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

CaLMPhosKAN: prediction of general phosphorylation sites in proteins via fusion of codon aware embeddings with amino acid aware embeddings and wavelet-based Kolmogorov-Arnold network

MOTIVATION

The mapping from codon to amino acid is surjective due to codon degeneracy, suggesting that codon space might harbor higher information content. Embeddings from the codon language model have recently demonstrated success in various protein downstream tasks. However, predictive models for residue-level tasks such as phosphorylation sites, arguably the most studied Post-Translational Modification (PTM), and PTM sites prediction in general, have predominantly relied on representations in amino acid space.

RESULTS

We introduce a novel approach for predicting phosphorylation sites by utilizing codon-level information through embeddings from the codon adaptation language model (CaLM), trained on protein-coding DNA sequences. Protein sequences are first reverse-translated into reliable coding sequences by mapping UniProt sequences to their corresponding NCBI reference sequences and extracting the exact coding sequences from their GenBank format using a dynamic programming-based global pairwise alignment. The resulting coding sequences are encoded using the CaLM encoder to generate codon-aware embeddings, which are subsequently integrated with amino acid-aware embeddings obtained from a protein language model, through an early fusion strategy. Next, a window-level representation of the site of interest, retaining the full sequence context, is constructed from the fused embeddings. A ConvBiGRU network extracts feature maps that capture spatiotemporal correlations between proximal residues within the window. This is followed by a prediction head based on a Kolmogorov-Arnold network (KAN) using the derivative of gaussian wavelet transform to generate the inference for the site. The overall model, dubbed CaLMPhosKAN, performs better than the existing approaches across multiple datasets.

AVAILABILITY AND IMPLEMENTATION

CaLMPhosKAN is publicly available at https://github.com/KCLabMTU/CaLMPhosKAN.

LMPTMSite: A Platform for PTM Site Prediction in Proteins Leveraging Transformer-Based Protein Language Models

Protein post-translational modifications (PTMs) introduce new functionalities and play a critical role in the regulation of protein functions. Characterizing these modifications, especially PTM sites, is essential for unraveling complex biological systems. However, traditional experimental approaches, such as mass spectrometry, are time-consuming and expensive. Machine learning and deep learning techniques offer promising alternatives for predicting PTM sites. In this chapter, we introduce our LMPTMSite (language model-based post-translational modification site predictor) platform, which emphasizes two transformer-based protein language model (pLM) approaches: pLMSNOSite and LMSuccSite, for the prediction of S-nitrosylation sites and succinylation sites in proteins, respectively. We highlight the various methods of using pLM-based sequence encoding, explain the underlying deep learning architectures, and discuss the superior efficacy of these tools compared to other state-of-the-art tools. Subsequently, we present an analysis of runtime and memory usage for pLMSNOSite, with a focus on CPU and RAM usage as the input sequence length is scaled up. Finally, we showcase a case study predicting succinylation sites in proteins active within the tricarboxylic acid (TCA) cycle pathway using LMSuccSite, demonstrating its potential utility and efficiency in real-world biological contexts. The LMPTMSite platform, inclusive of pLMSNOSite and LMSuccSite, is freely available both as a web server ( http://kcdukkalab.org/pLMSNOSite/ and http://kcdukkalab.org/LMSuccSite/ ) and as standalone packages ( https://github.com/KCLabMTU/pLMSNOSite and https://github.com/KCLabMTU/LMSuccSite ), providing valuable tools for researchers in the field.

KbhbXG: A Machine learning architecture based on XGBoost for prediction of lysine β-Hydroxybutyrylation (Kbhb) modification sites

Lysine β-hydroxybutyrylation is an important post-translational modification (PTM) involved in various physiological and biological processes. In this research, we introduce a novel predictor KbhbXG, which utilizes XGBoost to identify β-hydroxybutyrylation modification sites based on protein sequence information. The traditional experimental methods employed for the identification of β-hydroxybutyrylated sites using proteomic techniques are both costly and time-consuming. Thus, the development of computational methods and predictors can play a crucial role in facilitating the rapid identification of β-hydroxybutyrylation sites. Our proposed KbhbXG model first utilizes machine learning algorithm XGBoost to predict β-hydroxybutyrylation modification sites. On the independent test set, KbhbXG achieves an accuracy of 0.7457, specificity of 0.7771, and an impressive area under the curve (AUC) score of 0.8172. The high AUC score achieved by our method demonstrates its potential for effectively identifying novel β-hydroxybutyrylation sites, thereby facilitating further research and exploration of the β-hydroxybutyrylation process. Also, functional analyses have revealed that different organisms preferentially engage in distinct biological processes and pathways, which can provide valuable insights for understanding the mechanism of β-hydroxybutyrylation and guide experimental verification. To promote transparency and reproducibility, we have made both the codes and dataset of KbhbXG publicly available. Researchers interested in utilizing our proposed model can access these resources at https://github.com/Lab-Xu/KbhbXG.

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.

A Review of Machine Learning and Algorithmic Methods for Protein Phosphorylation Site Prediction

Post-translational modifications (PTMs) have key roles in extending the functional diversity of proteins and, as a result, regulating diverse cellular processes in prokaryotic and eukaryotic organisms. Phosphorylation modification is a vital PTM that occurs in most proteins and plays a significant role in many biological processes. Disorders in the phosphorylation process lead to multiple diseases, including neurological disorders and cancers. The purpose of this review is to organize this body of knowledge associated with phosphorylation site (p-site) prediction to facilitate future research in this field. At first, we comprehensively review all related databases and introduce all steps regarding dataset creation, data preprocessing, and method evaluation in p-site prediction. Next, we investigate p-site prediction methods, which are divided into two computational groups: algorithmic and machine learning (ML). Additionally, it is shown that there are basically two main approaches for p-site prediction by ML: conventional and end-to-end deep learning methods, both of which are given an overview. Moreover, this review introduces the most important feature extraction techniques, which have mostly been used in p-site prediction. Finally, we create three test sets from new proteins related to the released version of the database of protein post-translational modifications (dbPTM) in 2022 based on general and human species. Evaluating online p-site prediction tools on newly added proteins introduced in the dbPTM 2022 release, distinct from those in the dbPTM 2019 release, reveals their limitations. In other words, the actual performance of these online p-site prediction tools on unseen proteins is notably lower than the results reported in their respective research papers.

Advancing the accuracy of SARS-CoV-2 phosphorylation site detection via meta-learning approach

The worldwide appearance of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has generated significant concern and posed a considerable challenge to global health. Phosphorylation is a common post-translational modification that affects many vital cellular functions and is closely associated with SARS-CoV-2 infection. Precise identification of phosphorylation sites could provide more in-depth insight into the processes underlying SARS-CoV-2 infection and help alleviate the continuing COVID-19 crisis. Currently, available computational tools for predicting these sites lack accuracy and effectiveness. In this study, we designed an innovative meta-learning model, Meta-Learning for Serine/Threonine Phosphorylation (MeL-STPhos), to precisely identify protein phosphorylation sites. We initially performed a comprehensive assessment of 29 unique sequence-derived features, establishing prediction models for each using 14 renowned machine learning methods, ranging from traditional classifiers to advanced deep learning algorithms. We then selected the most effective model for each feature by integrating the predicted values. Rigorous feature selection strategies were employed to identify the optimal base models and classifier(s) for each cell-specific dataset. To the best of our knowledge, this is the first study to report two cell-specific models and a generic model for phosphorylation site prediction by utilizing an extensive range of sequence-derived features and machine learning algorithms. Extensive cross-validation and independent testing revealed that MeL-STPhos surpasses existing state-of-the-art tools for phosphorylation site prediction. We also developed a publicly accessible platform at https://balalab-skku.org/MeL-STPhos. We believe that MeL-STPhos will serve as a valuable tool for accelerating the discovery of serine/threonine phosphorylation sites and elucidating their role in post-translational regulation.

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.

IPs-GRUAtt: An attention-based bidirectional gated recurrent unit network for predicting phosphorylation sites of SARS-CoV-2 infection

The global pandemic of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection has generated tremendous concern and poses a serious threat to international public health. Phosphorylation is a common post-translational modification affecting many essential cellular processes and is inextricably linked to SARS-CoV-2 infection. Hence, accurate identification of phosphorylation sites will be helpful to understand the mechanisms of SARS-CoV-2 infection and mitigate the ongoing COVID-19 pandemic. In the present study, an attention-based bidirectional gated recurrent unit network, called IPs-GRUAtt, was proposed to identify phosphorylation sites in SARS-CoV-2-infected host cells. Comparative results demonstrated that IPs-GRUAtt surpassed both state-of-the-art machine-learning methods and existing models for identifying phosphorylation sites. Moreover, the attention mechanism made IPs-GRUAtt able to extract the key features from protein sequences. These results demonstrated that the IPs-GRUAtt is a powerful tool for identifying phosphorylation sites. For facilitating its academic use, a freely available online web server for IPs-GRUAtt is provided at http://cbcb.cdutcm.edu.cn/phosphory/.

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

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

A Transfer-Learning-Based Deep Convolutional Neural Network for Predicting Leukemia-Related Phosphorylation Sites from Protein Primary Sequences

As one of the most important post-translational modifications (PTMs), phosphorylation refers to the binding of a phosphate group with amino acid residues like Ser (S), Thr (T) and Tyr (Y) thus resulting in diverse functions at the molecular level. Abnormal phosphorylation has been proved to be closely related with human diseases. To our knowledge, no research has been reported describing specific disease-associated phosphorylation sites prediction which is of great significance for comprehensive understanding of disease mechanism. In this work, focusing on three types of leukemia, we aim to develop a reliable leukemia-related phosphorylation site prediction models by combing deep convolutional neural network (CNN) with transfer-learning. CNN could automatically discover complex representations of phosphorylation patterns from the raw sequences, and hence it provides a powerful tool for improvement of leukemia-related phosphorylation site prediction. With the largest dataset of myelogenous leukemia, the optimal models for S/T/Y phosphorylation sites give the AUC values of 0.8784, 0.8328 and 0.7716 respectively. When transferred learning on the small size datasets, the models for T-cell and lymphoid leukemia also give the promising performance by common sharing the optimal parameters. Compared with other five machine-learning methods, our CNN models reveal the superior performance. Finally, the leukemia-related pathogenesis analysis and distribution analysis on phosphorylated proteins along with K-means clustering analysis and position-specific conversation profiles on the phosphorylation site all indicate the strong practical feasibility of our easy-to-use CNN models.

FEPS: A Tool for Feature Extraction from Protein Sequence

Machine learning has become one of the most popular choices for developing computational approaches in protein structural bioinformatics. The ability to extract features from protein sequence/structure often becomes one of the crucial steps for the development of machine learning-based approaches. Over the years, various sequence, structural, and physicochemical descriptors have been developed for proteins and these descriptors have been used to predict/solve various bioinformatics problems. Hence, several feature extraction tools have been developed over the years to help researchers to generate numeric features from protein sequences. Most of these tools have some limitations regarding the number of sequences they can handle and the subsequent preprocessing that is required for the generated features before they can be fed to machine learning methods. Here, we present Feature Extraction from Protein Sequences (FEPS), a toolkit for feature extraction. FEPS is a versatile software package for generating various descriptors from protein sequences and can handle several sequences: the number of which is limited only by the computational resources. In addition, the features extracted from FEPS do not require subsequent processing and are ready to be fed to the machine learning techniques as it provides various output formats as well as the ability to concatenate these generated features. FEPS is made freely available via an online web server as well as a stand-alone toolkit. FEPS, a comprehensive toolkit for feature extraction, will help spur the development of machine learning-based models for various bioinformatics problems.

Bioinformatic Analyses of Peroxiredoxins and RF-Prx: A Random Forest-Based Predictor and Classifier for Prxs

Peroxiredoxins (Prxs) are a protein superfamily, present in all organisms, that play a critical role in protecting cellular macromolecules from oxidative damage but also regulate intracellular and intercellular signaling processes involving redox-regulated proteins and pathways. Bioinformatic approaches using computational tools that focus on active site-proximal sequence fragments (known as active site signatures) and iterative clustering and searching methods (referred to as TuLIP and MISST) have recently enabled the recognition of over 38,000 peroxiredoxins, as well as their classification into six functionally relevant groups. With these data providing so many examples of Prxs in each class, machine learning approaches offer an opportunity to extract additional information about features characteristic of these protein groups.In this study, we developed a novel computational method named "RF-Prx" based on a random forest (RF) approach integrated with K-space amino acid pairs (KSAAP) to identify peroxiredoxins and classify them into one of six subgroups. Our process performed in a superior manner compared to other machine learning classifiers. Thus the RF approach integrated with K-space amino acid pairs enabled the detection of class-specific conserved sequences outside the known functional centers and with potential importance. For example, drugs designed to target Prx proteins would likely suffer from cross-reactivity among distinct Prxs if targeted to conserved active sites, but this may be avoidable if remote, class-specific regions could be targeted instead.

DTL-DephosSite: Deep Transfer Learning Based Approach to Predict Dephosphorylation Sites

Phosphorylation, which is mediated by protein kinases and opposed by protein phosphatases, is an important post-translational modification that regulates many cellular processes, including cellular metabolism, cell migration, and cell division. Due to its essential role in cellular physiology, a great deal of attention has been devoted to identifying sites of phosphorylation on cellular proteins and understanding how modification of these sites affects their cellular functions. This has led to the development of several computational methods designed to predict sites of phosphorylation based on a protein’s primary amino acid sequence. In contrast, much less attention has been paid to dephosphorylation and its role in regulating the phosphorylation status of proteins inside cells. Indeed, to date, dephosphorylation site prediction tools have been restricted to a few tyrosine phosphatases. To fill this knowledge gap, we have employed a transfer learning strategy to develop a deep learning-based model to predict sites that are likely to be dephosphorylated. Based on independent test results, our model, which we termed DTL-DephosSite, achieved efficiency scores for phosphoserine/phosphothreonine residues of 84%, 84% and 0.68 with respect to sensitivity (SN), specificity (SP) and Matthew’s correlation coefficient (MCC). Similarly, DTL-DephosSite exhibited efficiency scores of 75%, 88% and 0.64 for phosphotyrosine residues with respect to SN, SP, and MCC.

A deep learning based approach for prediction of Chlamydomonas reinhardtii phosphorylation sites

Protein phosphorylation, which is one of the most important post-translational modifications (PTMs), is involved in regulating myriad cellular processes. Herein, we present a novel deep learning based approach for organism-specific protein phosphorylation site prediction in Chlamydomonas reinhardtii, a model algal phototroph. An ensemble model combining convolutional neural networks and long short-term memory (LSTM) achieves the best performance in predicting phosphorylation sites in C. reinhardtii. Deemed Chlamy-EnPhosSite, the measured best AUC and MCC are 0.90 and 0.64 respectively for a combined dataset of serine (S) and threonine (T) in independent testing higher than those measures for other predictors. When applied to the entire C. reinhardtii proteome (totaling 1,809,304 S and T sites), Chlamy-EnPhosSite yielded 499,411 phosphorylated sites with a cut-off value of 0.5 and 237,949 phosphorylated sites with a cut-off value of 0.7. These predictions were compared to an experimental dataset of phosphosites identified by liquid chromatography-tandem mass spectrometry (LC–MS/MS) in a blinded study and approximately 89.69% of 2,663 C. reinhardtii S and T phosphorylation sites were successfully predicted by Chlamy-EnPhosSite at a probability cut-off of 0.5 and 76.83% of sites were successfully identified at a more stringent 0.7 cut-off. Interestingly, Chlamy-EnPhosSite also successfully predicted experimentally confirmed phosphorylation sites in a protein sequence (e.g., RPS6 S245) which did not appear in the training dataset, highlighting prediction accuracy and the power of leveraging predictions to identify biologically relevant PTM sites. These results demonstrate that our method represents a robust and complementary technique for high-throughput phosphorylation site prediction in C. reinhardtii. It has potential to serve as a useful tool to the community. Chlamy-EnPhosSite will contribute to the understanding of how protein phosphorylation influences various biological processes in this important model microalga.

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

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

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 deep neural networks and biological subwords to detect protein S-sulfenylation sites

Protein S-sulfenylation is one kind of crucial post-translational modifications (PTMs) in which the hydroxyl group covalently binds to the thiol of cysteine. Some recent studies have shown that this modification plays an important role in signaling transduction, transcriptional regulation and apoptosis. To date, the dynamic of sulfenic acids in proteins remains unclear because of its fleeting nature. Identifying S-sulfenylation sites, therefore, could be the key to decipher its mysterious structures and functions, which are important in cell biology and diseases. However, due to the lack of effective methods, scientists in this field tend to be limited in merely a handful of some wet lab techniques that are time-consuming and not cost-effective. Thus, this motivated us to develop an in silico model for detecting S-sulfenylation sites only from protein sequence information. In this study, protein sequences served as natural language sentences comprising biological subwords. The deep neural network was consequentially employed to perform classification. The performance statistics within the independent dataset including sensitivity, specificity, accuracy, Matthews correlation coefficient and area under the curve rates achieved 85.71%, 69.47%, 77.09%, 0.5554 and 0.833, respectively. Our results suggested that the proposed method (fastSulf-DNN) achieved excellent performance in predicting S-sulfenylation sites compared to other well-known tools on a benchmark dataset.

DeepKinZero: zero-shot learning for predicting kinase-phosphosite associations involving understudied kinases

MOTIVATION

Protein phosphorylation is a key regulator of protein function in signal transduction pathways. Kinases are the enzymes that catalyze the phosphorylation of other proteins in a target-specific manner. The dysregulation of phosphorylation is associated with many diseases including cancer. Although the advances in phosphoproteomics enable the identification of phosphosites at the proteome level, most of the phosphoproteome is still in the dark: more than 95% of the reported human phosphosites have no known kinases. Determining which kinase is responsible for phosphorylating a site remains an experimental challenge. Existing computational methods require several examples of known targets of a kinase to make accurate kinase-specific predictions, yet for a large body of kinases, only a few or no target sites are reported.

RESULTS

We present DeepKinZero, the first zero-shot learning approach to predict the kinase acting on a phosphosite for kinases with no known phosphosite information. DeepKinZero transfers knowledge from kinases with many known target phosphosites to those kinases with no known sites through a zero-shot learning model. The kinase-specific positional amino acid preferences are learned using a bidirectional recurrent neural network. We show that DeepKinZero achieves significant improvement in accuracy for kinases with no known phosphosites in comparison to the baseline model and other methods available. By expanding our knowledge on understudied kinases, DeepKinZero can help to chart the phosphoproteome atlas.

AVAILABILITY AND IMPLEMENTATION

The source codes are available at https://github.com/Tastanlab/DeepKinZero.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

RF-MaloSite and DL-Malosite: Methods based on random forest and deep learning to identify malonylation sites

Malonylation, which has recently emerged as an important lysine modification, regulates diverse biological activities and has been implicated in several pervasive disorders, including cardiovascular disease and cancer. However, conventional global proteomics analysis using tandem mass spectrometry can be time-consuming, expensive and technically challenging. Therefore, to complement and extend existing experimental methods for malonylation site identification, we developed two novel computational methods for malonylation site prediction based on random forest and deep learning machine learning algorithms, RF-MaloSite and DL-MaloSite, respectively. DL-MaloSite requires the primary amino acid sequence as an input and RF-MaloSite utilizes a diverse set of biochemical, physiochemical and sequence-based features. While systematic assessment of performance metrics suggests that both ‘RF-MaloSite’ and ‘DL-MaloSite’ perform well in all metrics tested, our methods perform particularly well in the areas of accuracy, sensitivity and overall method performance (assessed by the Matthew’s Correlation Coefficient). For instance, RF-MaloSite exhibited MCC scores of 0.42 and 0.40 using 10-fold cross-validation and an independent test set, respectively. Meanwhile, DL-MaloSite was characterized by MCC scores of 0.51 and 0.49 based on 10-fold cross-validation and an independent set, respectively. Importantly, both methods exhibited efficiency scores that were on par or better than those achieved by existing malonylation site prediction methods. The identification of these sites may also provide important insights into the mechanisms of crosstalk between malonylation and other lysine modifications, such as acetylation, glutarylation and succinylation. To facilitate their use, both methods have been made freely available to the research community at https://github.com/dukkakc/DL-MaloSite-and-RF-MaloSite.

Deep learning for mining protein data

The recent emergence of deep learning to characterize complex patterns of protein big data reveals its potential to address the classic challenges in the field of protein data mining. Much research has revealed the promise of deep learning as a powerful tool to transform protein big data into valuable knowledge, leading to scientific discoveries and practical solutions. In this review, we summarize recent publications on deep learning predictive approaches in the field of mining protein data. The application architectures of these methods include multilayer perceptrons, stacked autoencoders, deep belief networks, two- or three-dimensional convolutional neural networks, recurrent neural networks, graph neural networks, and complex neural networks and are described from five perspectives: residue-level prediction, sequence-level prediction, three-dimensional structural analysis, interaction prediction, and mass spectrometry data mining. The advantages and deficiencies of these architectures are presented in relation to various tasks in protein data mining. Additionally, some practical issues and their future directions are discussed, such as robust deep learning for protein noisy data, architecture optimization for specific tasks, efficient deep learning for limited protein data, multimodal deep learning for heterogeneous protein data, and interpretable deep learning for protein understanding. This review provides comprehensive perspectives on general deep learning techniques for protein data analysis.

Computational methods and tools for binding site recognition between proteins and small molecules: from classical geometrical approaches to modern machine learning strategies

In the current "genomic era" the number of identified genes is growing exponentially. However, the biological function of a large number of the corresponding proteins is still unknown. Recognition of small molecule ligands (e.g., substrates, inhibitors, allosteric regulators, etc.) is pivotal for protein functions in the vast majority of the cases and knowledge of the region where these processes take place is essential for protein function prediction and drug design. In this regard, computational methods represent essential tools to tackle this problem. A significant number of software tools have been developed in the last few years which exploit either protein sequence information, structure information or both. This review describes the most recent developments in protein function recognition and binding site prediction, in terms of both freely-available and commercial solutions and tools, detailing the main characteristics of the considered tools and providing a comparative analysis of their performance.

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.

SVM-SulfoSite: A support vector machine based predictor for sulfenylation sites

Protein S-sulfenylation, which results from oxidation of free thiols on cysteine residues, has recently emerged as an important post-translational modification that regulates the structure and function of proteins involved in a variety of physiological and pathological processes. By altering the size and physiochemical properties of modified cysteine residues, sulfenylation can impact the cellular function of proteins in several different ways. Thus, the ability to rapidly and accurately identify putative sulfenylation sites in proteins will provide important insights into redox-dependent regulation of protein function in a variety of cellular contexts. Though bottom-up proteomic approaches, such as tandem mass spectrometry (MS/MS), provide a wealth of information about global changes in the sulfenylation state of proteins, MS/MS-based experiments are often labor-intensive, costly and technically challenging. Therefore, to complement existing proteomic approaches, researchers have developed a series of computational tools to identify putative sulfenylation sites on proteins. However, existing methods often suffer from low accuracy, specificity, and/or sensitivity. In this study, we developed SVM-SulfoSite, a novel sulfenylation prediction tool that uses support vector machines (SVM) to identify key determinants of sulfenylation among five feature classes: binary code, physiochemical properties, k-space amino acid pairs, amino acid composition and high-quality physiochemical indices. Using 10-fold cross-validation, SVM-SulfoSite achieved 95% sensitivity and 83% specificity, with an overall accuracy of 89% and Matthew’s correlation coefficient (MCC) of 0.79. Likewise, using an independent test set of experimentally identified sulfenylation sites, our method achieved scores of 74%, 62%, 80% and 0.42 for accuracy, sensitivity, specificity and MCC, with an area under the receiver operator characteristic (ROC) curve of 0.81. Moreover, in side-by-side comparisons, SVM-SulfoSite performed as well as or better than existing sulfenylation prediction tools. Together, these results suggest that our method represents a robust and complementary technique for advanced exploration of protein S-sulfenylation.

CNN-BLPred: a Convolutional neural network based predictor for β-Lactamases (BL) and their classes

BACKGROUND

The β-Lactamase (BL) enzyme family is an important class of enzymes that plays a key role in bacterial resistance to antibiotics. As the newly identified number of BL enzymes is increasing daily, it is imperative to develop a computational tool to classify the newly identified BL enzymes into one of its classes. There are two types of classification of BL enzymes: Molecular Classification and Functional Classification. Existing computational methods only address Molecular Classification and the performance of these existing methods is unsatisfactory.

RESULTS

We addressed the unsatisfactory performance of the existing methods by implementing a Deep Learning approach called Convolutional Neural Network (CNN). We developed CNN-BLPred, an approach for the classification of BL proteins. The CNN-BLPred uses Gradient Boosted Feature Selection (GBFS) in order to select the ideal feature set for each BL classification. Based on the rigorous benchmarking of CCN-BLPred using both leave-one-out cross-validation and independent test sets, CCN-BLPred performed better than the other existing algorithms. Compared with other architectures of CNN, Recurrent Neural Network, and Random Forest, the simple CNN architecture with only one convolutional layer performs the best. After feature extraction, we were able to remove ~95% of the 10,912 features using Gradient Boosted Trees. During 10-fold cross validation, we increased the accuracy of the classic BL predictions by 7%. We also increased the accuracy of Class A, Class B, Class C, and Class D performance by an average of 25.64%. The independent test results followed a similar trend.

CONCLUSIONS

We implemented a deep learning algorithm known as Convolutional Neural Network (CNN) to develop a classifier for BL classification. Combined with feature selection on an exhaustive feature set and using balancing method such as Random Oversampling (ROS), Random Undersampling (RUS) and Synthetic Minority Oversampling Technique (SMOTE), CNN-BLPred performs significantly better than existing algorithms for BL classification.

iMulti-HumPhos: a multi-label classifier for identifying human phosphorylated proteins using multiple kernel learning based support vector machines

An efficient multi-label classifier for identifying human phosphorylated proteins has been developed by introducing multiple kernel learning based support vector machines.