS and induction of cytokines during herpes simplex virus type 1 (HSV-1) infection. Multiple phosphorylation sites within an intrinsically disordered region (IDR) function combinatorially to activate IFI16 LLPS, facilitating filamentation. Regulated by CDK2 and GSK3β, IDR phosphorylation provides a toggle between active and inactive IFI16 and the decoupling of IFI16-mediated cytokine expression from repression of viral transcription. These findings show how IFI16 switch-like phase transitions are achieved with temporal resolution for immune signaling and, more broadly, the multi-layered regulation of nuclear DNA sensors.

Spastin Promotes the Migration and Invasion Capability of T98G Glioblastoma Cells by Interacting with Pin1 through Its Microtubule-Binding Domain

Microtubule-severing protein Spastin has been shown to co-localize with actin in migratory glioblastoma cells and is linked to glioblastomas' migration and invasion capacity. However, the effectiveness of Spastin in glioblastoma migration and the molecular mechanism underpinning the orientation of Spastin towards actin filaments remain unknown. Here, we demonstrated that Spastin plays an active role in glioblastoma migration by showing a reduced migratory potential of T98G glioblastoma cells using real-time cell analysis (RTCA) in Spastin-depleted cells. Pull-down assays revealed that a cis-trans isomerase Pin1 interacts with Spastin through binding to the phosphorylated Pin1 recognition motifs in the microtubule-binding domain (MBD), and immunocytochemistry analysis showed that interaction with Pin1 directs Spastin to actin filaments in extended cell regions. Consequently, by utilizing RTCA, we proved that the migration and invasion capacity of T98G glioblastoma cells significantly increased with the overexpression of Spastin, of which the Pin1 recognition motifs in MBD are constitutively phosphorylated, while the overexpression of phospho-mutant form did not have a significant effect on migration and invasion of T98G glioblastoma cells. These findings demonstrate that Pin1 is a novel interaction partner of Spastin, and their interaction drives Spastin to actin filaments, allowing Spastin to contribute to the glioblastomas' migration and invasion abilities.

pHisPred: a tool for the identification of histidine phosphorylation sites by integrating amino acid patterns and properties

Background

Protein histidine phosphorylation (pHis) plays critical roles in prokaryotic signal transduction pathways and various eukaryotic cellular processes. It is estimated to account for 6–10% of the phosphoproteome, however only hundreds of pHis sites have been discovered to date. Due to the inherent disadvantages of experimental methods, it is an urgent task for developing efficient computational approaches to identify pHis sites.

Results

Here, we present a novel tool, pHisPred, for accurately identifying pHis sites from protein sequences. We manually collected the largest number of experimental validated pHis sites to build benchmark datasets. Using randomized tenfold CV, the weighted SVM-RBF model shows the best performance than other four commonly used classification models (LR, KNN, RF, and MLP). From ten thousands of features, 140 and 150 most informative features were individually selected out for eukaryotic and prokaryotic models. The average AUC and F1-score values of pHisPred were (0.81, 0.40) and (0.78, 0.46) for tenfold CV on the eukaryotic and prokaryotic training datasets, respectively. In addition, pHisPred significantly outperforms other tools on testing datasets, in particular on the eukaryotic one.

Conclusion

We implemented a python program of pHisPred, which is freely available for non-commercial use at https://github.com/xiaofengsong/pHisPred. Moreover, users can use it to train new models with their own data.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12859-022-04938-x.

Deep Learning-Based Advances In Protein Posttranslational Modification Site and Protein Cleavage Prediction

Posttranslational modification (PTM ) is a ubiquitous phenomenon in both eukaryotes and prokaryotes which gives rise to enormous proteomic diversity. PTM mostly comes in two flavors: covalent modification to polypeptide chain and proteolytic cleavage. Understanding and characterization of PTM is a fundamental step toward understanding the underpinning of biology. Recent advances in experimental approaches, mainly mass-spectrometry-based approaches, have immensely helped in obtaining and characterizing PTMs. However, experimental approaches are not enough to understand and characterize more than 450 different types of PTMs and complementary computational approaches are becoming popular. Recently, due to the various advancements in the field of Deep Learning (DL), along with the explosion of applications of DL to various fields, the field of computational prediction of PTM has also witnessed the development of a plethora of deep learning (DL)-based approaches. In this book chapter, we first review some recent DL-based approaches in the field of PTM site prediction. In addition, we also review the recent advances in the not-so-studied PTM , that is, proteolytic cleavage predictions. We describe advances in PTM prediction by highlighting the Deep learning architecture, feature encoding, novelty of the approaches, and availability of the tools/approaches. Finally, we provide an outlook and possible future research directions for DL-based approaches for PTM prediction.

EMBER: multi-label prediction of kinase-substrate phosphorylation events through deep learning

MOTIVATION

Kinase-catalyzed phosphorylation of proteins forms the backbone of signal transduction within the cell, enabling the coordination of numerous processes such as the cell cycle, apoptosis, and differentiation. Although on the order of 105 phosphorylation events have been described, we know the specific kinase performing these functions for <5% of cases. The ability to predict which kinases initiate specific individual phosphorylation events has the potential to greatly enhance the design of downstream experimental studies, while simultaneously creating a preliminary map of the broader phosphorylation network that controls cellular signaling.

RESULTS

We describe Embedding-based multi-label prediction of phosphorylation events (EMBER), a deep learning method that integrates kinase phylogenetic information and motif-dissimilarity information into a multi-label classification model for the prediction of kinase-motif phosphorylation events. Unlike previous deep learning methods that perform single-label classification, we restate the task of kinase-motif phosphorylation prediction as a multi-label problem, allowing us to train a single unified model rather than a separate model for each of the 134 kinase families. We utilize a Siamese neural network to generate novel vector representations, or an embedding, of peptide motif sequences, and we compare our novel embedding to a previously proposed peptide embedding. Our motif vector representations are used, along with one-hot encoded motif sequences, as input to a classification neural network while also leveraging kinase phylogenetic relationships into our model via a kinase phylogeny-weighted loss function. Results suggest that this approach holds significant promise for improving the known map of phosphorylation relationships that underlie kinome signaling.

AVAILABILITY AND IMPLEMENTATION

The data and code underlying this article are available in a GitHub repository at https://github.com/gomezlab/EMBER.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

TransPhos: A Deep-Learning Model for General Phosphorylation Site Prediction Based on Transformer-Encoder Architecture

Protein phosphorylation is one of the most critical post-translational modifications of proteins in eukaryotes, which is essential for a variety of biological processes. Plenty of attempts have been made to improve the performance of computational predictors for phosphorylation site prediction. However, most of them are based on extra domain knowledge or feature selection. In this article, we present a novel deep learning-based predictor, named TransPhos, which is constructed using a transformer encoder and densely connected convolutional neural network blocks, for predicting phosphorylation sites. Data experiments are conducted on the datasets of PPA (version 3.0) and Phospho. ELM. The experimental results show that our TransPhos performs better than several deep learning models, including Convolutional Neural Networks (CNN), Long-term and short-term memory networks (LSTM), Recurrent neural networks (RNN) and Fully connected neural networks (FCNN), and some state-of-the-art deep learning-based prediction tools, including GPS2.1, NetPhos, PPRED, Musite, PhosphoSVM, SKIPHOS, and DeepPhos. Our model achieves a good performance on the training datasets of Serine (S), Threonine (T), and Tyrosine (Y), with AUC values of 0.8579, 0.8335, and 0.6953 using 10-fold cross-validation tests, respectively, and demonstrates that the presented TransPhos tool considerably outperforms competing predictors in general protein phosphorylation site prediction.

Non-canonical vs. Canonical Functions of Heme Oxygenase-1 in Cancer

Heme oxygenase-1 (HO-1) is a critical stress-responsive enzyme that has antioxidant and anti-inflammatory functions. HO-1 catalyzes heme degradation, which gives rise to the formation of carbon monoxide (CO), biliverdin, and iron. The upregulation of HO-1 under pathological conditions associated with cellular stress represents an important cytoprotective defense mechanism by virtue of the anti-oxidant properties of the bilirubin and the anti-inflammatory effect of the CO produced. The same mechanism is hijacked by premalignant and cancerous cells. In recent years, however, there has been accumulating evidence supporting that the upregulation of HO-1 promotes cancer progression, independently of its catalytic activity. Such non-canonical functions of HO-1 are associated with its interaction with other proteins, particularly transcription factors. HO-1 also undergoes post-translational modifications that influence its stability, functional activity, cellular translocation, etc. HO-1 is normally present in the endoplasmic reticulum, but distinct subcellular localizations, especially in the nucleus, are observed in multiple cancers. The nuclear HO-1 modulates the activation of various transcription factors, which does not appear to be mediated by carbon monoxide and iron. This commentary summarizes the non-canonical functions of HO-1 in the context of cancer growth and progression and underlying regulatory mechanisms.

Non-canonical vs. Canonical Functions of Heme Oxygenase-1 in Cancer

Heme oxygenase-1 (HO-1) is a critical stress-responsive enzyme that has antioxidant and anti-inflammatory functions. HO-1 catalyzes heme degradation, which gives rise to the formation of carbon monoxide (CO), biliverdin, and iron. The upregulation of HO-1 under pathological conditions associated with cellular stress represents an important cytoprotective defense mechanism by virtue of the anti-oxidant properties of the bilirubin and the anti-inflammatory effect of the CO produced. The same mechanism is hijacked by premalignant and cancerous cells. In recent years, however, there has been accumulating evidence supporting that the upregulation of HO-1 promotes cancer progression, independently of its catalytic activity. Such non-canonical functions of HO-1 are associated with its interaction with other proteins, particularly transcription factors. HO-1 also undergoes post-translational modifications that influence its stability, functional activity, cellular translocation, etc. HO-1 is normally present in the endoplasmic reticulum, but distinct subcellular localizations, especially in the nucleus, are observed in multiple cancers. The nuclear HO-1 modulates the activation of various transcription factors, which does not appear to be mediated by carbon monoxide and iron. This commentary summarizes the non-canonical functions of HO-1 in the context of cancer growth and progression and underlying regulatory mechanisms.

Phosphorylation tunes elongation propensity and cohesiveness of INCENP's intrinsically disordered region

The inner centromere protein, INCENP, is crucial for correct chromosome segregation during mitosis. It connects the kinase Aurora B to the inner centromere allowing this kinase to dynamically access its kinetochore targets. However, the function of its central, 440-residue long intrinsically disordered region (IDR) and its multiple phosphorylation sites is unclear. Here, we determined the conformational ensemble of INCENP's IDR, systematically varying the level of phosphorylation, using all-atom and coarse-grain molecular dynamics simulations. Our simulations show that phosphorylation expands INCENP's IDR, both locally and globally, mainly by increasing its overall net charge. The disordered region undergoes critical globule-to-coil conformational transitions and the transition temperature non-monotonically depends on the degree of phosphorylation, with a mildly phosphorylated case of neutral net charge featuring the highest collapse propensity. The IDR transitions from a multitude of globular states, accompanied by several specific internal contacts that reduce INCENP length by loop formation, to weakly interacting and highly extended coiled conformations. Phosphorylation critically shifts the population between these two regimes. It thereby influences cohesiveness and phase behavior of INCENP IDR assemblies, a feature presumably relevant for INCENP's function in the chromosomal passenger complex. Overall, we propose the disordered region of INCENP to act as a phosphorylation-regulated and length-variable component, within the previously defined "dog-leash" model, that thereby regulates how Aurora B reaches its targets for proper chromosome segregation.

PTMdyna: exploring the influence of post-translation modifications on protein conformational dynamics

Protein post-translational modifications (PTM) play vital roles in cellular regulation, modulating functions by driving changes in protein structure and dynamics. Exploring comprehensively the influence of PTM on conformational dynamics can facilitate the understanding of the related biological function and molecular mechanism. Currently, a series of excellent computation tools have been designed to analyze the time-dependent structural properties of proteins. However, the protocol aimed to explore conformational dynamics of post-translational modified protein is still a blank. To fill this gap, we present PTMdyna to visually predict the conformational dynamics differences between unmodified and modified proteins, thus indicating the influence of specific PTM. PTMdyna exhibits an AUC of 0.884 tested on 220 protein-protein complex structures. The case of heterochromatin protein 1α complexed with lysine 9-methylated histone H3, which is critical for genomic stability and cell differentiation, was used to demonstrate its applicability. PTMdyna provides a reliable platform to predict the influence of PTM on protein dynamics, making it easier to interpret PTM functionality at the structure level. The web server is freely available at http://ccbportal.com/PTMdyna.

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

Motivation

Phosphorylation 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.

Results

We 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 implementation

PhosIDN is freely available at https://github.com/ustchangyuanyang/PhosIDN.

Supplementary information

Supplementary data are available at Bioinformatics online.

Computational Phosphorylation Network Reconstruction: An Update on Methods and Resources

Most proteins undergo some form of modification after translation, and phosphorylation is one of the most relevant and ubiquitous post-translational modifications. The succession of protein phosphorylation and dephosphorylation catalyzed by protein kinase and phosphatase, respectively, constitutes a key mechanism of molecular information flow in cellular systems. The protein interactions of kinases, phosphatases, and their regulatory subunits and substrates are the main part of phosphorylation networks. To elucidate the landscape of phosphorylation events has been a central goal pursued by both experimental and computational approaches. Substrate specificity (e.g., sequence, structure) or the phosphoproteome has been utilized in an array of different statistical learning methods to infer phosphorylation networks. In this chapter, different computational phosphorylation network inference-related methods and resources are summarized and discussed.

Mutation in the MICOS subunit gene APOO (MIC26) associated with an X-linked recessive mitochondrial myopathy, lactic acidosis, cognitive impairment and autistic features

BACKGROUND

Mitochondria provide ATP through the process of oxidative phosphorylation, physically located in the inner mitochondrial membrane (IMM). The mitochondrial contact site and organising system (MICOS) complex is known as the 'mitoskeleton' due to its role in maintaining IMM architecture. APOO encodes MIC26, a component of MICOS, whose exact function in its maintenance or assembly has still not been completely elucidated.

METHODS

We have studied a family in which the most affected subject presented progressive developmental delay, lactic acidosis, muscle weakness, hypotonia, weight loss, gastrointestinal and body temperature dysautonomia, repetitive infections, cognitive impairment and autistic behaviour. Other family members showed variable phenotype presentation. Whole exome sequencing was used to screen for pathological variants. Patient-derived skin fibroblasts were used to confirm the pathogenicity of the variant found in APOO. Knockout models in Drosophila melanogaster and Saccharomyces cerevisiae were employed to validate MIC26 involvement in MICOS assembly and mitochondrial function.

RESULTS

A likely pathogenic c.350T>C transition was found in APOO predicting an I117T substitution in MIC26. The mutation caused impaired processing of the protein during import and faulty insertion into the IMM. This was associated with altered MICOS assembly and cristae junction disruption. The corresponding mutation in MIC26 or complete loss was associated with mitochondrial structural and functional deficiencies in yeast and D. melanogaster models.

CONCLUSION

This is the first case of pathogenic mutation in APOO, causing altered MICOS assembly and neuromuscular impairment. MIC26 is involved in the assembly or stability of MICOS in humans, yeast and flies.

KinPred: A unified and sustainable approach for harnessing proteome-level human kinase-substrate predictions

Tyrosine and serine/threonine kinases are essential regulators of cell processes and are important targets for human therapies. Unfortunately, very little is known about specific kinase-substrate relationships, making it difficult to infer meaning from dysregulated phosphoproteomic datasets or for researchers to identify possible kinases that regulate specific or novel phosphorylation sites. The last two decades have seen an explosion in algorithms to extrapolate from what little is known into the larger unknown-predicting kinase relationships with site-specific substrates using a variety of approaches that include the sequence-specificity of kinase catalytic domains and various other factors, such as evolutionary relationships, co-expression, and protein-protein interaction networks. Unfortunately, a number of limitations prevent researchers from easily harnessing these resources, such as loss of resource accessibility, limited information in publishing that results in a poor mapping to a human reference, and not being updated to match the growth of the human phosphoproteome. Here, we propose a methodological framework for publishing predictions in a unified way, which entails ensuring predictions have been run on a current reference proteome, mapping the same substrates and kinases across resources to a common reference, filtering for the human phosphoproteome, and providing methods for updating the resource easily in the future. We applied this framework on three currently available resources, published in the last decade, which provide kinase-specific predictions in the human proteome. Using the unified datasets, we then explore the role of study bias, the emergent network properties of these predictive algorithms, and comparisons within and between predictive algorithms. The combination of the code for unification and analysis, as well as the unified predictions are available under the resource we named KinPred. We believe this resource will be useful for a wide range of applications and establishes best practices for long-term usability and sustainability for new and existing predictive algorithms.

GasPhos: Protein Phosphorylation Site Prediction Using a New Feature Selection Approach with a GA-Aided Ant Colony System

Protein phosphorylation is one of the most important post-translational modifications, and many biological processes are related to phosphorylation, such as DNA repair, transcriptional regulation and signal transduction and, therefore, abnormal regulation of phosphorylation usually causes diseases. If we can accurately predict human phosphorylation sites, this could help to solve human diseases. Therefore, we developed a kinase-specific phosphorylation prediction system, GasPhos, and proposed a new feature selection approach, called Gas, based on the ant colony system and a genetic algorithm and used performance evaluation strategies focused on different kinases to choose the best learning model. Gas uses the mean decrease Gini index (MDGI) as a heuristic value for path selection and adopts binary transformation strategies and new state transition rules. GasPhos can predict phosphorylation sites for six kinases and showed better performance than other phosphorylation prediction tools. The disease-related phosphorylated proteins that were predicted with GasPhos are also discussed. Finally, Gas can be applied to other issues that require feature selection, which could help to improve prediction performance. GasPhos is available at http://predictor.nchu.edu.tw/GasPhos.

KSP: an integrated method for predicting catalyzing kinases of phosphorylation sites in proteins

BACKGROUND

Protein phosphorylation by kinases plays crucial roles in various biological processes including signal transduction and tumorigenesis, thus a better understanding of protein phosphorylation events in cells is fundamental for studying protein functions and designing drugs to treat diseases caused by the malfunction of phosphorylation. Although a large number of phosphorylation sites in proteins have been identified using high-throughput phosphoproteomic technologies, their specific catalyzing kinases remain largely unknown. Therefore, computational methods are urgently needed to predict the kinases that catalyze the phosphorylation of these sites.

RESULTS

We developed KSP, a new algorithm for predicting catalyzing kinases for experimentally identified phosphorylation sites in human proteins. KSP constructs a network based on known protein-protein interactions and kinase-substrate relationships. Based on the network, it computes an affinity score between a phosphorylation site and kinases, and returns the top-ranked kinases of the score as candidate catalyzing kinases. When tested on known kinase-substrate pairs, KSP outperforms existing methods including NetworKIN, iGPS, and PKIS.

CONCLUSIONS

We developed a novel accurate tool for predicting catalyzing kinases of known phosphorylation sites. It can work as a complementary network approach for sequence-based phosphorylation site predictors.

Bioinformatics toolbox for exploring protein phosphorylation network

A clear systematic delineation of the interactions between phosphorylation sites on substrates and their effector kinases plays a fundamental role in revealing cellular activities, understanding signaling modulation mechanisms and proposing novel hypotheses. The emergence of bioinformatics tools contributes to studying phosphorylation network. Some of them feature the visualization of network, enabling more effective trace of the underlying biological problems in a clear and succinct way. In this review, we aimed to provide a toolbox for exploring phosphorylation network. We first systematically surveyed 19 tools that are available for exploring phosphorylation networks, and subsequently comparatively analyzed and summarized these tools to guide tool selection in terms of functionality, data sources, performance, network visualization and implementation, and finally briefly discussed the application cases of these tools. In different scenarios, the conclusion on the suitability of a tool for a specific user may vary. Nevertheless, easily accessible bioinformatics tools are proved to facilitate biological findings. Hopefully, this work might also assist non-specialists, students, as well as computational scientists who aim at developing novel tools in the field of phosphorylation modification.

Using phosphoproteomics data to understand cellular signaling: a comprehensive guide to bioinformatics resources

Mass spectrometry-based phosphoproteomics is becoming an essential methodology for the study of global cellular signaling. Numerous bioinformatics resources are available to facilitate the translation of phosphopeptide identification and quantification results into novel biological and clinical insights, a critical step in phosphoproteomics data analysis. These resources include knowledge bases of kinases and phosphatases, phosphorylation sites, kinase inhibitors, and sequence variants affecting kinase function, and bioinformatics tools that can predict phosphorylation sites in addition to the kinase that phosphorylates them, infer kinase activity, and predict the effect of mutations on kinase signaling. However, these resources exist in silos and it is challenging to select among multiple resources with similar functions. Therefore, we put together a comprehensive collection of resources related to phosphoproteomics data interpretation, compared the use of tools with similar functions, and assessed the usability from the standpoint of typical biologists or clinicians. Overall, tools could be improved by standardization of enzyme names, flexibility of data input and output format, consistent maintenance, and detailed manuals.

DeepPhos: prediction of protein phosphorylation sites with deep learning

Motivation

Phosphorylation 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.

Results

In 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 implementation

The source code of DeepPhos is publicly deposited at https://github.com/USTCHIlab/DeepPhos.

Supplementary information

Supplementary data are available at Bioinformatics online.

AWESOME: a database of SNPs that affect protein post-translational modifications

Protein post-translational modifications (PTMs), including phosphorylation, ubiquitination, methylation, acetylation, glycosylation et al, are very important biological processes. PTM changes in some critical genes, which may be induced by base-pair substitution, are shown to affect the risk of diseases. Recently, large-scale exome-wide association studies found that missense single nucleotide polymorphisms (SNPs) play an important role in the susceptibility for complex diseases or traits. One of the functional mechanisms of missense SNPs is that they may affect PTMs and leads to a protein dysfunction and its downstream signaling pathway disorder. Here, we constructed a database named AWESOME (A Website Exhibits SNP On Modification Event, http://www.awesome-hust.com), which is an interactive web-based analysis tool that systematically evaluates the role of SNPs on nearly all kinds of PTMs based on 20 available tools. We also provided a well-designed scoring system to compare the performance of different PTM prediction tools and help users to get a better interpretation of results. Users can search SNPs, genes or position of interest, filter with specific modifications or prediction methods, to get a comprehensive PTM change induced by SNPs. In summary, our database provides a convenient way to detect PTM-related SNPs, which may potentially be pathogenic factors or therapeutic targets.

Recent Development of Machine Learning Methods in Microbial Phosphorylation Sites

A variety of protein post-translational modifications has been identified that control many cellular functions. Phosphorylation studies in mycobacterial organisms have shown critical importance in diverse biological processes, such as intercellular communication and cell division. Recent technical advances in high-precision mass spectrometry have determined a large number of microbial phosphorylated proteins and phosphorylation sites throughout the proteome analysis. Identification of phosphorylated proteins with specific modified residues through experimentation is often labor-intensive, costly and time-consuming. All these limitations could be overcome through the application of machine learning (ML) approaches. However, only a limited number of computational phosphorylation site prediction tools have been developed so far. This work aims to present a complete survey of the existing ML-predictors for microbial phosphorylation. We cover a variety of important aspects for developing a successful predictor, including operating ML algorithms, feature selection methods, window size, and software utility. Initially, we review the currently available phosphorylation site databases of the microbiome, the state-of-the-art ML approaches, working principles, and their performances. Lastly, we discuss the limitations and future directions of the computational ML methods for the prediction of phosphorylation.

PhosTransfer: A Deep Transfer Learning Framework for Kinase-Specific Phosphorylation Site Prediction in Hierarchy

Machine learning algorithms have been widely used for predicting kinase-specific phosphorylation sites. However, the scarcity of training data for specific kinases makes it difficult to train effective models for predicting their phosphorylation sites. In this paper, we propose a deep transfer learning framework, PhosTransfer, for improving kinase-specific phosphorylation site prediction. It banks on the hierarchical information encoded in the kinase classification tree (KCT) which involves four levels: kinase groups, families, subfamilies and protein kinases (PKs). With PhosTransfer, predictive models associated with tree nodes at higher levels, which are trained with more sufficient training data, can be transferred and reused as feature extractors for predictive models of tree nodes at a lower level. Out results indicate that models with deep transfer learning out-performed those without transfer learning for 73 out of 79 tested PKs. The positive effect of deep transfer learning is better demonstrated in the prediction of phosphosites for kinase nodes with less training data. These improved performances are further validated and explained by the visualisation of vector representations generated from hidden layers pre-trained at different KCT levels.

Preincubation With Everolimus and Sirolimus Reduces Organic Anion-Transporting Polypeptide (OATP)1B1- and 1B3-Mediated Transport Independently of mTOR Kinase Inhibition: Implication in Assessing OATP1B1- and OATP1B3-Mediated Drug-Drug Interactions

Organic anion transporting polypeptides (OATP)1B1 and OATP1B3 mediate hepatic uptake of many drugs including lipid-lowering statins. Current studies determined the OATP1B1/1B3-mediated drug-drug interaction (DDI) potential of mammalian target of rapamycin (mTOR) inhibitors, everolimus and sirolimus, using R-value and physiologically based pharmacokinetic models. Preincubation with everolimus and sirolimus significantly decreased OATP1B1/1B3-mediated transport even after washing and decreased inhibition constant values up to 8.3- and 2.9-fold for OATP1B1 and both 2.7-fold for OATP1B3, respectively. R-values of everolimus, but not sirolimus, were greater than the FDA-recommended cutoff value of 1.1. Physiologically based pharmacokinetic models predict that everolimus and sirolimus have low OATP1B1/1B3-mediated DDI potential against pravastatin. OATP1B1/1B3-mediated transport was not affected by preincubation with INK-128 (10 μM, 1 h), which does however abolish mTOR kinase activity. The preincubation effects of everolimus and sirolimus on OATP1B1/1B3-mediated transport were similar in cells before preincubation with vehicle control or INK-128, suggesting that inhibition of mTOR activity is not a prerequisite for the preincubation effects observed for everolimus and sirolimus. Nine potential phosphorylation sites of OATP1B1 were identified by phosphoproteomics; none of these are the predicted mTOR phosphorylation sites. We report the everolimus/sirolimus-preincubation-induced inhibitory effects on OATP1B1/1B3 and relatively low OATP1B1/1B3-mediated DDI potential of everolimus and sirolimus.

In silico structure analysis of alphaviral RNA genomes shows diversity in the evasion of IFIT1-mediated innate immunity

The IFIT (interferon-induced proteins with tetratricopeptide repeats) family constitutes a major arm of the antiviral function of type I interferon (IFN). Human IFIT1, the earliest discovered member of this family, inhibits several viruses of positivestrand RNA genome. IFIT1 specifically recognizes single-stranded RNAwith canonical 7-methylguanylate cap at the 50 end (Cap0), and inhibits their translation by competing with eIF4E (eukaryotic initiation factor 4E), an essential factor for 50Cap recognition. Recently, a novel viral mechanism of IFIT1 suppression was reported, in which an RNA hairpin in the 50 untranslated region (50UTR) of the viral genome prevented recognition by IFIT1 and enhanced virus growth. Here, I have analyzed the in silico predicted structures in the 50UTR of the genomes of the Alphaviruses, a large group of enveloped RNA virus with positive-sense single-stranded genome. The results uncovered a large ensemble of RNA secondary structures of diverse size and shape in the different viruses, which showed little correspondence to the phylogeny of the viruses. Unexpectedly, the 50UTR of several viral genomes in this family did not fold into any structure, suggesting either their extreme sensitivity to IFIT1 or the existence of alternative viral mechanisms of subverting IFIT1 function.

Biochemical characterization of Plasmodium falciparum parasite specific helicase 1 (PfPSH1)

Malaria, a disease caused by infection with parasites of the genus Plasmodium, causes millions of deaths worldwide annually. Of the five Plasmodium species that can infect humans, Plasmodium falciparum causes the most serious parasitic infection. The emergence of drug resistance and the ineffectiveness of old therapeutic regimes against malaria mean there is an urgent need to better understand the basic biology of the malaria parasite. Previously, we have reported the presence of parasite‐specific helicases identified through genome‐wide analysis of the P. falciparum (3D7) strain. Helicases are involved in various biological pathways in addition to nucleic acid metabolism, making them an important target of study. Here, we report the detailed biochemical characterization of P. falciparum parasite‐specific helicase 1 (PfPSH1) and the effect of phosphorylation on its biochemical activities. The C‐terminal of PfPSH1 (PfPSH1C) containing all conserved domains was used for biochemical characterization. PfPSH1C exhibits DNA‐ or ribonucleic acid (RNA)‐stimulated ATPase activity, and it can unwind DNA and RNA duplex substrates. It shows bipolar directionality because it can translocate in both (3′–5′ and 5′–3′) directions. PfPSH1 is mainly localized to the cytoplasm during early stages (including ring and trophozoite stages of intraerythrocytic development), but at late stages, it is partially located in the cytoplasm. The biochemical activities of PfPSH1 are upregulated after phosphorylation with PKC. The detailed biochemical characterization of PfPSH1 will help us understand its functional role in the parasite and pave the way for future studies.

Computational prediction and analysis of species-specific fungi phosphorylation via feature optimization strategy

Protein phosphorylation is a reversible and ubiquitous post-translational modification that primarily occurs at serine, threonine and tyrosine residues and regulates a variety of biological processes. In this paper, we first briefly summarized the current progresses in computational prediction of eukaryotic protein phosphorylation sites, which mainly focused on animals and plants, especially on human, with a less extent on fungi. Since the number of identified fungi phosphorylation sites has greatly increased in a wide variety of organisms and their roles in pathological physiology still remain largely unknown, more attention has been paid on the identification of fungi-specific phosphorylation. Here, experimental fungi phosphorylation sites data were collected and most of the sites were classified into different types to be encoded with various features and trained via a two-step feature optimization method. A novel method for prediction of species-specific fungi phosphorylation-PreSSFP was developed, which can identify fungi phosphorylation in seven species for specific serine, threonine and tyrosine residues (http://computbiol.ncu.edu.cn/PreSSFP). Meanwhile, we critically evaluated the performance of PreSSFP and compared it with other existing tools. The satisfying results showed that PreSSFP is a robust predictor. Feature analyses exhibited that there have some significant differences among seven species. The species-specific prediction via two-step feature optimization method to mine important features for training could considerably improve the prediction performance. We anticipate that our study provides a new lead for future computational analysis of fungi phosphorylation.

Structural motif, topi and its role in protein function and fibrillation

A protein chain is arranged into regions in which the backbone is organized into regular patterns (of conformation and hydrogen bonding) to form the most common secondary structures, α-helix and β-sheet, which are interspersed by turns and more irregular loop regions. A structural motif, topi, is discussed in which a pair of 2-residue segments, each containing hydrogen-bonded five-membered fused-ring motifs, distant in sequence are linked to each other by a hydrogen bond. Though a small motif, it appears to be important in the context of local folding patterns of proteins and occurs near protein active sites. The motif shows quite significant residue preference, and a Cys (or Ser) occupying the second position may further stabilize the motif by forming an additional hydrogen bond across it. Remarkably, topi is found within disease causing misfolded proteins, such as the fibrilled form of Aβ42, and also across the interface between two protein chains. This motif may be an important component of fibrillation and useful for modeling loop regions.

Prediction of prkC-mediated protein serine/threonine phosphorylation sites for bacteria

As an abundant post-translational modification, reversible phosphorylation is critical for the dynamic regulation of various biological processes. prkC, a critical serine/threonine-protein kinase in bacteria, plays important roles in regulation of signaling transduction. Identification of prkC-specific phosphorylation sites is fundamental for understanding the molecular mechanism of phosphorylation-mediated signaling. However, experimental identification of substrates for prkC is time-consuming and labor-intensive, and computational methods for kinase-specific phosphorylation prediction in bacteria have yet to be developed. In this study, we manually curated the experimentally identified substrates and phosphorylation sites of prkC from the published literature. The analyses of the sequence preferences showed that the substrate recognition pattern for prkC might be miscellaneous, and a complex strategy should be employed to predict potential prkC-specific phosphorylation sites. To develop the predictor, the amino acid location feature extraction method and the support vector machine algorithm were employed, and the methods achieved promising performance. Through 10-fold cross validation, the predictor reached a sensitivity of 91.67% at the specificity of 95.12%. Then, we developed freely accessible software, which is provided at http://free.cancerbio.info/prkc/. Based on the predictor, hundreds of potential prkC-specific phosphorylation sites were annotated based on the known bacterial phosphorylation sites. prkC-PSP was the first predictor for prkC-specific phosphorylation sites, and its prediction performance was promising. We anticipated that these analyses and the predictor could be helpful for further studies of prkC-mediated phosphorylation.

PTM-ssMP: A Web Server for Predicting Different Types of Post-translational Modification Sites Using Novel Site-specific Modification Profile

Protein post-translational modifications (PTMs) are chemical modifications of a protein after its translation. Owing to its play an important role in deep understanding of various biological processes and the development of effective drugs, PTM site prediction have become a hot topic in bioinformatics. Recently, many online tools are developed to prediction various types of PTM sites, most of which are based on local sequence and some biological information. However, few of existing tools consider the relations between different PTMs for their prediction task. Here, we develop a web server called PTM-ssMP to predict PTM site, which adopts site-specific modification profile (ssMP) to efficiently extract and encode the information of both proximal PTMs and local sequence simultaneously. In PTM-ssMP we provide efficient prediction of multiple types of PTM site including phosphorylation, lysine acetylation, ubiquitination, sumoylation, methylation, O-GalNAc, O-GlcNAc, sulfation and proteolytic cleavage. To assess the performance of PTM-ssMP, a large number of experimentally verified PTM sites are collected from several sources and used to train and test the prediction models. Our results suggest that ssMP consistently contributes to remarkable improvement of prediction performance. In addition, results of independent tests demonstrate that PTM-ssMP compares favorably with other existing tools for different PTM types. PTM-ssMP is implemented as an online web server with user-friendly interface, which is freely available at http://bioinformatics.ustc.edu.cn/PTM-ssMP/index/.

A Novel Phosphorylation Site-Kinase Network-Based Method for the Accurate Prediction of Kinase-Substrate Relationships

Protein phosphorylation is catalyzed by kinases which regulate many aspects that control death, movement, and cell growth. Identification of the phosphorylation site-specific kinase-substrate relationships (ssKSRs) is important for understanding cellular dynamics and provides a fundamental basis for further disease-related research and drug design. Although several computational methods have been developed, most of these methods mainly use local sequence of phosphorylation sites and protein-protein interactions (PPIs) to construct the prediction model. While phosphorylation presents very complicated processes and is usually involved in various biological mechanisms, the aforementioned information is not sufficient for accurate prediction. In this study, we propose a new and powerful computational approach named KSRPred for ssKSRs prediction, by introducing a novel phosphorylation site-kinase network (pSKN) profiles that can efficiently incorporate the relationships between various protein kinases and phosphorylation sites. The experimental results show that the pSKN profiles can efficiently improve the prediction performance in collaboration with local sequence and PPI information. Furthermore, we compare our method with the existing ssKSRs prediction tools and the results demonstrate that KSRPred can significantly improve the prediction performance compared with existing tools.

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.

Membrane depolarization activates BK channels through ROCK-mediated β1 subunit surface trafficking to limit vasoconstriction

Membrane depolarization of smooth muscle cells (myocytes) in the small arteries that regulate regional organ blood flow leads to vasoconstriction. Membrane depolarization also activates large-conductance calcium (Ca²⁺)-activated potassium (BK) channels, which limits Ca²⁺ channel activity that promotes vasoconstriction, thus leading to vasodilation. We showed that in human and rat arterial myocytes, membrane depolarization rapidly increased the cell surface abundance of auxiliary BK β1 subunits but not that of the pore-forming BKα channels. Membrane depolarization stimulated voltage-dependent Ca²⁺ channels, leading to Ca²⁺ influx and the activation of Rho kinase (ROCK) 1 and 2. ROCK1/2-mediated activation of Rab11A promoted the delivery of β1 subunits to the plasma membrane by Rab11A-positive recycling endosomes. These additional β1 subunits associated with BKα channels already at the plasma membrane, leading to an increase in apparent Ca²⁺ sensitivity and activation of the channels in pressurized arterial myocytes and vasodilation. Thus, membrane depolarization activates BK channels through stimulation of ROCK- and Rab11A-dependent trafficking of β1 subunits to the surface of arterial myocytes.

Prediction of post-translational modification sites using multiple kernel support vector machine

Protein post-translational modification (PTM) is an important mechanism that is involved in the regulation of protein function. Considering the high-cost and labor-intensive of experimental identification, many computational prediction methods are currently available for the prediction of PTM sites by using protein local sequence information in the context of conserved motif. Here we proposed a novel computational method by using the combination of multiple kernel support vector machines (SVM) for predicting PTM sites including phosphorylation, O-linked glycosylation, acetylation, sulfation and nitration. To largely make use of local sequence information and site-modification relationships, we developed a local sequence kernel and Gaussian interaction profile kernel, respectively. Multiple kernels were further combined to train SVM for efficiently leveraging kernel information to boost predictive performance. We compared the proposed method with existing PTM prediction methods. The experimental results revealed that the proposed method performed comparable or better performance than the existing prediction methods, suggesting the feasibility of the developed kernels and the usefulness of the proposed method in PTM sites prediction.

Protein post-translational modifications: In silico prediction tools and molecular modeling

Post-translational modifications (PTMs) occur in almost all proteins and play an important role in numerous biological processes by significantly affecting proteins' structure and dynamics. Several computational approaches have been developed to study PTMs (e.g., phosphorylation, sumoylation or palmitoylation) showing the importance of these techniques in predicting modified sites that can be further investigated with experimental approaches. In this review, we summarize some of the available online platforms and their contribution in the study of PTMs. Moreover, we discuss the emerging capabilities of molecular modeling and simulation that are able to complement these bioinformatics methods, providing deeper molecular insights into the biological function of post-translational modified proteins.

Cysteine-linked dimerization of BST-2 confers anoikis resistance to breast cancer cells by negating proapoptotic activities to promote tumor cell survival and growth

Almost all breast tumors express the antiviral protein BST-2 with 67%, 25% and 8.2% containing high, medium or low levels of BST-2, respectively. Breast tumor cells and tissues that contain elevated levels of BST-2 are highly aggressive. Suppression of BST-2 expression reprograms tumorigenic properties of cancer cells and diminishes cancer cell aggressiveness. Using structure/function studies, we report that dimerization of BST-2 through cysteine residues located in the BST-2 extracellular domain (ECD), leads to anoikis resistance and cell survival through proteasome-mediated degradation of BIM—a key proapoptotic factor. Importantly, BST-2 dimerization promotes tumor growth in preclinical breast cancer models in vitro and in vivo. Furthermore, we demonstrate that restoration of the ECD cysteine residues is sufficient to rescue cell survival and tumor growth via a previously unreported pathway—BST-2/GRB2/ERK/BIM/Cas3. These findings suggest that disruption of BST-2 dimerization offers a potential therapeutic approach for breast cancer.

Regulation of divalent metal transporter-1 by serine phosphorylation

Divalent metal transporter-1 (DMT1) mediates dietary iron uptake across the intestinal mucosa and facilitates peripheral delivery of iron released by transferrin in the endosome. Here, we report that classical cannabinoids (Δ⁹-tetrahydrocannabinol, Δ⁹-THC), nonclassical cannabinoids (CP 55,940), aminoalkylindoles (WIN 55,212-2) and endocannabinoids (anandamide) reduce ⁵⁵Fe and ⁵⁴Mn uptake by HEK293T(DMT1) cells stably expressing the transporter. siRNA knockdown of cannabinoid receptor type 2 (CB2) abrogated inhibition. CB2 is a G-protein (GTP-binding protein)-coupled receptor that negatively regulates signal transduction cascades involving serine/threonine kinases. Immunoprecipitation experiments showed that DMT1 is serine-phosphorylated under basal conditions, but that treatment with Δ⁹-THC reduced phosphorylation. Site-directed mutation of predicted DMT1 phosphosites further showed that substitution of serine with alanine at N-terminal position 43 (S⁴³A) abolished basal phosphorylation. Concordantly, both the rate and extent of ⁵⁵Fe uptake in cells expressing DMT1(S⁴³A) was reduced compared with those expressing wild-type DMT1. Among kinase inhibitors that affected DMT1-mediated iron uptake, staurosporine also reduced DMT1 phosphorylation confirming a role for serine phosphorylation in iron transport regulation. These combined data indicate that phosphorylation at serine 43 of DMT1 promotes transport activity, whereas dephosphorylation is associated with loss of iron uptake. Since anti-inflammatory actions mediated through CB2 would be associated with reduced DMT1 phosphorylation, we postulate that this pathway provides a means to reduce oxidative stress by limiting iron uptake.

Regulation of BLM Nucleolar Localization

Defects in coordinated ribosomal RNA (rRNA) transcription in the nucleolus cause cellular and organismal growth deficiencies. Bloom's syndrome, an autosomal recessive human disorder caused by mutated recQ-like helicase BLM, presents with growth defects suggestive of underlying defects in rRNA transcription. Our previous studies showed that BLM facilitates rRNA transcription and interacts with RNA polymerase I and topoisomerase I (TOP1) in the nucleolus. The mechanisms regulating localization of BLM to the nucleolus are unknown. In this study, we identify the TOP1-interaction region of BLM by co-immunoprecipitation of in vitro transcribed and translated BLM segments and show that this region includes the highly conserved nuclear localization sequence (NLS) of BLM. Biochemical and nucleolar co-localization studies using site-specific mutants show that two serines within the NLS (S1342 and S1345) are critical for nucleolar localization of BLM but do not affect the functional interaction of BLM with TOP1. Mutagenesis of both serines to aspartic acid (phospho-mimetic), but not alanine (phospho-dead), results in approximately 80% reduction in nucleolar localization of BLM while retaining the biochemical functions and nuclear localization of BLM. Our studies suggest a role for this region in regulating nucleolar localization of BLM via modification of the two serines within the NLS.

Inferring Disease Associated Phosphorylation Sites via Random Walk on Multi-Layer Heterogeneous Network

As protein phosphorylation plays an important role in numerous cellular processes, many studies have been undertaken to analyze phosphorylation-related activities for drug design and disease treatment. However, although progresses have been made in illustrating the relationship between phosphorylation and diseases, no existing method focuses on disease-associated phosphorylation sites prediction. In this work, we proposed a multi-layer heterogeneous network model that makes use of the kinase information to infer disease-phosphorylation site relationship and implemented random walk on the heterogeneous network. Experimental results reveal that multi-layer heterogeneous network model with kinase layer is superior in inferring disease-phosphorylation site relationship when comparing with existing random walk model and common used classification methods.

A novel method for predicting post-translational modifications on serine and threonine sites by using site-modification network profiles

Post-translational modifications (PTMs) regulate many aspects of biological behaviours including protein-protein interactions and cellular processes. Identification of PTM sites is helpful for understanding the PTM regulatory mechanisms. The PTMs on serine and threonine sites include phosphorylation, O-linked glycosylation and acetylation. Although a lot of computational approaches have been developed for PTM site prediction, currently most of them generate the predictive models by employing only local sequence information and few of them consider the relationship between different PTMs. In this paper, by adopting the site-modification network (SMNet) profiles that efficiently incorporate in situ PTM information, we develop a novel method to predict PTM sites on serine and threonine. PTM data are collected from various PTM databases and the SMNet is built to reflect the relationship between multiple PTMs, from which SMNet profiles are extracted to train predictive models based on SVM. Performance analysis of the SVM models shows that the SMNet profiles play an important role in accurately predicting PTM sites on serine and threonine. Furthermore, the proposed method is compared with existing PTM prediction approaches. The results from 10-fold cross-validation demonstrate that the proposed method with SMNet profiles performs remarkably better than existing methods, suggesting the power of SMNet profiles in identifying PTM sites.

PredPhos: an ensemble framework for structure-based prediction of phosphorylation sites

Background

Post-translational modifications (PTMs) occur on almost all proteins and often strongly affect the functions of modified proteins. Phosphorylation is a crucial PTM mechanism with important regulatory functions in biological systems. Identifying the potential phosphorylation sites of a target protein may increase our understanding of the molecular processes in which it takes part.

Results

In this paper, we propose PredPhos, a computational method that can accurately predict both kinase-specific and non-kinase-specific phosphorylation sites by using optimally selected properties. The optimal combination of features was selected from a set of 153 novel structural neighborhood properties by a two-step feature selection method consisting of a random forest algorithm and a sequential backward elimination method. To overcome the imbalanced problem, we adopt an ensemble method, which combines bootstrap resampling technique, support vector machine-based fusion classifiers and majority voting strategy. We evaluate the proposed method using both tenfold cross validation and independent test. Results show that our method achieves a significant improvement on the prediction performance for both kinase-specific and non-kinase-specific phosphorylation sites.

Conclusions

The experimental results demonstrate that the proposed method is quite effective in predicting phosphorylation sites. Promising results are derived from the new structural neighborhood properties, the novel way of feature selection, as well as the ensemble method.