Prediction of protein kinase-specific phosphorylation sites in hierarchical structure using functional information and random forest

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.

Phosformer: an explainable transformer model for protein kinase-specific phosphorylation predictions

MOTIVATION

The human genome encodes over 500 distinct protein kinases which regulate nearly all cellular processes by the specific phosphorylation of protein substrates. While advances in mass spectrometry and proteomics studies have identified thousands of phosphorylation sites across species, information on the specific kinases that phosphorylate these sites is currently lacking for the vast majority of phosphosites. Recently, there has been a major focus on the development of computational models for predicting kinase-substrate associations. However, most current models only allow predictions on a subset of well-studied kinases. Furthermore, the utilization of hand-curated features and imbalances in training and testing datasets pose unique challenges in the development of accurate predictive models for kinase-specific phosphorylation prediction. Motivated by the recent development of universal protein language models which automatically generate context-aware features from primary sequence information, we sought to develop a unified framework for kinase-specific phosphosite prediction, allowing for greater investigative utility and enabling substrate predictions at the whole kinome level.

RESULTS

We present a deep learning model for kinase-specific phosphosite prediction, termed Phosformer, which predicts the probability of phosphorylation given an arbitrary pair of unaligned kinase and substrate peptide sequences. We demonstrate that Phosformer implicitly learns evolutionary and functional features during training, removing the need for feature curation and engineering. Further analyses reveal that Phosformer also learns substrate specificity motifs and is able to distinguish between functionally distinct kinase families. Benchmarks indicate that Phosformer exhibits significant improvements compared to the state-of-the-art models, while also presenting a more generalized, unified, and interpretable predictive framework.

AVAILABILITY AND IMPLEMENTATION

Code and data are available at https://github.com/esbgkannan/phosformer.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

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.

Multi-Modal Classification for Human Breast Cancer Prognosis Prediction: Proposal of Deep-Learning Based Stacked Ensemble Model

Breast Cancer is a highly aggressive type of cancer generally formed in the cells of the breast. Despite significant advances in the treatment of primary breast cancer in the last decade, there is a dire need to attempt of an accurate predictive model for breast cancer prognosis prediction. Researchers from various disciplines are working together to develop methods to save people from this fatal disease. A good predictive model can help in correct prognosis prediction of breast cancer. This accurate prediction can have several benefits like detection of cancer in the early stage, spare patients from getting unnecessary treatment and medical expenses related to it. Previous works rely mostly on uni-modal data (selected gene expression)for predictive model design. In recent years, however, multi-modal cancer data sets have become available (gene expression, copy number alteration and clinical). Motivated by the enhancement of deep-learning based models, in the current study, we propose to use some deep-learning based predictive models in a stacked ensemble framework to improve the prognosis prediction of breast cancer from available multi-modal data sets. One of the unique advantages of the proposed approach lies in the architecture of the model. It is a two-stage model. Stage one uses a convolutional neural network for feature extraction, while stage two uses the extracted features as input to the stack-based ensemble model. The predictive performance evaluated using different performance measures shows that this model produces better result than already existing approaches. This model results in AUC value of 0.93 and accuracy of 90.2 percent at medium stringency level (Specificity = 95 percent and threshold = 0.45). Keras 2.2.1, along with Tensorflow 1.12, is used for implementing the source code of the model. The source code can be downloaded from Github: https://github.com/nikhilaryan92/BreastCancer.

SSKM_Succ: A Novel Succinylation Sites Prediction Method Incorporating K-Means Clustering With a New Semi-Supervised Learning Algorithm

Protein succinylation is a type of post-translational modification (PTM) that occurs on lysine sites and plays a key role in protein conformation regulation and cellular function control. When training in computational method, it is difficult to designate negative samples because of the uncertainty of non-succinylation lysine sites, and if not handled properly, it may affect the performance of computational models dramatically. Therefore, we propose a new semi-supervised learning method to identify reliable non-succinylation lysine sites as negative samples. This method, named SSKM_Succ, also employs K-means clustering to divide data into 5 clusters. Besides, information of proximal PTMs and three kinds of sequence features (grey pseudo amino acid composition, K-space and position-special amino acid propensity) are utilized to formulate protein. Then, we perform a two-step feature selection to remove redundant features and construct the optimization model for each cluster. Finally, support vector machine is applied to construct a prediction model for each cluster. Promising results are obtained by this method with an accuracy of 80.18 percent for succinylation sites on the independent testing dataset. Meanwhile, we compare the result with other existing tools, and it shows that our method is promising for predicting succinylation sites. Through analysis, we further verify that succinylated protein has potential effects on amino acid degradation and fatty acid metabolism, and speculate that protein succinylation may be closely related to neurodegenerative diseases. The code of SSKM_Succ is available on the web https://github.com/yangyq505/SSKM_Succ.git.

PKSPS: a novel method for predicting kinase of specific phosphorylation sites based on maximum weighted bipartite matching algorithm and phosphorylation sequence enrichment analysis

With the development of biotechnology, a large number of phosphorylation sites have been experimentally confirmed and collected, but only a few of them have kinase annotations. Since experimental methods to detect kinases at specific phosphorylation sites are expensive and accidental, some computational methods have been proposed to predict the kinase of these sites, but most methods only consider single sequence information or single functional network information. In this study, a new method Predicting Kinase of Specific Phosphorylation Sites (PKSPS) is developed to predict kinases of specific phosphorylation sites in human proteins by combining PKSPS-Net with PKSPS-Seq, which considers protein-protein interaction (PPI) network information and sequence information. For PKSPS-Net, kinase-kinase and substrate-substrate similarity are quantified based on the topological similarity of proteins in the PPI network, and maximum weighted bipartite matching algorithm is proposed to predict kinase-substrate relationship. In PKSPS-Seq, phosphorylation sequence enrichment analysis is used to analyze the similarity of local sequences around phosphorylation sites and predict the kinase of specific phosphorylation sites (KSP). PKSPS has been proved to be more effective than the PKSPS-Net or PKSPS-Seq on different sets of kinases. Further comparison results show that the PKSPS method performs better than existing methods. Finally, the case study demonstrates the effectiveness of the PKSPS in predicting kinases of specific phosphorylation sites. The open source code and data of the PKSPS can be obtained from https://github.com/guoxinyunncu/PKSPS.

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.

RAM-PGK: Prediction of Lysine Phosphoglycerylation Based on Residue Adjacency Matrix

Background: Post-translational modification (PTM) is a biological process that is associated with the modification of proteome, which results in the alteration of normal cell biology and pathogenesis. There have been numerous PTM reports in recent years, out of which, lysine phosphoglycerylation has emerged as one of the recent developments. The traditional methods of identifying phosphoglycerylated residues, which are experimental procedures such as mass spectrometry, have shown to be time-consuming and cost-inefficient, despite the abundance of proteins being sequenced in this post-genomic era. Due to these drawbacks, computational techniques are being sought to establish an effective identification system of phosphoglycerylated lysine residues. The development of a predictor for phosphoglycerylation prediction is not a first, but it is necessary as the latest predictor falls short in adequately detecting phosphoglycerylated and non-phosphoglycerylated lysine residues. Results: In this work, we introduce a new predictor named RAM-PGK, which uses sequence-based information relating to amino acid residues to predict phosphoglycerylated and non-phosphoglycerylated sites. A benchmark dataset was employed for this purpose, which contained experimentally identified phosphoglycerylated and non-phosphoglycerylated lysine residues. From the dataset, we extracted the residue adjacency matrix pertaining to each lysine residue in the protein sequences and converted them into feature vectors, which is used to build the phosphoglycerylation predictor. Conclusion: RAM-PGK, which is based on sequential features and support vector machine classifiers, has shown a noteworthy improvement in terms of performance in comparison to some of the recent prediction methods. The performance metrics of the RAM-PGK predictor are: 0.5741 sensitivity, 0.6436 specificity, 0.0531 precision, 0.6414 accuracy, and 0.0824 Mathews correlation coefficient.

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.

Developing Computational Model to Predict Protein-Protein Interaction Sites Based on the XGBoost Algorithm

The study of protein-protein interaction is of great biological significance, and the prediction of protein-protein interaction sites can promote the understanding of cell biological activity and will be helpful for drug development. However, uneven distribution between interaction and non-interaction sites is common because only a small number of protein interactions have been confirmed by experimental techniques, which greatly affects the predictive capability of computational methods. In this work, two imbalanced data processing strategies based on XGBoost algorithm were proposed to re-balance the original dataset from inherent relationship between positive and negative samples for the prediction of protein-protein interaction sites. Herein, a feature extraction method was applied to represent the protein interaction sites based on evolutionary conservatism of proteins, and the influence of overlapping regions of positive and negative samples was considered in prediction performance. Our method showed good prediction performance, such as prediction accuracy of 0.807 and MCC of 0.614, on an original dataset with 10,455 surface residues but only 2297 interface residues. Experimental results demonstrated the effectiveness of our XGBoost-based method.

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.

Bigram-PGK: phosphoglycerylation prediction using the technique of bigram probabilities of position specific scoring matrix

BACKGROUND

The biological process known as post-translational modification (PTM) is a condition whereby proteomes are modified that affects normal cell biology, and hence the pathogenesis. A number of PTMs have been discovered in the recent years and lysine phosphoglycerylation is one of the fairly recent developments. Even with a large number of proteins being sequenced in the post-genomic era, the identification of phosphoglycerylation remains a big challenge due to factors such as cost, time consumption and inefficiency involved in the experimental efforts. To overcome this issue, computational techniques have emerged to accurately identify phosphoglycerylated lysine residues. However, the computational techniques proposed so far hold limitations to correctly predict this covalent modification.

RESULTS

We propose a new predictor in this paper called Bigram-PGK which uses evolutionary information of amino acids to try and predict phosphoglycerylated sites. The benchmark dataset which contains experimentally labelled sites is employed for this purpose and profile bigram occurrences is calculated from position specific scoring matrices of amino acids in the protein sequences. The statistical measures of this work, such as sensitivity, specificity, precision, accuracy, Mathews correlation coefficient and area under ROC curve have been reported to be 0.9642, 0.8973, 0.8253, 0.9193, 0.8330, 0.9306, respectively.

CONCLUSIONS

The proposed predictor, based on the feature of evolutionary information and support vector machine classifier, has shown great potential to effectively predict phosphoglycerylated and non-phosphoglycerylated lysine residues when compared against the existing predictors. The data and software of this work can be acquired from https://github.com/abelavit/Bigram-PGK.

LSCDFS-MKL: A multiple kernel based method for lung squamous cell carcinomas disease-free survival prediction with pathological and genomic data

Lung squamous cell carcinoma (SCC) is a fatal disease in both male and female, for which current treatments are inadequate. Surgical resection is regarded as the cornerstone of treatment for patients with lung SCC, but even for the same stage patients, the wide spectrum of disease-free survival (DFS) times exits. Therefore, how to improve the DFS prediction performance of lung SCC becomes one major research area. In this study, we proposed a novel method called LSCDFS-MKL, which was on the basis of multiple kernel learning to predict DFS of lung SCC. In LSCDFS-MKL, we first efficiently integrated pathological images and genomic data (copy number aberration, gene expression, protein expression) from lung SCC. The results of LSCDFS-MKL between different types of data show that the features extracted from pathological images play an important role in DFS prediction of lung SCC. Then we compared our method LSCDFS-MKL with other existing methods and performance analysis indicates that LSCDFS-MKL has a significantly better performance than other prediction methods. After that, we applied the proposed method on different stage stratums and the performance demonstrates that LSCDFS-MKL remains efficient in DFS prediction of lung SCC patients. Finally, we performed LSCDFS-MKL on an independent validation dataset and the accuracy of DFS prediction achieves 100%, which is promising.

Identifying Interactions Between Kinases and Substrates Based on Protein-Protein Interaction Network

Protein phosphorylation is a kind of important post-translational modification of protein, which plays a critical role in many biological processes of eukaryote. Identifying kinase-substrate interactions is helpful to understand the mechanism of many diseases. Many computational algorithms for kinase-substrate interactions identification have been proposed. However, most of those methods are mainly focused on utilizing protein local sequence information. In this article, we propose a new computational method to predict kinase-substrate interactions based on protein-protein interaction (PPI) network. Different from existing methods, the PPI network is utilized to measure the similarities of kinase-kinase and substrate-substrate, respectively. Then, the pairwise similarities of kinase-kinase and substrate-substrate are adjusted based on the assumption that the similarities of kinase-kinase and substrate-substrate are more reliable if they are in the same cluster. Finally, the bi-random walk is used to predict potential kinase-substrate interactions. The experimental results show that our method outperforms other state-of-the-art algorithms in performance. Furthermore, the case study demonstrates that it is effective in predicting potential kinase-substrate interactions.

KSIMC: Predicting Kinase⁻Substrate Interactions Based on Matrix Completion

Protein phosphorylation is an important chemical modification catalyzed by kinases. It plays important roles in many cellular processes. Predicting kinase–substrate interactions is vital to understanding the mechanism of many diseases. Many computational methods have been proposed to identify kinase–substrate interactions. However, the prediction accuracy still needs to be improved. Therefore, it is necessary to develop an efficient computational method to predict kinase–substrate interactions. In this paper, we propose a novel computational approach, KSIMC, to identify kinase–substrate interactions based on matrix completion. Firstly, the kinase similarity and substrate similarity are calculated by aligning sequence of kinase–kinase and substrate–substrate, respectively. Then, the original association network is adjusted based on the similarities. Finally, the matrix completion is used to predict potential kinase–substrate interactions. The experiment results show that our method outperforms other state-of-the-art algorithms in performance. Furthermore, the relevant databases and scientific literature verify the effectiveness of our algorithm for new kinase–substrate interaction identification.

Integration of A Deep Learning Classifier with A Random Forest Approach for Predicting Malonylation Sites

As a newly-identified protein post-translational modification, malonylation is involved in a variety of biological functions. Recognizing malonylation sites in substrates represents an initial but crucial step in elucidating the molecular mechanisms underlying protein malonylation. In this study, we constructed a deep learning (DL) network classifier based on long short-term memory (LSTM) with word embedding (LSTM_WE) for the prediction of mammalian malonylation sites. LSTM_WE performs better than traditional classifiers developed with common pre-defined feature encodings or a DL classifier based on LSTM with a one-hot vector. The performance of LSTM_WE is sensitive to the size of the training set, but this limitation can be overcome by integration with a traditional machine learning (ML) classifier. Accordingly, an integrated approach called LEMP was developed, which includes LSTM_WE and the random forest classifier with a novel encoding of enhanced amino acid content. LEMP performs not only better than the individual classifiers but also superior to the currently-available malonylation predictors. Additionally, it demonstrates a promising performance with a low false positive rate, which is highly useful in the prediction application. Overall, LEMP is a useful tool for easily identifying malonylation sites with high confidence. LEMP is available at http://www.bioinfogo.org/lemp.

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.

Research progress in protein posttranslational modification site prediction

Posttranslational modifications (PTMs) play an important role in regulating protein folding, activity and function and are involved in almost all cellular processes. Identification of PTMs of proteins is the basis for elucidating the mechanisms of cell biology and disease treatments. Compared with the laboriousness of equivalent experimental work, PTM prediction using various machine-learning methods can provide accurate, simple and rapid research solutions and generate valuable information for further laboratory studies. In this review, we manually curate most of the bioinformatics tools published since 2008. We also summarize the approaches for predicting ubiquitination sites and glycosylation sites. Moreover, we discuss the challenges of current PTM bioinformatics tools and look forward to future research possibilities.

PhoglyStruct: Prediction of phosphoglycerylated lysine residues using structural properties of amino acids

The biological process known as post-translational modification (PTM) contributes to diversifying the proteome hence affecting many aspects of normal cell biology and pathogenesis. There have been many recently reported PTMs, but lysine phosphoglycerylation has emerged as the most recent subject of interest. Despite a large number of proteins being sequenced, the experimental method for detection of phosphoglycerylated residues remains an expensive, time-consuming and inefficient endeavor in the post-genomic era. Instead, the computational methods are being proposed for accurately predicting phosphoglycerylated lysines. Though a number of predictors are available, performance in detecting phosphoglycerylated lysine residues is still limited. In this paper, we propose a new predictor called PhoglyStruct that utilizes structural information of amino acids alongside a multilayer perceptron classifier for predicting phosphoglycerylated and non-phosphoglycerylated lysine residues. For the experiment, we located phosphoglycerylated and non-phosphoglycerylated lysines in our employed benchmark. We then derived and integrated properties such as accessible surface area, backbone torsion angles, and local structure conformations. PhoglyStruct showed significant improvement in the ability to detect phosphoglycerylated residues from non-phosphoglycerylated ones when compared to previous predictors. The sensitivity, specificity, accuracy, Mathews correlation coefficient and AUC were 0.8542, 0.7597, 0.7834, 0.5468 and 0.8077, respectively. The data and Matlab/Octave software packages are available at https://github.com/abelavit/PhoglyStruct .

Integrating genomic data and pathological images to effectively predict breast cancer clinical outcome

BACKGROUND AND OBJECTIVE

Breast cancer is a leading cause of death from cancer for females. The high mortality rate of breast cancer is largely due to the complexity among invasive breast cancer and its significantly varied clinical outcomes. Therefore, improving the accuracy of breast cancer survival prediction has important significance and becomes one of the major research areas. Nowadays many computational models have been proposed for breast cancer survival prediction, however, most of them generate the predictive models by employing only the genomic data information and few of them consider the complementary information from pathological images.

METHODS

In our study, we introduce a novel method called GPMKL based on multiple kernel learning (MKL), which efficiently employs heterogeneous information containing genomic data (gene expression, copy number alteration, gene methylation, protein expression) and pathological images. With above heterogeneous features, GPMKL is proposed to execute feature fusion which is embedded in breast cancer classification.

RESULTS

Performance analysis of the GPMKL model indicates that the pathological image information plays a critical part in accurately predicting the survival time of breast cancer patients. Furthermore, the proposed method is compared with other existing breast cancer survival prediction methods, and the results demonstrate that the proposed framework with pathological images performs remarkably better than the existing survival prediction methods.

CONCLUSIONS

All results performed in our study suggest that the usefulness and superiority of GPMKL in predicting human breast cancer survival.

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 multimodal deep neural network for human breast cancer prognosis prediction by integrating multi-dimensional data

Breast cancer is a highly aggressive type of cancer with very low median survival. Accurate prognosis prediction of breast cancer can spare a significant number of patients from receiving unnecessary adjuvant systemic treatment and its related expensive medical costs. Previous work relies mostly on selected gene expression data to create a predictive model. The emergence of deep learning methods and multi-dimensional data offers opportunities for more comprehensive analysis of the molecular characteristics of breast cancer and therefore can improve diagnosis, treatment and prevention. In this study, we propose a Multimodal Deep Neural Network by integrating Multi-dimensional Data (MDNNMD) for the prognosis prediction of breast cancer. The novelty of the method lies in the design of our method's architecture and the fusion of multi-dimensional data. The comprehensive performance evaluation results show that the proposed method achieves a better performance than the prediction methods with single-dimensional data and other existing approaches. The source code implemented by TensorFlow 1.0 deep learning library can be downloaded from the Github: https://github.com/USTC-HIlab/MDNNMD.

ksrMKL: a novel method for identification of kinase-substrate relationships using multiple kernel learning

Phosphorylation exerts a crucial role in multiple biological cellular processes which is catalyzed by protein kinases and closely related to many diseases. Identification of kinase-substrate relationships is important for understanding phosphorylation and provides a fundamental basis for further disease-related research and drug design. In this study, we develop a novel computational method to identify kinase-substrate relationships based on multiple kernel learning. The comparative analysis is based on a 10-fold cross-validation process and the dataset collected from the Phospho.ELM database. The results show that ksrMKL is greatly improved in various measures when compared with the single kernel support vector machine. Furthermore, with an independent test dataset extracted from the PhosphoSitePlus database, we compare ksrMKL with two existing kinase-substrate relationship prediction tools, namely iGPS and PKIS. The experimental results show that ksrMKL has better prediction performance than these 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.

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.

GPS-PAIL: prediction of lysine acetyltransferase-specific modification sites from protein sequences

Protein acetylation catalyzed by specific histone acetyltransferases (HATs) is an essential post-translational modification (PTM) and involved in the regulation a broad spectrum of biological processes in eukaryotes. Although several ten thousands of acetylation sites have been experimentally identified, the upstream HATs for most of the sites are unclear. Thus, the identification of HAT-specific acetylation sites is fundamental for understanding the regulatory mechanisms of protein acetylation. In this work, we first collected 702 known HAT-specific acetylation sites of 205 proteins from the literature and public data resources, and a motif-based analysis demonstrated that different types of HATs exhibit similar but considerably distinct sequence preferences for substrate recognition. Using 544 human HAT-specific sites for training, we constructed a highly useful tool of GPS-PAIL for the prediction of HAT-specific sites for up to seven HATs, including CREBBP, EP300, HAT1, KAT2A, KAT2B, KAT5 and KAT8. The prediction accuracy of GPS-PAIL was critically evaluated, with a satisfying performance. Using GPS-PAIL, we also performed a large-scale prediction of potential HATs for known acetylation sites identified from high-throughput experiments in nine eukaryotes. Both online service and local packages were implemented, and GPS-PAIL is freely available at: http://pail.biocuckoo.org.

GlycoMinestruct: a new bioinformatics tool for highly accurate mapping of the human N-linked and O-linked glycoproteomes by incorporating structural features

Glycosylation plays an important role in cell-cell adhesion, ligand-binding and subcellular recognition. Current approaches for predicting protein glycosylation are primarily based on sequence-derived features, while little work has been done to systematically assess the importance of structural features to glycosylation prediction. Here, we propose a novel bioinformatics method called GlycoMine^struct(http://glycomine.erc.monash.edu/Lab/GlycoMine_Struct/) for improved prediction of human N- and O-linked glycosylation sites by combining sequence and structural features in an integrated computational framework with a two-step feature-selection strategy. Experiments indicated that GlycoMine^struct outperformed NGlycPred, the only predictor that incorporated both sequence and structure features, achieving AUC values of 0.941 and 0.922 for N- and O-linked glycosylation, respectively, on an independent test dataset. We applied GlycoMine^struct to screen the human structural proteome and obtained high-confidence predictions for N- and O-linked glycosylation sites. GlycoMine^struct can be used as a powerful tool to expedite the discovery of glycosylation events and substrates to facilitate hypothesis-driven experimental studies.

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.

Sequence- and Structure-Based Analysis of Tissue-Specific Phosphorylation Sites

Phosphorylation is the most widespread and well studied reversible posttranslational modification. Discovering tissue-specific preferences of phosphorylation sites is important as phosphorylation plays a role in regulating almost every cellular activity and disease state. Here we present a comprehensive analysis of global and tissue-specific sequence and structure properties of phosphorylation sites utilizing recent proteomics data. We identified tissue-specific motifs in both sequence and spatial environments of phosphorylation sites. Target site preferences of kinases across tissues indicate that, while many kinases mediate phosphorylation in all tissues, there are also kinases that exhibit more tissue-specific preferences which, notably, are not caused by tissue-specific kinase expression. We also demonstrate that many metabolic pathways are differentially regulated by phosphorylation in different tissues.

RF-Phos: A Novel General Phosphorylation Site Prediction Tool Based on Random Forest

Protein phosphorylation is one of the most widespread regulatory mechanisms in eukaryotes. Over the past decade, phosphorylation site prediction has emerged as an important problem in the field of bioinformatics. Here, we report a new method, termed Random Forest-based Phosphosite predictor 2.0 (RF-Phos 2.0), to predict phosphorylation sites given only the primary amino acid sequence of a protein as input. RF-Phos 2.0, which uses random forest with sequence and structural features, is able to identify putative sites of phosphorylation across many protein families. In side-by-side comparisons based on 10-fold cross validation and an independent dataset, RF-Phos 2.0 compares favorably to other popular mammalian phosphosite prediction methods, such as PhosphoSVM, GPS2.1, and Musite.

Kinase Identification with Supervised Laplacian Regularized Least Squares

Phosphorylation is catalyzed by protein kinases and is irreplaceable in regulating biological processes. Identification of phosphorylation sites with their corresponding kinases contributes to the understanding of molecular mechanisms. Mass spectrometry analysis of phosphor-proteomes generates a large number of phosphorylated sites. However, experimental methods are costly and time-consuming, and most phosphorylation sites determined by experimental methods lack kinase information. Therefore, computational methods are urgently needed to address the kinase identification problem. To this end, we propose a new kernel-based machine learning method called Supervised Laplacian Regularized Least Squares (SLapRLS), which adopts a new method to construct kernels based on the similarity matrix and minimizes both structure risk and overall inconsistency between labels and similarities. The results predicted using both Phospho.ELM and an additional independent test dataset indicate that SLapRLS can more effectively identify kinases compared to other existing algorithms.

Tyrosine Kinase Ligand-Receptor Pair Prediction by Using Support Vector Machine

Receptor tyrosine kinases are essential proteins involved in cellular differentiation and proliferation in vivo and are heavily involved in allergic diseases, diabetes, and onset/proliferation of cancerous cells. Identifying the interacting partner of this protein, a growth factor ligand, will provide a deeper understanding of cellular proliferation/differentiation and other cell processes. In this study, we developed a method for predicting tyrosine kinase ligand-receptor pairs from their amino acid sequences. We collected tyrosine kinase ligand-receptor pairs from the Database of Interacting Proteins (DIP) and UniProtKB, filtered them by removing sequence redundancy, and used them as a dataset for machine learning and assessment of predictive performance. Our prediction method is based on support vector machines (SVMs), and we evaluated several input features suitable for tyrosine kinase for machine learning and compared and analyzed the results. Using sequence pattern information and domain information extracted from sequences as input features, we obtained 0.996 of the area under the receiver operating characteristic curve. This accuracy is higher than that obtained from general protein-protein interaction pair predictions.

Exploiting holistic approaches to model specificity in protein phosphorylation

Phosphate plays a chemically unique role in shaping cellular signaling of all current living systems, especially eukaryotes. Protein phosphorylation has been studied at several levels, from the near-site context, both in sequence and structure, to the crowded cellular environment, and ultimately to the systems-level perspective. Despite the tremendous advances in mass spectrometry and efforts dedicated to the development of ad hoc highly sophisticated methods, phosphorylation site inference and associated kinase identification are still unresolved problems in kinome biology. The sequence and structure of the substrate near-site context are not sufficient alone to model the in vivo phosphorylation rules, and they should be integrated with orthogonal information in all possible applications. Here we provide an overview of the different contexts that contribute to protein phosphorylation, discussing their potential impact in phosphorylation site annotation and in predicting kinase-substrate specificity.

Spermatid cyst polarization in Drosophila depends upon apkc and the CPEB family translational regulator orb2

Mature Drosophila sperm are highly polarized cells—on one side is a nearly 2 mm long flagellar tail that comprises most of the cell, while on the other is the sperm head, which carries the gamete's genetic information. The polarization of the sperm cells commences after meiosis is complete and the 64-cell spermatid cyst begins the process of differentiation. The spermatid nuclei cluster to one side of the cyst, while the flagellar axonemes grows from the other. The elongating spermatid bundles are also polarized with respect to the main axis of the testis; the sperm heads are always oriented basally, while the growing tails extend apically. This orientation within the testes is important for transferring the mature sperm into the seminal vesicles. We show here that orienting cyst polarization with respect to the main axis of the testis depends upon atypical Protein Kinase C (aPKC), a factor implicated in polarity decisions in many different biological contexts. When apkc activity is compromised in the male germline, the direction of cyst polarization within this organ is randomized. Significantly, the mechanisms used to spatially restrict apkc activity to the apical side of the spermatid cyst are different from the canonical cross-regulatory interactions between this kinase and other cell polarity proteins that normally orchestrate polarization. We show that the asymmetric accumulation of aPKC protein in the cyst depends on an mRNA localization pathway that is regulated by the Drosophila CPEB protein Orb2. orb2 is required to properly localize and activate the translation of apkc mRNAs in polarizing spermatid cysts. We also show that orb2 functions not only in orienting cyst polarization with respect to the apical-basal axis of the testis, but also in the process of polarization itself. One of the orb2 targets in this process is its own mRNA. Moreover, the proper execution of this orb2 autoregulatory pathway depends upon apkc.

After completion of meiosis, the 64 cells in the spermatid cyst begin differentiating into sperm. Sperm are highly polarized cells and a critical step in their differentiation is spermatid cyst polarization. Spermatids are also polarized within the testis, with the heads of the elongating spermatids located basally, while the tails extend apically. We show that aPKC accumulates preferentially on the apical side of the cyst during polarization and is required to correctly orient cyst polarization with respect to the apical-basal axis of the testis. Unexpectedly, aPKC activity is spatially restricted by a mechanism that depends upon the CPEB family translational regulator orb2. orb2 is required to asymmetrically localize and activate the translation of apkc mRNAs during spermatid differentiation. In addition to correctly orienting the direction of cyst polarization, orb2 is required for the process of polarization itself. One of the orb2 regulatory targets in this process is its own mRNA, and this autoregulatory activity depends, in turn, upon apkc.