DeepNphos: A deep-learning architecture for prediction of N-phosphorylation sites

MOTIVATION

Phosphorylation, a prevalent post-translational modification, plays a crucial role in regulating cellular activities. This process encompasses O-phosphorylation (e.g., phosphoserine) and N-phosphorylation (e.g., phospho-lysine (pK), phospho-arginine (pR), and phospho-histidine (pH)). While significant research has focused on O-phosphorylation, resulting in the development of various algorithms for predicting O-phosphorylation sites with commendable performance, there has been a notable absence of models designed to predict N-phosphorylation sites. This study introduces an integrated model named DeepNphos, designed to predict N-phosphorylation sites. This model is developed based on the analysis of thousands of experimentally identified pK, pR and pH sites.

RESULTS

Observing that the Convolutional Neural Network (CNN) model, incorporating the One-Hot encoding feature, demonstrates favorable performance in comparison to other models when predicting pK, pR, and pH sites. Additionally, pK exhibits similarities to other lysine modification types, and integrating the CNN model with a deep-transfer learning (DTL) strategy based on tens of thousands of known lysine modification sites could enhance pK prediction performance. In contrast, pR exhibits little similarity to other arginine modification types, and the integration of DTL has minimal impact on pR prediction performance. Furthermore, the decision was made to refrain from incorporating the DTL strategy in predicting pH sites, given the scarcity of histidine modification sites beyond those associated with pH. The final classifiers for predicting pK, pR, and pH sites achieve AUC values of 0.856, 0.805 and 0.802 for ten-fold cross-validation, respectively. Overall, DeepNphos is the first classifier for predicting N-phosphorylation sites, accessible at https://github.com/ChangXulinmessi/DeepNPhos.

PhosBoost: Improved phosphorylation prediction recall using gradient boosting and protein language models

Protein phosphorylation is a dynamic and reversible post-translational modification that regulates a variety of essential biological processes. The regulatory role of phosphorylation in cellular signaling pathways, protein-protein interactions, and enzymatic activities has motivated extensive research efforts to understand its functional implications. Experimental protein phosphorylation data in plants remains limited to a few species, necessitating a scalable and accurate prediction method. Here, we present PhosBoost, a machine-learning approach that leverages protein language models and gradient-boosting trees to predict protein phosphorylation from experimentally derived data. Trained on data obtained from a comprehensive plant phosphorylation database, qPTMplants, we compared the performance of PhosBoost to existing protein phosphorylation prediction methods, PhosphoLingo and DeepPhos. For serine and threonine prediction, PhosBoost achieved higher recall than PhosphoLingo and DeepPhos (.78, .56, and .14, respectively) while maintaining a competitive area under the precision-recall curve (.54, .56, and .42, respectively). PhosphoLingo and DeepPhos failed to predict any tyrosine phosphorylation sites, while PhosBoost achieved a recall score of .6. Despite the precision-recall tradeoff, PhosBoost offers improved performance when recall is prioritized while consistently providing more confident probability scores. A sequence-based pairwise alignment step improved prediction results for all classifiers by effectively increasing the number of inferred positive phosphosites. We provide evidence to show that PhosBoost models are transferable across species and scalable for genome-wide protein phosphorylation predictions. PhosBoost is freely and publicly available on GitHub.

LMPhosSite: A Deep Learning-Based Approach for General Protein Phosphorylation Site Prediction Using Embeddings from the Local Window Sequence and Pretrained Protein Language Model

Phosphorylation is one of the most important post-translational modifications and plays a pivotal role in various cellular processes. Although there exist several computational tools to predict phosphorylation sites, existing tools have not yet harnessed the knowledge distilled by pretrained protein language models. Herein, we present a novel deep learning-based approach called LMPhosSite for the general phosphorylation site prediction that integrates embeddings from the local window sequence and the contextualized embedding obtained using global (overall) protein sequence from a pretrained protein language model to improve the prediction performance. Thus, the LMPhosSite consists of two base-models: one for capturing effective local representation and the other for capturing global per-residue contextualized embedding from a pretrained protein language model. The output of these base-models is integrated using a score-level fusion approach. LMPhosSite achieves a precision, recall, Matthew's correlation coefficient, and F1-score of 38.78%, 67.12%, 0.390, and 49.15%, for the combined serine and threonine independent test data set and 34.90%, 62.03%, 0.298, and 44.67%, respectively, for the tyrosine independent test data set, which is better than the compared approaches. These results demonstrate that LMPhosSite is a robust computational tool for the prediction of the general phosphorylation sites in proteins.

Golgi_DF: Golgi proteins classification with deep forest

Introduction

Golgi is one of the components of the inner membrane system in eukaryotic cells. Its main function is to send the proteins involved in the synthesis of endoplasmic reticulum to specific parts of cells or secrete them outside cells. It can be seen that Golgi is an important organelle for eukaryotic cells to synthesize proteins. Golgi disorders can cause various neurodegenerative and genetic diseases, and the accurate classification of Golgi proteins is helpful to develop corresponding therapeutic drugs.

Methods

This paper proposed a novel Golgi proteins classification method, which is Golgi_DF with the deep forest algorithm. Firstly, the classified proteins method can be converted the vector features containing various information. Secondly, the synthetic minority oversampling technique (SMOTE) is utilized to deal with the classified samples. Next, the Light GBM method is utilized to feature reduction. Meanwhile, the features can be utilized in the penultimate dense layer. Therefore, the reconstructed features can be classified with the deep forest algorithm.

Results

In Golgi_DF, this method can be utilized to select the important features and identify Golgi proteins. Experiments show that the well-performance than the other art-of-the state methods. Golgi_DF as a standalone tools, all its source codes publicly available at https://github.com/baowz12345/golgiDF.

Discussion

Golgi_DF employed reconstructed feature to classify the Golgi proteins. Such method may achieve more available features among the UniRep features.

Ensemble learning-based feature selection for phosphorylation site detection

SARS-COV-2 is prevalent all over the world, causing more than six million deaths and seriously affecting human health. At present, there is no specific drug against SARS-COV-2. Protein phosphorylation is an important way to understand the mechanism of SARS -COV-2 infection. It is often expensive and time-consuming to identify phosphorylation sites with specific modified residues through experiments. A method that uses machine learning to make predictions about them is proposed. As all the methods of extracting protein sequence features are knowledge-driven, these features may not be effective for detecting phosphorylation sites without a complete understanding of the mechanism of protein. Moreover, redundant features also have a great impact on the fitting degree of the model. To solve these problems, we propose a feature selection method based on ensemble learning, which firstly extracts protein sequence features based on knowledge, then quantifies the importance score of each feature based on data, and finally uses the subset of important features as the final features to predict phosphorylation sites.

SgRNA-RF: Identification of SgRNA On-Target Activity With Imbalanced Datasets

Single-guide RNA is a guide RNA (gRNA), which guides the insertion or deletion of uridine residues into kinetoplastid during RNA editing. It is a small non-coding RNA that can be combined with pre -mRNA pairing. SgRNA is a critical component of the CRISPR/Cas9 gene knockout system and play an important role in gene editing and gene regulation. It is important to accurately and quickly identify highly on-target activity sgRNAs. Due to its importance, several computational predictors have been proposed to predict sgRNAs on-target activity. All these methods have clearly contributed to the development of this very important field. However, they also have certain limitations. In the paper, we developed a new classifier SgRNA-RF, which extracts the features of nucleic acid composition and structure of on-target activity sgRNA sequence and identified by random forest algorithm. In addition to solving an imbalanced dataset, this paper proposed a new method called CS-Smote. We compared sgRNA-RF with state-of-the-art predictors on the five datasets, and found SgRNA-RF significantly improved the identification accuracy, with accuracies of 0.8636,0.9161,0.894,0.938,0.965,0.77,0.979,0.973, respectively. The user-friendly web server that implements sgRNA-RF is freely available at http://server.malab.cn/sgRNA-RF/.

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.

Biological Sequence Classification: A Review on Data and General Methods

With the rapid development of biotechnology, the number of biological sequences has grown exponentially. The continuous expansion of biological sequence data promotes the application of machine learning in biological sequences to construct predictive models for mining biological sequence information. There are many branches of biological sequence classification research. In this review, we mainly focus on the function and modification classification of biological sequences based on machine learning. Sequence-based prediction and analysis are the basic tasks to understand the biological functions of DNA, RNA, proteins, and peptides. However, there are hundreds of classification models developed for biological sequences, and the quite varied specific methods seem dizzying at first glance. Here, we aim to establish a long-term support website ( http://lab.malab.cn/~acy/BioseqData/home.html ), which provides readers with detailed information on the classification method and download links to relevant datasets. We briefly introduce the steps to build an effective model framework for biological sequence data. In addition, a brief introduction to single-cell sequencing data analysis methods and applications in biology is also included. Finally, we discuss the current challenges and future perspectives of biological sequence classification research.

iR5hmcSC: Identifying RNA 5-hydroxymethylcytosine with multiple features based on stacking learning

RNA 5-hydroxymethylcytosine (5hmC) modification is the basis of the translation of genetic information and the biological evolution. The study of its distribution in transcriptome is fundamentally crucial to reveal the biological significance of 5hmC. Biochemical experiments can use a variety of sequencing-based technologies to achieve high-throughput identification of 5hmC; however, they are labor-intensive, time-consuming, as well as expensive. Therefore, it is urgent to develop more effective and feasible computational methods. In this paper, a novel and powerful model called iR5hmcSC is designed for identifying 5hmC. Firstly, we extract the different features by K-mer, Pseudo Structure Status Composition and One-Hot encoding. Subsequently, the combination of chi-square test and logistic regression is utilized as the feature selection method to select the optimal feature sets. And then stacking learning, an ensemble learning method including random forest (RF), extra trees (EX), AdaBoost (Ada), gradient boosting decision tree (GBDT), and support vector machine (SVM), is used to recognize 5hmC and non-5hmC. Finally, 10-fold cross-validation test is performed to evaluate the model. The accuracy reaches 85.27% and 79.92% on benchmark dataset and independent dataset, respectively. The result is better than the state-of-the-art methods, which indicates that our model is a feasible tool to identify 5hmC. The datasets and source code are freely available at https://github.com/HongyanShi026/iR5hmcSC.

Machine Learning Methods in Prediction of Protein Palmitoylation Sites: A Brief Review

Protein palmitoylation is a fundamental and reversible post-translational lipid modification that involves a series of biological processes. Although a large number of experimental studies have explored the molecular mechanism behind the palmitoylation process, the computational methods has attracted much attention for its good performance in predicting palmitoylation sites compared with expensive and time-consuming biochemical experiments. The prediction of protein palmitoylation sites is helpful to reveal its biological mechanism. Therefore, the research on the application of machine learning methods to predict palmitoylation sites has become a hot topic in bioinformatics and promoted the development in the related fields. In this review, we briefly introduced the recent development in predicting protein palmitoylation sites by using machine learningbased methods and discussed their benefits and drawbacks. The perspective of machine learning-based methods in predicting palmitoylation sites was also provided. We hope the review could provide a guide in related fields.

DeepIPs: comprehensive assessment and computational identification of phosphorylation sites of SARS-CoV-2 infection using a deep learning-based approach

The rapid spread of SARS-CoV-2 infection around the globe has caused a massive health and socioeconomic crisis. Identification of phosphorylation sites is an important step for understanding the molecular mechanisms of SARS-CoV-2 infection and the changes within the host cells pathways. In this study, we present DeepIPs, a first specific deep-learning architecture to identify phosphorylation sites in host cells infected with SARS-CoV-2. DeepIPs consists of the most popular word embedding method and convolutional neural network-long short-term memory network architecture to make the final prediction. The independent test demonstrates that DeepIPs improves the prediction performance compared with other existing tools for general phosphorylation sites prediction. Based on the proposed model, a web-server called DeepIPs was established and is freely accessible at http://lin-group.cn/server/DeepIPs. The source code of DeepIPs is freely available at the repository https://github.com/linDing-group/DeepIPs.

Predicting phosphorylation sites using machine learning by integrating the sequence, structure, and functional information of proteins

BACKGROUND

Post-translational modification (PTM) is a biological process that alters proteins and is therefore involved in the regulation of various cellular activities and pathogenesis. Protein phosphorylation is an essential process and one of the most-studied PTMs: it occurs when a phosphate group is added to serine (Ser, S), threonine (Thr, T), or tyrosine (Tyr, Y) residue. Dysregulation of protein phosphorylation can lead to various diseases-most commonly neurological disorders, Alzheimer's disease, and Parkinson's disease-thus necessitating the prediction of S/T/Y residues that can be phosphorylated in an uncharacterized amino acid sequence. Despite a surplus of sequencing data, current experimental methods of PTM prediction are time-consuming, costly, and error-prone, so a number of computational methods have been proposed to replace them. However, phosphorylation prediction remains limited, owing to substrate specificity, performance, and the diversity of its features.

METHODS

In the present study we propose machine-learning-based predictors that use the physicochemical, sequence, structural, and functional information of proteins to classify S/T/Y phosphorylation sites. Rigorous feature selection, the minimum redundancy/maximum relevance approach, and the symmetrical uncertainty method were employed to extract the most informative features to train the models.

RESULTS

The RF and SVM models generated using diverse feature types in the present study were highly accurate as is evident from good values for different statistical measures. Moreover, independent test sets and benchmark validations indicated that the proposed method clearly outperformed the existing methods, demonstrating its ability to accurately predict protein phosphorylation.

CONCLUSIONS

The results obtained in the present work indicate that the proposed computational methodology can be effectively used for predicting putative phosphorylation sites further facilitating discovery of various biological processes mechanisms.

A Transfer Learning-Based Approach for Lysine Propionylation Prediction

Lysine propionylation is a newly discovered posttranslational modification (PTM) and plays a key role in the cellular process. Although proteomics techniques was capable of detecting propionylation, large-scale detection was still challenging. To bridge this gap, we presented a transfer learning-based method for computationally predicting propionylation sites. The recurrent neural network-based deep learning model was trained firstly by the malonylation and then fine-tuned by the propionylation. The trained model served as feature extractor where protein sequences as input were translated into numerical vectors. The support vector machine was used as the final classifier. The proposed method reached a matthews correlation coefficient (MCC) of 0.6615 on the 10-fold crossvalidation and 0.3174 on the independent test, outperforming state-of-the-art methods. The enrichment analysis indicated that the propionylation was associated with these GO terms (GO:0016620, GO:0051287, GO:0003735, GO:0006096, and GO:0005737) and with metabolism. We developed a user-friendly online tool for predicting propoinylation sites which is available at http://47.113.117.61/.

iORI-ENST: identifying origin of replication sites based on elastic net and stacking learning

DNA replication is not only the basis of biological inheritance but also the most fundamental process in all living organisms. It plays a crucial role in the cell-division cycle and gene expression regulation. Hence, the accurate identification of the origin of replication sites (ORIs) has a great meaning for further understanding the regulatory mechanism of gene expression and treating genic diseases. In this paper, a novel, feasible and powerful model, namely, iORI-ENST is designed for identifying ORIs. Firstly, we extract the different features by incorporating mono-nucleotide binary encoding and dinucleotide-based spatial autocorrelation. Subsequently, elastic net is utilized as the feature selection method to select the optimal feature set. And then stacking learning is employed to predict ORIs and non-ORIs, which contains random forest, adaboost, gradient boosting decision tree, extra trees and support vector machine. Finally, the ORI sites are identified on the benchmark datasets S1 and S2 with their accuracies of 91.41% and 95.07%, respectively. Meanwhile, an independent dataset S3 is employed to verify the validation and transferability of our model and its accuracy reaches 91.10%. Comparing with state-of-the-art methods, our model achieves more remarkable performance. The results show our model is a feasible, effective and powerful tool for identifying ORIs. The source code and datasets are available at https://github.com/YingyingYao/iORI-ENST.

sgRNACNN: identifying sgRNA on-target activity in four crops using ensembles of convolutional neural networks

KEY MESSAGE

We proposed an ensemble convolutional neural network model to identify sgRNA high on-target activity in four crops and we used one-hot encoding and k-mers for sequence encoding. As an important component of the CRISPR/Cas9 system, single-guide RNA (sgRNA) plays an important role in gene redirection and editing. sgRNA has played an important role in the improvement of agronomic species, but there is a lack of effective bioinformatics tools to identify the activity of sgRNA in agronomic species. Therefore, it is necessary to develop a method based on machine learning to identify sgRNA high on-target activity. In this work, we proposed a simple convolutional neural network method to identify sgRNA high on-target activity. Our study used one-hot encoding and k-mers for sequence data conversion and a voting algorithm for constructing the convolutional neural network ensemble model sgRNACNN for the prediction of sgRNA activity. The ensemble model sgRNACNN was used for predictions in four crops: Glycine max, Zea mays, Sorghum bicolor and Triticum aestivum. The accuracy rates of the four crops in the sgRNACNN model were 82.43%, 80.33%, 78.25% and 87.49%, respectively. The experimental results showed that sgRNACNN realizes the identification of high on-target activity sgRNA of agronomic data and can meet the demands of sgRNA activity prediction in agronomy to a certain extent. These results have certain significance for guiding crop gene editing and academic research. The source code and relevant dataset can be found in the following link: https://github.com/nmt315320/sgRNACNN.git .

BBPpred: Sequence-Based Prediction of Blood-Brain Barrier Peptides with Feature Representation Learning and Logistic Regression

Blood-brain barrier peptides (BBPs) have a large range of biomedical applications since they can cross the blood-brain barrier based on different mechanisms. As experimental methods for the identification of BBPs are laborious and expensive, computational approaches are necessary to be developed for predicting BBPs. In this work, we describe a computational method, BBPpred (blood-brain barrier peptides prediction), that can efficiently identify BBPs using logistic regression. We investigate a wide variety of features from amino acid sequence information, and then a feature learning method is adopted to represent the informative features. To improve the prediction performance, seven informative features are selected for classification by eliminating redundant and irrelevant features. In addition, we specifically create two benchmark data sets (training and independent test), which contain a total of 119 BBPs from public databases and the literature. On the training data set, BBPpred shows promising performances with an AUC score of 0.8764 and an AUPR score of 0.8757 using the 10-fold cross-validation. We also test our new method on the independent test data set and obtain a favorable performance. We envision that BBPpred will be a useful tool for identifying, annotating, and characterizing BBPs. BBPpred is freely available at http://BBPpred.xialab.info.

Distinguishing Enzymes and Non-enzymes Based on Structural Information with an Alignment Free Approach

Background:

Knowledge of protein functions is very crucial for the understanding of biological processes. Experimental methods for protein function prediction are powerless to treat the growing amount of protein sequence and structure data.

Objective:

To develop some computational techniques for the protein function prediction.

Method:

Based on the residue interaction network features and the motion mode information, an SVM model was constructed and used as the predictor. The role of these features was analyzed and some interesting results were obtained.

Results:

An alignment-free method for the classification of enzyme and non-enzyme is developed in this work. There is not any single feature that occupies a dominant position in the prediction process. The topological and the information-theoretic residue interaction network features have a better performance. The combination of the fast mode and the slow mode can get a better explanation for the classification result.

Conclusion:

The method proposed in this paper can act as a classifier for the enzymes and nonenzymes.

DeepPSP: A Global-Local Information-Based Deep Neural Network for the Prediction of Protein Phosphorylation Sites

Identification of phosphorylation sites is an important step in the function study and drug design of proteins. In recent years, there have been increasing applications of the computational method in the identification of phosphorylation sites because of its low cost and high speed. Most of the currently available methods focus on using local information around potential phosphorylation sites for prediction and do not take the global information of the protein sequence into consideration. Here, we demonstrated that the global information of protein sequences may be also critical for phosphorylation site prediction. In this paper, a new deep neural network model, called DeepPSP, was proposed for the prediction of protein phosphorylation sites. In the DeepPSP model, two parallel modules were introduced to extract both local and global features from protein sequences. Two squeeze-and-excitation blocks and one bidirectional long short-term memory block were introduced into each module to capture effective representations of the sequences. Comparative studies were carried out to evaluate the performance of DeepPSP, and four other prediction methods using public data sets The F1-score, area under receiver operating characteristic curves (AUROC), and area under precision-recall curves (AUPRC) of DeepPSP were found to be 0.4819, 0.82, and 0.50, respectively, for S/T general site prediction and 0.4206, 0.73, and 0.39, respectively, for Y general site prediction. Compared with the MusiteDeep method, the F1-score, AUROC, and AUPRC of DeepPSP were found to increase by 8.6, 2.5, and 8.7%, respectively, for S/T general site prediction and by 20.6, 5.8, and 18.2%, respectively, for Y general site prediction. Among the tested methods, the developed DeepPSP method was also found to produce best results for different kinase-specific site predictions including CDK, mitogen-activated protein kinase, CAMK, AGC, and CMGC. Taken together, the developed DeepPSP method may offer a more accurate phosphorylation site prediction by including global information. It may serve as an alternative model with better performance and interpretability for protein phosphorylation site prediction.

Deep Learning in Proteomics

Proteomics, the study of all the proteins in biological systems, is becoming a data-rich science. Protein sequences and structures are comprehensively catalogued in online databases. With recent advancements in tandem mass spectrometry (MS) technology, protein expression and post-translational modifications (PTMs) can be studied in a variety of biological systems at the global scale. Sophisticated computational algorithms are needed to translate the vast amount of data into novel biological insights. Deep learning automatically extracts data representations at high levels of abstraction from data, and it thrives in data-rich scientific research domains. Here, a comprehensive overview of deep learning applications in proteomics, including retention time prediction, MS/MS spectrum prediction, de novo peptide sequencing, PTM prediction, major histocompatibility complex-peptide binding prediction, and protein structure prediction, is provided. Limitations and the future directions of deep learning in proteomics are also discussed. This review will provide readers an overview of deep learning and how it can be used to analyze proteomics data.

Identification of Latent Oncogenes with a Network Embedding Method and Random Forest

Oncogene is a special type of genes, which can promote the tumor initiation. Good study on oncogenes is helpful for understanding the cause of cancers. Experimental techniques in early time are quite popular in detecting oncogenes. However, their defects become more and more evident in recent years, such as high cost and long time. The newly proposed computational methods provide an alternative way to study oncogenes, which can provide useful clues for further investigations on candidate genes. Considering the limitations of some previous computational methods, such as lack of learning procedures and terming genes as individual subjects, a novel computational method was proposed in this study. The method adopted the features derived from multiple protein networks, viewing proteins in a system level. A classic machine learning algorithm, random forest, was applied on these features to capture the essential characteristic of oncogenes, thereby building the prediction model. All genes except validated oncogenes were ranked with a measurement yielded by the prediction model. Top genes were quite different from potential oncogenes discovered by previous methods, and they can be confirmed to become novel oncogenes. It was indicated that the newly identified genes can be essential supplements for previous results.

DeepAdd: Protein function prediction from k-mer embedding and additional features

With the application of new high throughput sequencing technology, a large number of protein sequences is becoming available. Determination of the functional characteristics of these proteins by experiments is an expensive endeavor that requires a lot of time. Furthermore, at the organismal level, such kind of experimental functional analyses can be conducted only for a very few selected model organisms. Computational function prediction methods can be used to fill this gap. The functions of proteins are classified by Gene Ontology (GO), which contains more than 40,000 classifications in three domains, Molecular Function (MF), Biological Process (BP), and Cellular Component (CC). Additionally, since proteins have many functions, function prediction represents a multi-label and multi-class problem. We developed a new method to predict protein function from sequence. To this end, natural language model was used to generate word embedding of sequence and learn features from it by deep learning, and additional features to locate every protein. Our method uses the dependencies between GO classes as background information to construct a deep learning model. We evaluate our method using the standards established by the Computational Assessment of Function Annotation (CAFA) and have noticeable improvement over several algorithms, such as FFPred, DeepGO, GoFDR and other methods compared on the CAFA3 datasets.

DeepPPSite: A deep learning-based model for analysis and prediction of phosphorylation sites using efficient sequence information

Phosphorylation is a ubiquitous type of post-translational modification (PTM) that occurs in both eukaryotic and prokaryotic cells where in a phosphate group binds with amino acid residues. These specific residues, i.e., serine (S), threonine (T), and tyrosine (Y), exhibit diverse functions at the molecular level. Recent studies have determined that some diseases such as cancer, diabetes, and neurodegenerative diseases are caused by abnormal phosphorylation. Based on its potential applications in biological research and drug development, the large-scale identification of phosphorylation sites has attracted interest. Existing wet-lab technologies for targeting phosphorylation sites are overpriced and time consuming. Thus, computational algorithms that can efficiently accelerate the annotation of phosphorylation sites from massive protein sequences are needed. Numerous machine learning-based methods have been implemented for phosphorylation sites prediction. However, despite extensive efforts, existing computational approaches continue to have inadequate performance, particularly in terms of overall ACC, MCC, and AUC. In this paper, we report a novel deep learning-based predictor to overcome these performance hurdles, DeepPPSite, which was constructed using a stacked long short-term memory recurrent network for predicting phosphorylation sites. The proposed technique expediently learns the protein representations from conjoint protein descriptors. The experimental results indicated that our model achieved superior performance on the training dataset for S, T and Y, with MCC values of 0.608, 0.602, and 0.558, respectively, using a 10-fold cross-validation test. We further determined the generalization efficacy of the proposed predictor DeepPPSite by conducting a rigorous independent test. The predictive MCC values were 0.358, 0.356, and 0.350 for the S, T, and Y phosphorylation sites, respectively. Rigorous cross-validation and independent validation tests for the three types of phosphorylation sites demonstrated that the designed DeepPPSite tool significantly outperforms state-of-the-art methods.

Hidden dynamic signatures drive substrate selectivity in the disordered phosphoproteome

The discovery that more than 40% of the eukaryotic proteome is intrinsically disordered, and that these disordered segments are enriched in phosphorylation sites, suggests that conformational heterogeneity may be important to kinase selectivity. Indeed, phosphorylation prediction programs reliant on classic notions of conserved sequence information (i.e., “vertical information”) are only partially effective. We find that the conformational equilibrium of the phosphorylatable site, whose information is embedded in sequence-averaged energetic and structural properties of the protein (i.e., “horizontal information”), plays a major role in distinguishing phosphorylatable versus nonphosphorylatable sites. In fact, employing both horizontal and vertical information produces a state-of-the-art phosphorylation predictor, wherein the conformational equilibrium of the disordered chain is the dominant contributor.

Phosphorylation sites are hyperabundant in the eukaryotic disordered proteome, suggesting that conformational fluctuations play a major role in determining to what extent a kinase interacts with a particular substrate. In biophysical terms, substrate selectivity may be determined not just by the structural–chemical complementarity between the kinase and its protein substrates but also by the free energy difference between the conformational ensembles that are, or are not, recognized by the kinase. To test this hypothesis, we developed a statistical-thermodynamics-based informatics framework, which allows us to probe for the contribution of equilibrium fluctuations to phosphorylation, as evaluated by the ability to predict Ser/Thr/Tyr phosphorylation sites in the disordered proteome. Essential to this framework is a decomposition of substrate sequence information into two types: vertical information encoding conserved kinase specificity motifs and horizontal information encoding substrate conformational equilibrium that is embedded, but often not apparent, within position-specific conservation patterns. We find not only that conformational fluctuations play a major role but also that they are the dominant contribution to substrate selectivity. In fact, the main substrate classifier distinguishing selectivity is the magnitude of change in local compaction of the disordered chain upon phosphorylation of these mostly singly phosphorylated sites. In addition to providing fundamental insights into the consequences of phosphorylation across the proteome, our approach provides a statistical-thermodynamic strategy for partitioning any sequence-based search into contributions from structural–chemical complementarity and those from changes in conformational equilibrium.

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.

Use Chou’s 5-Step Rule to Classify Protein Modification Sites with Neural Network

Lysine malonylation is a novel-type protein post-translational modification and plays essential roles in many biological activities. Having a good knowledge of malonylation sites can provide guidance in many issues, including disease prevention and drug discovery and other related fields. There are several experimental approaches to identify modification sites in the field of biology. However, these methods seem to be expensive. In this study, we proposed malNet, which employed neural network and utilized several novel and effective feature description methods. It was pointed that ANN’s performance is better than other models. Furthermore, we trained the classifiers according to an original crossvalidation method named Split to Equal validation (SEV). The results achieved AUC value of 0.6684, accuracy of 54.93%, and MCC of 0.1045, which showed great improvement than before.

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.

Capsule network for protein post-translational modification site prediction

MOTIVATION

Computational methods for protein post-translational modification (PTM) site prediction provide a useful approach for studying protein functions. The prediction accuracy of the existing methods has significant room for improvement. A recent deep-learning architecture, Capsule Network (CapsNet), which can characterize the internal hierarchical representation of input data, presents a great opportunity to solve this problem, especially using small training data.

RESULTS

We proposed a CapsNet for predicting protein PTM sites, including phosphorylation, N-linked glycosylation, N6-acetyllysine, methyl-arginine, S-palmitoyl-cysteine, pyrrolidone-carboxylic-acid and SUMOylation sites. The CapsNet outperformed the baseline convolutional neural network architecture MusiteDeep and other well-known tools in most cases and provided promising results for practical use, especially in learning from small training data. The capsule length also gives an accurate estimate for the confidence of the PTM prediction. We further demonstrated that the internal capsule features could be trained as a motif detector of phosphorylation sites when no kinase-specific phosphorylation labels were provided. In addition, CapsNet generates robust representations that have strong discriminant power in distinguishing kinase substrates from different kinase families. Our study sheds some light on the recognition mechanism of PTMs and applications of CapsNet on other bioinformatic problems.

AVAILABILITY AND IMPLEMENTATION

The codes are free to download from https://github.com/duolinwang/CapsNet_PTM.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Predicting Protein Phosphorylation Sites Based on Deep Learning

Background:

Protein phosphorylation is one of the most important Post-translational Modifications (PTMs) occurring at amino acid residues serine (S), threonine (T), and tyrosine (Y). It plays critical roles in protein structure and function predicting. With the development of novel high-throughput sequencing technologies, there are a huge amount of protein sequences being generated and stored in databases.

Objective:

It is of great importance in both basic research and drug development to quickly and accurately predict which residues of S, T, or Y can be phosphorylated.

Methods:

In order to solve the problem, a novel hybrid deep learning model with a convolutional neural network and bi-directional long short-term memory recurrent neural network (CNN+BLSTM) is proposed for predicting phosphorylation sites in proteins. The model contains a list of layers that transform the input data into an output class, in which the convolution layer captures higher-level abstraction features of amino acid, while the recurrent layer captures long-term dependencies between amino acids to improve predictions. The joint model learns interactions between higher-level features derived from the protein sequence to predict the phosphorylated sites.

Results:

We applied our model together with two canonical methods namely iPhos-PseEn and MusiteDeep. A 5-fold cross-validation process indicated that CNN+BLSTM outperforms the two competitors in various evaluation metrics like the area under the receiver operating characteristic and precision-recall curves, the Matthews correlation coefficient, F-measure, accuracy, and so on.

Conclusion:

CNN+BLSTM is promising in identifying potential protein phosphorylation for further experimental validation.

Prediction of 2-hydroxyisobutyrylation sites by integrating multiple sequence features with ensemble support vector machine

Lysine 2-hydroxyisobutyrylation (Khib) is a new type of histone mark, which has been found to affect the association between histone and DNA. To better understand the molecular mechanism of Khib, it is important to identify 2-hydroxyisobutyrylated substrates and their corresponding Khib sites accurately. In this study, a novel bioinformatics tool named KhibPred is proposed to predict Khib sites in human HeLa cells. Three kinds of effective features, the composition of k-spaced amino acid pairs, binary encoding and amino acid factors, are incorporated to encode Khib sites. Moreover, an ensemble support vector machine is employed to overcome the imbalanced problem in the prediction. As illustrated by 10-fold cross-validation, the performance of KhibPred achieves a satisfactory performance with an area under receiver operating characteristic curve of 0.7937. Therefore, KhibPred can be a useful tool for predicting protein Khib sites. Feature analysis shows that the polarity factor features play significant roles in the prediction of Khib sites. The conclusions derived from this study might provide useful insights for in-depth investigation into the molecular mechanisms of Khib.

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.

CirRNAPL: A web server for the identification of circRNA based on extreme learning machine

Circular RNA (circRNA) plays an important role in the development of diseases, and it provides a novel idea for drug development. Accurate identification of circRNAs is important for a deeper understanding of their functions. In this study, we developed a new classifier, CirRNAPL, which extracts the features of nucleic acid composition and structure of the circRNA sequence and optimizes the extreme learning machine based on the particle swarm optimization algorithm. We compared CirRNAPL with existing methods, including blast, on three datasets and found CirRNAPL significantly improved the identification accuracy for the three datasets, with accuracies of 0.815, 0.802, and 0.782, respectively. Additionally, we performed sequence alignment on 564 sequences of the independent detection set of the third data set and analyzed the expression level of circRNAs. Results showed the expression level of the sequence is positively correlated with the abundance. A user-friendly CirRNAPL web server is freely available at http://server.malab.cn/CirRNAPL/.

Predicting ATP-Binding Cassette Transporters Using the Random Forest Method

ATP-binding cassette (ABC) proteins play important roles in a wide variety of species. These proteins are involved in absorbing nutrients, exporting toxic substances, and regulating potassium channels, and they contribute to drug resistance in cancer cells. Therefore, the identification of ABC transporters is an urgent task. The present study used 188D as the feature extraction method, which is based on sequence information and physicochemical properties. We also visualized the feature extracted by t-Distributed Stochastic Neighbor Embedding (t-SNE). The sample based on the features extracted by 188D may be separated. Further, random forest (RF) is an efficient classifier to identify proteins. Under the 10-fold cross-validation of the model proposed here for a training set, the average accuracy rate of 10 training sets was 89.54%. We obtained values of 0.87 for specificity, 0.92 for sensitivity, and 0.79 for MCC. In the testing set, the accuracy achieved was 89%. These results suggest that the model combining 188D with RF is an optimal tool to identify ABC transporters.

RF-PseU: A Random Forest Predictor for RNA Pseudouridine Sites

One of the ubiquitous chemical modifications in RNA, pseudouridine modification is crucial for various cellular biological and physiological processes. To gain more insight into the functional mechanisms involved, it is of fundamental importance to precisely identify pseudouridine sites in RNA. Several useful machine learning approaches have become available recently, with the increasing progress of next-generation sequencing technology; however, existing methods cannot predict sites with high accuracy. Thus, a more accurate predictor is required. In this study, a random forest-based predictor named RF-PseU is proposed for prediction of pseudouridylation sites. To optimize feature representation and obtain a better model, the light gradient boosting machine algorithm and incremental feature selection strategy were used to select the optimum feature space vector for training the random forest model RF-PseU. Compared with previous state-of-the-art predictors, the results on the same benchmark data sets of three species demonstrate that RF-PseU performs better overall. The integrated average leave-one-out cross-validation and independent testing accuracy scores were 71.4% and 74.7%, respectively, representing increments of 3.63% and 4.77% versus the best existing predictor. Moreover, the final RF-PseU model for prediction was built on leave-one-out cross-validation and provides a reliable and robust tool for identifying pseudouridine sites. A web server with a user-friendly interface is accessible at http://148.70.81.170:10228/rfpseu.

Exploration of the correlation between GPCRs and drugs based on a learning to rank algorithm

Exploring the protein - drug correlation can not only solve the problem of selecting candidate compounds but also solve related problems such as drug redirection and finding potential drug targets. Therefore, many researchers have proposed different machine learning methods for prediction of protein-drug correlations. However, many existing models simply divide the protein-drug relationship into related or irrelevant categories and do not deeply explore the most relevant target (or drug) for a given drug (or target). In order to solve this problem, this paper applies the ranking concept to the prediction of the GPCR (G Protein-Coupled Receptors)-drug correlation. This study uses two different types of data sets to explore candidate compound and potential target problems, and both sets achieved good results. In addition, this study also found that the family to which a protein belongs is not an inherent factor that affects the ranking of GPCR-drug correlations; however, if the drug affects other family members of the protein, then the protein is likely to be a potential target of the drug. This study showed that the learning to rank algorithm is a good tool for exploring protein-drug correlations.

6mA-RicePred: A Method for Identifying DNA N 6-Methyladenine Sites in the Rice Genome Based on Feature Fusion

MOTIVATION

The biological function of N 6-methyladenine DNA (6mA) in plants is largely unknown. Rice is one of the most important crops worldwide and is a model species for molecular and genetic studies. There are few methods for 6mA site recognition in the rice genome, and an effective computational method is needed.

RESULTS

In this paper, we propose a new computational method called 6mA-Pred to identify 6mA sites in the rice genome. 6mA-Pred employs a feature fusion method to combine advantageous features from other methods and thus obtain a new feature to identify 6mA sites. This method achieved an accuracy of 87.27% in the identification of 6mA sites with 10-fold cross-validation and achieved an accuracy of 85.6% in independent test sets.

Predict New Therapeutic Drugs for Hepatocellular Carcinoma Based on Gene Mutation and Expression

Hepatocellular carcinoma (HCC) is the fourth most common primary liver tumor and is an important medical problem worldwide. However, the use of current therapies for HCC is no possible to be cured, and despite numerous attempts and clinical trials, there are not so many approved targeted treatments for HCC. So, it is necessary to identify additional treatment strategies to prevent the growth of HCC tumors. We are looking for a systematic drug repositioning bioinformatics method to identify new drug candidates for the treatment of HCC, which considers not only aberrant genomic information, but also the changes of transcriptional landscapes. First, we screen the collection of HCC feature genes, i.e., kernel genes, which frequently mutated in most samples of HCC based on human mutation data. Then, the gene expression data of HCC in TCGA are combined to classify the kernel genes of HCC. Finally, the therapeutic score (TS) of each drug is calculated based on the kolmogorov-smirnov statistical method. Using this strategy, we identify five drugs that associated with HCC, including three drugs that could treat HCC and two drugs that might have side-effect on HCC. In addition, we also make Connectivity Map (CMap) profiles similarity analysis and KEGG enrichment analysis on drug targets. All these findings suggest that our approach is effective for accurate predicting novel therapeutic options for HCC and easily to be extended to other tumors.

A Bioinformatics Tool for the Prediction of DNA N6-Methyladenine Modifications Based on Feature Fusion and Optimization Protocol

DNA N⁶-methyladenine (6mA) is closely involved with various biological processes. Identifying the distributions of 6mA modifications in genome-scale is of great significance to in-depth understand the functions. In recent years, various experimental and computational methods have been proposed for this purpose. Unfortunately, existing methods cannot provide accurate and fast 6mA prediction. In this study, we present 6mAPred-FO, a bioinformatics tool that enables researchers to make predictions based on sequences only. To sufficiently capture the characteristics of 6mA sites, we integrate the sequence-order information with nucleotide positional specificity information for feature encoding, and further improve the feature representation capacity by analysis of variance-based feature optimization protocol. The experimental results show that using this feature protocol, we can significantly improve the predictive performance. Via further feature analysis, we found that the sequence-order information and positional specificity information are complementary to each other, contributing to the performance improvement. On the other hand, the improvement is also due to the use of the feature optimization protocol, which is capable of effectively capturing the most informative features from the original feature space. Moreover, benchmarking comparison results demonstrate that our 6mAPred-FO outperforms several existing predictors. Finally, we establish a web-server that implements the proposed method for convenience of researchers' use, which is currently available at http://server.malab.cn/6mAPred-FO.

Robust Prediction of Single and Multiple Point Protein Mutations Stability Changes

Accurate prediction of protein stability changes resulting from amino acid substitutions is of utmost importance in medicine to better understand which mutations are deleterious, leading to diseases, and which are neutral. Since conducting wet lab experiments to get a better understanding of protein mutations is costly and time consuming, and because of huge number of possible mutations the need of computational methods that could accurately predict effects of amino acid mutations is of greatest importance. In this research, we present a robust methodology to predict the energy changes of a proteins upon mutations. The proposed prediction scheme is based on two step algorithm that is a Holdout Random Sampler followed by a neural network model for regression. The Holdout Random Sampler is utilized to analysis the energy change, the corresponding uncertainty, and to obtain a set of admissible energy changes, expressed as a cumulative distribution function. These values are further utilized to train a simple neural network model that can predict the energy changes. Results were blindly tested (validated) against experimental energy changes, giving Pearson correlation coefficients of 0.66 for Single Point Mutations and 0.77 for Multiple Point Mutations. These results confirm the successfulness of our method, since it outperforms majority of previous studies in this field.

Twenty years of bioinformatics research for protease-specific substrate and cleavage site prediction: a comprehensive revisit and benchmarking of existing methods

The roles of proteolytic cleavage have been intensively investigated and discussed during the past two decades. This irreversible chemical process has been frequently reported to influence a number of crucial biological processes (BPs), such as cell cycle, protein regulation and inflammation. A number of advanced studies have been published aiming at deciphering the mechanisms of proteolytic cleavage. Given its significance and the large number of functionally enriched substrates targeted by specific proteases, many computational approaches have been established for accurate prediction of protease-specific substrates and their cleavage sites. Consequently, there is an urgent need to systematically assess the state-of-the-art computational approaches for protease-specific cleavage site prediction to further advance the existing methodologies and to improve the prediction performance. With this goal in mind, in this article, we carefully evaluated a total of 19 computational methods (including 8 scoring function-based methods and 11 machine learning-based methods) in terms of their underlying algorithm, calculated features, performance evaluation and software usability. Then, extensive independent tests were performed to assess the robustness and scalability of the reviewed methods using our carefully prepared independent test data sets with 3641 cleavage sites (specific to 10 proteases). The comparative experimental results demonstrate that PROSPERous is the most accurate generic method for predicting eight protease-specific cleavage sites, while GPS-CCD and LabCaS outperformed other predictors for calpain-specific cleavage sites. Based on our review, we then outlined some potential ways to improve the prediction performance and ease the computational burden by applying ensemble learning, deep learning, positive unlabeled learning and parallel and distributed computing techniques. We anticipate that our study will serve as a practical and useful guide for interested readers to further advance next-generation bioinformatics tools for protease-specific cleavage site prediction.

ACPred-Fuse: fusing multi-view information improves the prediction of anticancer peptides

Fast and accurate identification of the peptides with anticancer activity potential from large-scale proteins is currently a challenging task. In this study, we propose a new machine learning predictor, namely, ACPred-Fuse, that can automatically and accurately predict protein sequences with or without anticancer activity in peptide form. Specifically, we establish a feature representation learning model that can explore class and probabilistic information embedded in anticancer peptides (ACPs) by integrating a total of 29 different sequence-based feature descriptors. In order to make full use of various multiview information, we further fused the class and probabilistic features with handcrafted sequential features and then optimized the representation ability of the multiview features, which are ultimately used as input for training our prediction model. By comparing the multiview features and existing feature descriptors, we demonstrate that the fused multiview features have more discriminative ability to capture the characteristics of ACPs. In addition, the information from different views is complementary for the performance improvement. Finally, our benchmarking comparison results showed that the proposed ACPred-Fuse is more precise and promising in the identification of ACPs than existing predictors. To facilitate the use of the proposed predictor, we built a web server, which is now freely available via http://server.malab.cn/ACPred-Fuse.

Pred-BVP-Unb: Fast prediction of bacteriophage Virion proteins using un-biased multi-perspective properties with recursive feature elimination

Bacteriophage virion proteins (BVPs) are bacterial viruses that have a great impact on different biological functions of bacteria. They are significantly used in genetic engineering and phage therapy applications. Correct identification of BVP through conventional pathogen methods are slow and expensive. Thus, designing a Bioinformatics predictor is urgently desirable to accelerate correct identification of BVPs within a huge volume of proteins. However, available prediction tools performance is inadequate due to the lack of useful feature representation and severe imbalance issue. In the present study, we propose an intelligent model, called Pred-BVP-Unb for discrimination of BVPs that employed three nominal sequences-driven descriptors, i.e. Bi-PSSM evolutionary information, composition & translation, and split amino acid composition. The imbalance phenomena between classes were coped with the help of a synthetic minority oversampling technique. The essential attributes are selected by a robust algorithm called recursive feature elimination. Finally, the optimal feature space is provided to support vector machine classifier using a radial base kernel in order to train the model. Our predictor remarkably outperforms than existing approaches in the literature by achieving the highest accuracy of 92.54% and 83.06% respectively on the benchmark and independent datasets. We expect that Pred-BVP-Unb tool can provide useful hints for designing antibacterial drugs and also helpful to expedite large scale discovery of new bacteriophage virion proteins. The source code and all datasets are publicly available at https://github.com/Muhammad-Arif-NUST/BVP_Pred_Unb.

Boosting phosphorylation site prediction with sequence feature-based machine learning

Protein phosphorylation is one of the essential posttranslation modifications playing a vital role in the regulation of many fundamental cellular processes. We propose a LightGBM-based computational approach that uses evolutionary, geometric, sequence environment, and amino acid-specific features to decipher phosphate binding sites from a protein sequence. Our method, while compared with other existing methods on 2429 protein sequences taken from standard Phospho.ELM (P.ELM) benchmark data set featuring 11 organisms reports a higher F₁ score = 0.504 (harmonic mean of the precision and recall) and ROC AUC = 0.836 (area under the curve of the receiver operating characteristics). The computation time of our proposed approach is much less than that of the recently developed deep learning-based framework. Structural analysis on selected protein sequences informs that our prediction is the superset of the phosphorylation sites, as mentioned in P.ELM data set. The foundation of our scheme is manual feature engineering and a decision tree-based classification. Hence, it is intuitive, and one can interpret the final tree as a set of rules resulting in a deeper understanding of the relationships between biophysical features and phosphorylation sites. Our innovative problem transformation method permits more control over precision and recall as is demonstrated by the fact that if we incorporate output probability of the existing deep learning framework as an additional feature, then our prediction improves (F₁ score = 0.546; ROC AUC = 0.849). The implementation of our method can be accessed at http://cse.iitkgp.ac.in/~pralay/resources/PPSBoost/ and is mirrored at https://cosmos.iitkgp.ac.in/PPSBoost.

Machine learning empowers phosphoproteome prediction in cancers

MOTIVATION

Reversible protein phosphorylation is an essential post-translational modification regulating protein functions and signaling pathways in many cellular processes. Aberrant activation of signaling pathways often contributes to cancer development and progression. The mass spectrometry-based phosphoproteomics technique is a powerful tool to investigate the site-level phosphorylation of the proteome in a global fashion, paving the way for understanding the regulatory mechanisms underlying cancers. However, this approach is time-consuming and requires expensive instruments, specialized expertise and a large amount of starting material. An alternative in silico approach is predicting the phosphoproteomic profiles of cancer patients from the available proteomic, transcriptomic and genomic data.

RESULTS

Here, we present a winning algorithm in the 2017 NCI-CPTAC DREAM Proteogenomics Challenge for predicting phosphorylation levels of the proteome across cancer patients. We integrate four components into our algorithm, including (i) baseline correlations between protein and phosphoprotein abundances, (ii) universal protein-protein interactions, (iii) shareable regulatory information across cancer tissues and (iv) associations among multi-phosphorylation sites of the same protein. When tested on a large held-out testing dataset of 108 breast and 62 ovarian cancer samples, our method ranked first in both cancer tissues, demonstrating its robustness and generalization ability.

AVAILABILITY AND IMPLEMENTATION

Our code and reproducible results are freely available on GitHub: https://github.com/GuanLab/phosphoproteome_prediction.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Fast Prediction of Protein Methylation Sites Using a Sequence-Based Feature Selection Technique

Protein methylation, an important post-translational modification, plays crucial roles in many cellular processes. The accurate prediction of protein methylation sites is fundamentally important for revealing the molecular mechanisms undergoing methylation. In recent years, computational prediction based on machine learning algorithms has emerged as a powerful and robust approach for identifying methylation sites, and much progress has been made in predictive performance improvement. However, the predictive performance of existing methods is not satisfactory in terms of overall accuracy. Motivated by this, we propose a novel random-forest-based predictor called MePred-RF, integrating several discriminative sequence-based feature descriptors and improving feature representation capability using a powerful feature selection technique. Importantly, unlike other methods based on multiple, complex information inputs, our proposed MePred-RF is based on sequence information alone. Comparative studies on benchmark datasets via vigorous jackknife tests indicate that our proposed MePred-RF method remarkably outperforms other state-of-the-art predictors, leading by a 4.5 percent average in terms of overall accuracy. A user-friendly webserver that implements the proposed method has been established for researchers' convenience, and is now freely available for public use through http://server.malab.cn/MePred-RF. We anticipate our research tool to be useful for the large-scale prediction and analysis of protein methylation sites.

PEPred-Suite: improved and robust prediction of therapeutic peptides using adaptive feature representation learning

Motivation

Prediction of therapeutic peptides is critical for the discovery of novel and efficient peptide-based therapeutics. Computational methods, especially machine learning based methods, have been developed for addressing this need. However, most of existing methods are peptide-specific; currently, there is no generic predictor for multiple peptide types. Moreover, it is still challenging to extract informative feature representations from the perspective of primary sequences.

Results

In this study, we have developed PEPred-Suite, a bioinformatics tool for the generic prediction of therapeutic peptides. In PEPred-Suite, we introduce an adaptive feature representation strategy that can learn the most representative features for different peptide types. To be specific, we train diverse sequence-based feature descriptors, integrate the learnt class information into our features, and utilize a two-step feature optimization strategy based on the area under receiver operating characteristic curve to extract the most discriminative features. Using the learnt representative features, we trained eight random forest models for eight different types of functional peptides, respectively. Benchmarking results showed that as compared with existing predictors, PEPred-Suite achieves better and robust performance for different peptides. As far as we know, PEPred-Suite is currently the first tool that is capable of predicting so many peptide types simultaneously. In addition, our work demonstrates that the learnt features can reliably predict different peptides.

Availability and implementation

The user-friendly webserver implementing the proposed PEPred-Suite is freely accessible at http://server.malab.cn/PEPred-Suite.

Supplementary information

Supplementary data are available at Bioinformatics online.

Combinatorial Pattern of Histone Modifications in Exon Skipping Event

Histone modifications are associated with alternative splicing. It has been suggested that histone modifications act in combinational patterns in gene expression regulation. However, how they interact with each other and what is their casual relationships in the process of RNA splicing remain unclear. In this study, the combinatorial patterns of 38 kinds of histone modifications in the exon skipping event of the CD4⁺ T cell were analyzed by constructing Bayesian networks. Distinct combinatorial patterns of histone modifications that illustrating their casual relationships were observed in excluded/included exons and the surrounding intronic regions. The Bayesian networks also indicate that some histone modifications directly correlate with RNA splicing. We anticipate that this work could provide novel insights into the effects of histone modifications on RNA splicing regulation.

Computational Method for the Identification of Molecular Metabolites Involved in Cereal Hull Color Variations

Background:

Cereal hull color is an important quality specification characteristic. Many studies were conducted to identify genetic changes underlying cereal hull color diversity. However, these studies mainly focused on the gene level. Recent studies have suggested that metabolomics can accurately reflect the integrated and real-time cell processes that contribute to the formation of different cereal colors.

Methods:

In this study, we exploited published metabolomics databases and applied several advanced computational methods, such as minimum redundancy maximum relevance (mRMR), incremental forward search (IFS), random forest (RF) to investigate cereal hull color at the metabolic level. First, the mRMR was applied to analyze cereal hull samples represented by metabolite features, yielding a feature list. Then, the IFS and RF were used to test several feature sets, constructed according to the aforementioned feature list. Finally, the optimal feature sets and RF classifier were accessed based on the testing results.

Results and Conclusion:

A total of 158 key metabolites were found to be useful in distinguishing white cereal hulls from colorful cereal hulls. A prediction model constructed with these metabolites and a random forest algorithm generated a high Matthews coefficient correlation value of 0.701. Furthermore, 24 of these metabolites were previously found to be relevant to cereal color. Our study can provide new insights into the molecular basis of cereal hull color formation.

Gene2vec: gene subsequence embedding for prediction of mammalian N6-methyladenosine sites from mRNA

N⁶-Methyladenosine (m⁶A) refers to methylation modification of the adenosine nucleotide acid at the nitrogen-6 position. Many conventional computational methods for identifying N⁶-methyladenosine sites are limited by the small amount of data available. Taking advantage of the thousands of m⁶A sites detected by high-throughput sequencing, it is now possible to discover the characteristics of m⁶A sequences using deep learning techniques. To the best of our knowledge, our work is the first attempt to use word embedding and deep neural networks for m⁶A prediction from mRNA sequences. Using four deep neural networks, we developed a model inferred from a larger sequence shifting window that can predict m⁶A accurately and robustly. Four prediction schemes were built with various RNA sequence representations and optimized convolutional neural networks. The soft voting results from the four deep networks were shown to outperform all of the state-of-the-art methods. We evaluated these predictors mentioned above on a rigorous independent test data set and proved that our proposed method outperforms the state-of-the-art predictors. The training, independent, and cross-species testing data sets are much larger than in previous studies, which could help to avoid the problem of overfitting. Furthermore, an online prediction web server implementing the four proposed predictors has been built and is available at http://server.malab.cn/Gene2vec/.