DeepNitro: Prediction of Protein Nitration and Nitrosylation Sites by Deep Learning

Network analysis of S-nitrosylated synaptic proteins demonstrates unique roles in health and disease

Nitric oxide can covalently modify cysteine thiols on target proteins to alter that protein's function in a process called S-nitrosylation (SNO). S-nitrosylation of synaptic proteins plays an integral part in neurotransmission. Here we review the function of the SNO-proteome at the synapse and whether clusters of SNO-modification may predict synaptic dysfunction associated with disease. We used a systematic search strategy to concatenate SNO-proteomic datasets from normal human or murine brain samples. Identified SNO-modified proteins were then filtered against proteins reported in the Synaptome Database, which provides a detailed and experimentally verified annotation of all known synaptic proteins. Subsequently, we performed an unbiased network analysis of all known SNO-synaptic proteins to identify clusters of SNO proteins commonly involved in biological processes or with known disease associations. The resulting SNO networks were significantly enriched in biological processes related to metabolism, whereas significant gene-disease associations were related to Schizophrenia, Alzheimer's, Parkinson's and Huntington's disease. Guided by an unbiased network analysis, the current review presents a thorough discussion of how clustered changes to the SNO-proteome influence health and disease.

DF-Phos: Prediction of Protein Phosphorylation Sites by Deep Forest

Phosphorylation is the most important and studied post-translational modification (PTM), which plays a crucial role in protein function studies and experimental design. Many significant studies have been performed to predict phosphorylation sites using various machine-learning methods. Recently, several studies have claimed that deep learning-based methods are the best way to predict the phosphorylation sites because deep learning as an advanced machine learning method can automatically detect complex representations of phosphorylation patterns from raw sequences and thus offers a powerful tool to improve phosphorylation site prediction. In this study, we report DF-Phos, a new phosphosite predictor based on the Deep Forest to predict phosphorylation sites. In DF-Phos, the feature vector taken from the CkSAApair method is as input for a Deep Forest framework for predicting phosphorylation sites. The results of 10-fold cross-validation show that the Deep Forest method has the highest performance among other available methods. We implemented a Python program of DF-Phos, which is freely available for non-commercial use at https://github.com/zahiriz/DF-Phos Moreover, users can use it for various PTM predictions.

NTpred: a robust and precise machine learning framework for in silico identification of Tyrosine nitration sites in protein sequences

Post-translational modifications (PTMs) either enhance a protein's activity in various sub-cellular processes, or degrade their activity which leads toward failure of intracellular processes. Tyrosine nitration (NT) modification degrades protein's activity that initiates and propagates various diseases including neurodegenerative, cardiovascular, autoimmune diseases and carcinogenesis. Identification of NT modification supports development of novel therapies and drug discoveries for associated diseases. Identification of NT modification in biochemical labs is expensive, time consuming and error-prone. To supplement this process, several computational approaches have been proposed. However these approaches fail to precisely identify NT modification, due to the extraction of irrelevant, redundant and less discriminative features from protein sequences. This paper presents the NTpred framework that is competent in extracting comprehensive features from raw protein sequences using four different sequence encoders. To reap the benefits of different encoders, it generates four additional feature spaces by fusing different combinations of individual encodings. Furthermore, it eradicates irrelevant and redundant features from eight different feature spaces through a Recursive Feature Elimination process. Selected features of four individual encodings and four feature fusion vectors are used to train eight different Gradient Boosted Tree classifiers. The probability scores from the trained classifiers are utilized to generate a new probabilistic feature space, which is used to train a Logistic Regression classifier. On the BD1 benchmark dataset, the proposed framework outperforms the existing best-performing predictor in 5-fold cross validation and independent test evaluation with combined improvement of 13.7% in MCC and 20.1% in AUC. Similarly, on the BD2 benchmark dataset, the proposed framework outperforms the existing best-performing predictor with combined improvement of 5.3% in MCC and 1.0% in AUC. NTpred is publicly available for further experimentation and predictive use at: https://sds_genetic_analysis.opendfki.de/PredNTS/.

Empowering Protein Engineering through Recombination of Beneficial Substitutions

Directed evolution stands as a seminal technology for generating novel protein functionalities, a cornerstone in biocatalysis, metabolic engineering, and synthetic biology. Today, with the development of various mutagenesis methods and advanced analytical machines, the challenge of diversity generation and high-throughput screening platforms is largely solved, and one of the remaining challenges is: how to empower the potential of single beneficial substitutions with recombination to achieve the epistatic effect. This review overviews experimental and computer-assisted recombination methods in protein engineering campaigns. In addition, integrated and machine learning-guided strategies were highlighted to discuss how these recombination approaches contribute to generating the screening library with better diversity, coverage, and size. A decision tree was finally summarized to guide the further selection of proper recombination strategies in practice, which was beneficial for accelerating protein engineering.

PPSNO: A Feature-Rich SNO Sites Predictor by Stacking Ensemble Strategy from Protein Sequence-Derived Information

The protein S-nitrosylation (SNO) is a significant post-translational modification that affects the stability, activity, cellular localization, and function of proteins. Therefore, highly accurate prediction of SNO sites aids in grasping biological function mechanisms. In this document, we have constructed a predictor, named PPSNO, forecasting protein SNO sites using stacked integrated learning. PPSNO integrates multiple machine learning techniques into an ensemble model, enhancing its predictive accuracy. First, we established benchmark datasets by collecting SNO sites from various sources, including literature, databases, and other predictors. Second, various techniques for feature extraction are applied to derive characteristics from protein sequences, which are subsequently amalgamated into the PPSNO predictor for training. Five-fold cross-validation experiments show that PPSNO outperformed existing predictors, such as PSNO, PreSNO, pCysMod, DeepNitro, RecSNO, and Mul-SNO. The PPSNO predictor achieved an impressive accuracy of 92.8%, an area under the curve (AUC) of 96.1%, a Matthews correlation coefficient (MCC) of 81.3%, an F1-score of 85.6%, an SN of 79.3%, an SP of 97.7%, and an average precision (AP) of 92.2%. We also employed ROC curves, PR curves, and radar plots to show the superior performance of PPSNO. Our study shows that fused protein sequence features and two-layer stacked ensemble models can improve the accuracy of predicting SNO sites, which can aid in comprehending cellular processes and disease mechanisms. The codes and data are available at https://github.com/serendipity-wly/PPSNO .

A metabolic perspective on nitric oxide function in melanoma

Nitric oxide (NO) generated from nitric oxide synthase (NOS) exerts a dichotomous effect in melanoma, suppressing or promoting tumor progression. This dichotomy is thought to depend on the intracellular NO concentration and the cell type in which it is generated. Due to its central role in the metabolism of multiple critical constituents involved in signaling and stress, it is crucial to explore NO's contribution to the metabolic dysfunction of melanoma. This review will discuss many known metabolites linked to NO production in melanoma. We discuss the synthesis of these metabolites, their role in biochemical pathways, and how they alter the biological processes observed in the melanoma tumor microenvironment. The metabolic pathways altered by NO and the corresponding metabolites reinforce its dual role in melanoma and support investigating this effect for potential avenues of therapeutic intervention.

Macrophages undergo functionally significant reprograming of nucleotide metabolism upon classical activation

During an immune response, macrophages systematically rewire their metabolism in specific ways to support their diversve functions. However, current knowledge of macrophage metabolism is largely concentrated on central carbon metabolism. Using multi-omics analysis, we identified nucleotide metabolism as one of the most significantly rewired pathways upon classical activation. Further isotopic tracing studies revealed several major changes underlying the substantial metabolomic alterations: 1) de novo synthesis of both purines and pyrimidines is shut down at several specific steps; 2) nucleotide degradation activity to nitrogenous bases is increased but complete oxidation of bases is reduced, causing a great accumulation of nucleosides and bases; and 3) cells gradually switch to primarily relying on salvaging the nucleosides and bases for maintaining most nucleotide pools. Mechanistically, the inhibition of purine nucleotide de novo synthesis is mainly caused by nitric oxide (NO)-driven inhibition of the IMP synthesis enzyme ATIC, with NO-independent transcriptional downregulation of purine synthesis genes augmenting the effect. The inhibition of pyrimidine nucleotide de novo synthesis is driven by NO-driven inhibition of CTP synthetase (CTPS) and transcriptional downregulation of thymidylate synthase (TYMS). For the rewiring of degradation, purine nucleoside phosphorylase (PNP) and uridine phosphorylase (UPP) are transcriptionally upregulated, increasing nucleoside degradation activity. However, complete degradation of purine bases by xanthine oxidoreductase (XOR) is inhibited by NO, diverting flux into nucleotide salvage. Inhibiting the activation-induced switch from nucleotide de novo synthesis to salvage by knocking out the purine salvage enzyme hypoxanthine-guanine phosporibosyl transferase (Hprt) significantly alters the expression of genes important for activated macrophage functions, suppresses macrophage migration, and increases pyroptosis. Furthermore, knocking out Hprt or Xor increases proliferation of the intracellular parasite Toxoplasma gondii in macrophages. Together, these studies comprehensively reveal the characteristics, the key regulatory mechanisms, and the functional importance of the dynamic rewiring of nucleotide metabolism in classically activated macrophages.

Reactive oxygen species- and nitric oxide-dependent regulation of ion and metal homeostasis in plants

Deterioration and impoverishment of soil, caused by environmental pollution and climate change, result in reduced crop productivity. To adapt to hostile soils, plants have developed a complex network of factors involved in stress sensing, signal transduction, and adaptive responses. The chemical properties of reactive oxygen species (ROS) and reactive nitrogen species (RNS) allow them to participate in integrating the perception of external signals by fine-tuning protein redox regulation and signal transduction, triggering specific gene expression. Here, we update and summarize progress in understanding the mechanistic basis of ROS and RNS production at the subcellular level in plants and their role in the regulation of ion channels/transporters at both transcriptional and post-translational levels. We have also carried out an in silico analysis of different redox-dependent modifications of ion channels/transporters and identified cysteine and tyrosine targets of nitric oxide in metal transporters. Further, we summarize possible ROS- and RNS-dependent sensors involved in metal stress sensing, such as kinases and phosphatases, as well as some ROS/RNS-regulated transcription factors that could be involved in metal homeostasis. Understanding ROS- and RNS-dependent signaling events is crucial to designing new strategies to fortify crops and improve plant tolerance of nutritional imbalance and metal toxicity.

Unveiling the human nitroproteome: Protein tyrosine nitration in cell signaling and cancer

Covalent amino acid modification significantly expands protein functional capability in regulating biological processes. Tyrosine residues can undergo phosphorylation, sulfation, adenylation, halogenation, and nitration. These posttranslational modifications (PTMs) result from the actions of specific enzymes: tyrosine kinases, tyrosyl-protein sulfotransferase(s), adenylate transferase(s), oxidoreductases, peroxidases, and metal-heme containing proteins. Whereas phosphorylation, sulfation, and adenylation modify the hydroxyl group of tyrosine, tyrosine halogenation and nitration target the adjacent carbon residues. Because aberrant tyrosine nitration has been associated with human disorders and with animal models of disease, we have created an updated and curated database of 908 human nitrated proteins. We have also analyzed this new resource to provide insight into the role of tyrosine nitration in cancer biology, an area that has not previously been considered in detail. Unexpectedly, we have found that 879 of the 1971 known sites of tyrosine nitration are also sites of phosphorylation suggesting an extensive role for nitration in cell signaling. Overall, the review offers several forward-looking opportunities for future research and new perspectives for understanding the role of tyrosine nitration in cancer biology.

Novel insights about albumin in cardiovascular diseases: Focus on heart failure

The Human Plasma Proteome has always been the most investigated compartment in proteomics-based biomarker discovery, and is considered the largest and deepest version of the human proteome, reflecting the state of the body in health and disease. Even if efforts have been always dedicated to the refinement of proteomic approaches to investigate more deeply the plasma proteome, it should not be forgotten that also highly abundant plasma proteins, like human serum albumin (HSA), often neglected in these studies, might provide fundamental physiological functions in plasma, and should be better considered. This review summarizes the important roles of HSA in the context of cardiovascular diseases (CVD), and in particular in heart failure. Notwithstanding much attention has been historically directed toward the association of HSA levels and CVD risk, the advances in the field of mass spectrometry research allow also a better characterization of the effects of oxidative modifications that could alter not only the structure but also the function of HSA.

The ROP2 GTPase Participates in Nitric Oxide (NO)-Induced Root Shortening in Arabidopsis

Nitric oxide (NO) is a versatile signal molecule that mediates environmental and hormonal signals orchestrating plant development. NO may act via reversible S-nitrosation of proteins during which an NO moiety is added to a cysteine thiol to form an S-nitrosothiol. In plants, several proteins implicated in hormonal signaling have been reported to undergo S-nitrosation. Here, we report that the Arabidopsis ROP2 GTPase is a further potential target of NO-mediated regulation. The ROP2 GTPase was found to be required for the root shortening effect of NO. NO inhibits primary root growth by altering the abundance and distribution of the PIN1 auxin efflux carrier protein and lowering the accumulation of auxin in the root meristem. In rop2-1 insertion mutants, however, wild-type-like root size of the NO-treated roots were maintained in agreement with wild-type-like PIN1 abundance in the meristem. The ROP2 GTPase was shown to be S-nitrosated in vitro, suggesting that NO might directly regulate the GTPase. The potential mechanisms of NO-mediated ROP2 GTPase regulation and ROP2-mediated NO signaling in the primary root meristem are discussed.

pLMSNOSite: an ensemble-based approach for predicting protein S-nitrosylation sites by integrating supervised word embedding and embedding from pre-trained protein language model

BACKGROUND

Protein S-nitrosylation (SNO) plays a key role in transferring nitric oxide-mediated signals in both animals and plants and has emerged as an important mechanism for regulating protein functions and cell signaling of all main classes of protein. It is involved in several biological processes including immune response, protein stability, transcription regulation, post translational regulation, DNA damage repair, redox regulation, and is an emerging paradigm of redox signaling for protection against oxidative stress. The development of robust computational tools to predict protein SNO sites would contribute to further interpretation of the pathological and physiological mechanisms of SNO.

RESULTS

Using an intermediate fusion-based stacked generalization approach, we integrated embeddings from supervised embedding layer and contextualized protein language model (ProtT5) and developed a tool called pLMSNOSite (protein language model-based SNO site predictor). On an independent test set of experimentally identified SNO sites, pLMSNOSite achieved values of 0.340, 0.735 and 0.773 for MCC, sensitivity and specificity respectively. These results show that pLMSNOSite performs better than the compared approaches for the prediction of S-nitrosylation sites.

CONCLUSION

Together, the experimental results suggest that pLMSNOSite achieves significant improvement in the prediction performance of S-nitrosylation sites and represents a robust computational approach for predicting protein S-nitrosylation sites. pLMSNOSite could be a useful resource for further elucidation of SNO and is publicly available at https://github.com/KCLabMTU/pLMSNOSite .

Accurate Prediction of Anti-hypertensive Peptides Based on Convolutional Neural Network and Gated Recurrent unit

Hypertension (HT) is a general disease, and also one of the most ordinary and major causes of cardiovascular disease. Some diseases are caused by high blood pressure, including impairment of heart and kidney function, cerebral hemorrhage and myocardial infarction. Due to the limitations of laboratory methods, bioactive peptides for the treatment of HT need a long time to be identified. Therefore, it is of great immediate significance for the identification of anti-hypertensive peptides (AHTPs). With the prevalence of machine learning, it is suggested to use it as a supplementary method for AHTPs classification. Therefore, we develop a new model to identify AHTPs based on multiple features and deep learning. And the deep model is constructed by combining a convolutional neural network (CNN) and a gated recurrent unit (GRU). The unique convolution structure is used to reduce the feature dimension and running time. The data processed by CNN is input into the recurrent structure GRU, and important information is filtered out through the reset gate and update gate. Finally, the output layer adopts Sigmoid activation function. Firstly, we use Kmer, the deviation between the dipeptide frequency and the expected mean (DDE), encoding based on grouped weight (EBGW), enhanced grouped amino acid composition (EGAAC) and dipeptide binary profile and frequency (DBPF) to extract features. For Kmer, DDE, EBGW and EGAAC, it is widely used in the field of protein research. DBPF is a new feature representation method designed by us. It corresponds dipeptides to binary numbers, and finally obtains a binary coding file and a frequency file. Then these features are spliced together and input into our proposed model for prediction and analysis. After a tenfold cross-validation test, this model has a better competitive advantage than the previous methods, and the accuracy is 96.23% and 99.10%, respectively. From the results, compared with the previous methods, it has been greatly improved. It shows that the combination of convolution calculation and recurrent structure has a positive impact on the classification of AHTPs. The results show that this method is a feasible, efficient and competitive sequence analysis tool for AHTPs. Meanwhile, we design a friendly online prediction tool and it is freely accessible at http://ahtps.zhanglab.site/ .

Thirty years of molecular dynamics simulations on posttranslational modifications of proteins

Posttranslational modifications (PTMs) are an integral component to how cells respond to perturbation. While experimental advances have enabled improved PTM identification capabilities, the same throughput for characterizing how structural changes caused by PTMs equate to altered physiological function has not been maintained. In this Perspective, we cover the history of computational modeling and molecular dynamics simulations which have characterized the structural implications of PTMs. We distinguish results from different molecular dynamics studies based upon the timescales simulated and analysis approaches used for PTM characterization. Lastly, we offer insights into how opportunities for modern research efforts on in silico PTM characterization may proceed given current state-of-the-art computing capabilities and methodological advancements.

Regulation of PaRBOH1-mediated ROS production in Norway spruce by Ca2+ binding and phosphorylation

Plant respiratory burst oxidase homologs (RBOHs) are plasma membrane-localized NADPH oxidases that generate superoxide anion radicals, which then dismutate to H₂O₂, into the apoplast using cytoplasmic NADPH as an electron donor. PaRBOH1 is the most highly expressed RBOH gene in developing xylem as well as in a lignin-forming cell culture of Norway spruce (Picea abies L. Karst.). Since no previous information about regulation of gymnosperm RBOHs exist, our aim was to resolve how PaRBOH1 is regulated with a focus on phosphorylation. The N-terminal part of PaRBOH1 was found to contain several putative phosphorylation sites and a four-times repeated motif with similarities to the Botrytis-induced kinase 1 target site in Arabidopsis AtRBOHD. Phosphorylation was indicated for six of the sites in in vitro kinase assays using 15 amino-acid-long peptides for each of the predicted phosphotarget site in the presence of protein extracts of developing xylem. Serine and threonine residues showing positive response in the peptide assays were individually mutated to alanine (kinase-inactive) or to aspartate (phosphomimic), and the wild type PaRBOH1 and the mutated constructs transfected to human kidney embryogenic (HEK293T) cells with a low endogenous level of extracellular ROS production. ROS-producing assays with HEK cells showed that Ca²⁺ and phosphorylation synergistically activate the enzyme and identified several serine and threonine residues that are likely to be phosphorylated including a novel phosphorylation site not characterized in other plant species. These were further investigated with a phosphoproteomic study. Results of Norway spruce, the first gymnosperm species studied in relation to RBOH regulation, show that regulation of RBOH activity is conserved among seed plants.

Stimulation of Akt Phosphorylation and Glucose Transport by Metalloporphyrins with Peroxynitrite Decomposition Catalytic Activity

Iron porphyrin molecules such as hemin and iron(III) 4,4′,4″,4‴-(porphine-5,10,15,20-tetrayl)tetrakis(benzoic acid) (FeTBAP) have previously been shown to influence insulin signaling and glucose metabolism. We undertook this study to determine whether a catalytic action of iron porphyrin compounds would be related to their stimulation of insulin signaling and glucose uptake in C2C12 myotubes. FeTBAP did not display nitrite reductase activity or alter protein S-nitrosylation in myotubes, eliminating this as a candidate mode by which FeTBAP could act. FeTBAP displayed peroxynitrite decomposition catalytic activity in vitro. Additionally, in myotubes FeTBAP decreased protein nitration. The peroxynitrite decomposition catalyst Fe(III)5,10,15,20-tetrakis(4-sulfonatophenyl)porphyrinato chloride (FeTPPS) also decreased protein nitration in myotubes, but the iron porphyrin Fe(III)tetrakis(1-methyl-4-pyridyl)porphyrin pentachlorideporphyrin pentachloride (FeTMPyP) did not. FeTBAP and FeTPPS, but not FeTMPyP, showed in vitro peroxidase activity. Further, FeTBAP and FeTPPs, but not FeTMPyP, increased Akt phosphorylation and stimulated glucose uptake in myotubes. These findings suggest that iron porphyrin compounds with both peroxynitrite decomposition activity and peroxidase activity can stimulate insulin signaling and glucose transport in skeletal muscle cells.

Thiol-based Oxidative Posttranslational Modifications (OxiPTMs) of Plant Proteins

The thiol group of cysteine (Cys) residues, often present in the active center of the protein, is of particular importance to protein function, which is significantly determined by the redox state of a protein's environment. Our knowledge of different thiol-based oxidative posttranslational modifications (oxiPTMs), which compete for specific protein thiol groups, has increased over the last 10 years. The principal oxiPTMs include S-sulfenylation, S-glutathionylation, S-nitrosation, persulfidation, S-cyanylation and S-acylation. The role of each oxiPTM depends on the redox cellular state, which in turn depends on cellular homeostasis under either optimal or stressful conditions. Under such conditions, the metabolism of molecules such as glutathione, NADPH (reduced nicotinamide adenine dinucleotide phosphate), nitric oxide, hydrogen sulfide and hydrogen peroxide can be altered, exacerbated and, consequently, outside the cell's control. This review provides a broad overview of these oxiPTMs under physiological and unfavorable conditions, which can regulate the function of target proteins.

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.

Characterization of the B-Cell Epitopes of Echinococcus granulosus Histones H4 and H2A Recognized by Sera From Patients With Liver Cysts

Cystic echinococcosis (CE) is a zoonotic disease worldwide distributed, caused by the cestode Echinococcus granulosus sensu lato (E. granulosus), with an incidence rate of 50/100,000 person/year and a high prevalence in humans of 5-10%. Serology has variable sensitivity and specificity and low predictive values. Antigens used are from the hydatid fluid and recombinant antigens have not demonstrated superiority over hydatid fluid. A cell line called EGPE was obtained from E. granulosus sensu lato G1 strain from bovine liver. Serum from CE patients recognizes protein extracts from EGPE cells with higher sensitivity than protein extracts from hydatid fluid. In the present study, EGPE cell protein extracts and supernatants from cell colonies were eluted from a protein G affinity column performed with sera from 11 CE patients. LC-MS/MS proteomic analysis of the eluted proteins identified four E. granulosus histones: one histone H4 in the cell extract and supernatant, one histone H2A only in the cell extract, and two histones H2A only in the supernatant. This differential distribution of histones could reflect different parasite viability stages regarding their role in gene transcription and silencing and could interact with host cells. Bioinformatics tools characterized the linear and conformational epitopes involved in antibody recognition. The three-dimensional structure of each histone was obtained by molecular modeling and validated by molecular dynamics simulation and PCR confirmed the presence of the epitopes in the parasite genome. The three histones H2A were very different and had a less conserved sequence than the histone H4. Comparison of the histones of E. granulosus with those of other organisms showed exclusive regions for E. granulosus. Since histones play a role in the host-parasite relationship they could be good candidates to improve the predictive value of serology in CE.

Accurately predicting nitrosylated tyrosine sites using probabilistic sequence information

Post-translational modification (PTM) is defined as the enzymatic changes of proteins after the translation process in protein biosynthesis. Nitrotyrosine, which is one of the most important modifications of proteins, is interceded by the active nitrogen molecule. It is known to be associated with different diseases including autoimmune diseases characterized by chronic inflammation and cell damage. Currently, nitrotyrosine sites are identified using experimental approaches which are laborious and costly. In this study, we propose a new machine learning method called PredNitro to accurately predict nitrotyrosine sites. To build PredNitro, we use sequence coupling information from the neighboring amino acids of tyrosine residues along with a support vector machine as our classification technique.Our results demonstrates that PredNitro achieves 98.0% accuracy with more than 0.96 MCC and 0.99 AUC in both 5-fold cross-validation and jackknife cross-validation tests which are significantly better than those reported in previous studies. PredNitro is publicly available as an online predictor at: http://103.99.176.239/PredNitro.

Protein S-Nitrosation: Biochemistry, Identification, Molecular Mechanisms, and Therapeutic Applications

Protein S-nitrosation (SNO), a posttranslational modification (PTM) of cysteine (Cys) residues elicited by nitric oxide (NO), regulates a wide range of protein functions. As a crucial form of redox-based signaling by NO, SNO contributes significantly to the modulation of physiological functions, and SNO imbalance is closely linked to pathophysiological processes. Site-specific identification of the SNO protein is critical for understanding the underlying molecular mechanisms of protein function regulation. Although careful verification is needed, SNO modification data containing numerous functional proteins are a potential research direction for druggable target identification and drug discovery. Undoubtedly, SNO-related research is meaningful not only for the development of NO donor drugs but also for classic target-based drug design. Herein, we provide a comprehensive summary of SNO, including its origin and transport, identification, function, and potential contribution to drug discovery. Importantly, we propose new views to develop novel therapies based on potential protein SNO-sourced targets.

Hsp70 in Redox Homeostasis

Cellular redox homeostasis is precisely balanced by generation and elimination of reactive oxygen species (ROS). ROS are not only capable of causing oxidation of proteins, lipids and DNA to damage cells but can also act as signaling molecules to modulate transcription factors and epigenetic pathways that determine cell survival and death. Hsp70 proteins are central hubs for proteostasis and are important factors to ameliorate damage from different kinds of stress including oxidative stress. Hsp70 members often participate in different cellular signaling pathways via their clients and cochaperones. ROS can directly cause oxidative cysteine modifications of Hsp70 members to alter their structure and chaperone activity, resulting in changes in the interactions between Hsp70 and their clients or cochaperones, which can then transfer redox signals to Hsp70-related signaling pathways. On the other hand, ROS also activate some redox-related signaling pathways to indirectly modulate Hsp70 activity and expression. Post-translational modifications including phosphorylation together with elevated Hsp70 expression can expand the capacity of Hsp70 to deal with ROS-damaged proteins and support antioxidant enzymes. Knowledge about the response and role of Hsp70 in redox homeostasis will facilitate our understanding of the cellular knock-on effects of inhibitors targeting Hsp70 and the mechanisms of redox-related diseases and aging.

S-Nitrosation of E3 Ubiquitin Ligase Complex Components Regulates Hormonal Signalings in Arabidopsis

E3 ubiquitin ligases mediate the last step of the ubiquitination pathway in the ubiquitin-proteasome system (UPS). By targeting transcriptional regulators for their turnover, E3s play a crucial role in every aspect of plant biology. In plants, SKP1/CULLIN1/F-BOX PROTEIN (SCF)-type E3 ubiquitin ligases are essential for the perception and signaling of several key hormones including auxins and jasmonates (JAs). F-box proteins, TRANSPORT INHIBITOR RESPONSE 1 (TIR1) and CORONATINE INSENSITIVE 1 (COI1), bind directly transcriptional repressors AUXIN/INDOLE-3-ACETIC ACID (AUX/IAA) and JASMONATE ZIM-DOMAIN (JAZ) in auxin- and JAs-depending manner, respectively, which permits the perception of the hormones and transcriptional activation of signaling pathways. Redox modification of proteins mainly by S-nitrosation of cysteines (Cys) residues via nitric oxide (NO) has emerged as a valued regulatory mechanism in physiological processes requiring its rapid and versatile integration. Previously, we demonstrated that TIR1 and Arabidopsis thaliana SKP1 (ASK1) are targets of S-nitrosation, and these NO-dependent posttranslational modifications enhance protein-protein interactions and positively regulate SCF^TIR1 complex assembly and expression of auxin response genes. In this work, we confirmed S-nitrosation of Cys140 in TIR1, which was associated in planta to auxin-dependent developmental and stress-associated responses. In addition, we provide evidence on the modulation of the SCF^COI1 complex by different S-nitrosation events. We demonstrated that S-nitrosation of ASK1 Cys118 enhanced ASK1-COI1 protein-protein interaction. Overexpression of non-nitrosable ask1 mutant protein impaired the activation of JA-responsive genes mediated by SCF^COI1 illustrating the functional relevance of this redox-mediated regulation in planta. In silico analysis positions COI1 as a promising S-nitrosation target, and demonstrated that plants treated with methyl JA (MeJA) or S-nitrosocysteine (NO-Cys, S-nitrosation agent) develop shared responses at a genome-wide level. The regulation of SCF components involved in hormonal perception by S-nitrosation may represent a key strategy to determine the precise time and site-dependent activation of each hormonal signaling pathway and highlights NO as a pivotal molecular player in these scenarios.

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.

O-glycosylation site prediction for Homo sapiens by combining properties and sequence features with support vector machine

O-glycosylation is a protein posttranslational modification important in regulating almost all cells. It is related to a large number of physiological and pathological phenomena. Recognizing O-glycosylation sites is the key to further investigating the molecular mechanism of protein posttranslational modification. This study aimed to collect a reliable dataset on Homo sapiens and develop an O-glycosylation predictor for Homo sapiens, named Captor, through multiple features. A random undersampling method and a synthetic minority oversampling technique were employed to deal with imbalanced data. In addition, the Kruskal-Wallis (K-W) test was adopted to optimize feature vectors and improve the performance of the model. A support vector machine, due to its optimal performance, was used to train and optimize the final prediction model after a comprehensive comparison of various classifiers in traditional machine learning methods and deep learning. On the independent test set, Captor outperformed the existing O-glycosylation tool, suggesting that Captor could provide more instructive guidance for further experimental research on O-glycosylation. The source code and datasets are available at https://github.com/YanZhu06/Captor/.

Gutter oil detection for food safety based on multi-feature machine learning and implementation on FPGA with approximate multipliers

Since consuming gutter oil does great harm to people's health, the Food Safety Administration has always been seeking for a more effective and timely supervision. As laboratory tests consume much time, and existing field tests have excessive limitations, a more comprehensive method is in great need. This is the first time a study proposes machine learning algorithms for real-time gutter oil detection under multiple feature dimensions. Moreover, it is deployed on FPGA to be low-power and portable for actual use. Firstly, a variety of oil samples are generated by simulating the real detection environment. Next, based on previous studies, sensors are used to collect significant features that help distinguish gutter oil. Then, the acquired features are filtered and compared using a variety of classifiers. The best classification result is obtained by k-NN with an accuracy of 97.18%, and the algorithm is deployed to FPGA with no significant loss of accuracy. Power consumption is further reduced with the approximate multiplier we designed. Finally, the experimental results show that compared with all other platforms, the whole FPGA-based classification process consumes 4.77 µs and the power consumption is 65.62 mW. The dataset, source code and the 3D modeling file are all open-sourced.

Mul-SNO: A novel prediction tool for S-nitrosylation sites based on deep learning methods

Protein s-nitrosylation (SNO is one of the most important post-translational modifications and is formed by the covalent modification of nitric oxide and cysteine residues. Extensive studies have shown that SNO plays a pivotal role in the plant immune response and treating various major human diseases. In recent years, SNO sites have become a hot research topic. Traditional biochemical methods for SNO site identification are time-consuming and costly. In this study, we developed an economical and efficient SNO site prediction tool named Mul-SNO. Mul-SNO ensembled current popular and powerful deep learning model bidirectional long short-term memory (BiLSTM and bidirectional encoder representations from Transformers (BERT . Compared with existing state-of-the-art methods, Mul-SNO obtained better ACC of 0.911 and 0.796 based on 10-fold cross-validation and independent data sets, respectively. The prediction server can be obtained for free at http://lab.malab.cn/~mjq/Mul-SNO/.

Altitude acclimatization via hypoxia-mediated oxidative eustress involves interplay of protein nitrosylation and carbonylation: A redoxomics perspective

AIM

Hypoxia is an important feature of multiple diseases like cancer and obesity and also an environmental stressor to high altitude travelers. Emerging research suggests the importance of redox signaling in physiological responses transforming the notion of oxidative stress into eustress and distress. However, the behavior of redox protein post-translational modifications (PTMs), and their correlation with stress acclimatization in humans remains sketchy. Scant information exists about modifications in redoxome during physiological exposure to environmental hypoxia. In this study, we investigated redox PTMs, nitrosylation and carbonylation, in context of extended environmental hypoxia exposure.

METHODS

The volunteers were confirmed to be free of any medical conditions and matched for age and weight. The human global redoxome and the affected networks were investigated using TMT-labeled quantitative proteo-bioinformatics and biochemical assays. The percolator PSM algorithm was used for peptide-spectrum match (PSM) validation in database searches. The FDR for peptide matches was set to 0.01. 1-way ANOVA and Tukey's Multiple Comparison test were used for biochemical assays. p-value<0.05 was considered statistically significant. Three independent experiments (biological replicates) were performed. Results were presented as Mean ± standard error of mean (SEM).

KEY FINDINGS

This investigation revealed direct and indirect interplay between nitrosylation and carbonylation especially within coagulation and inflammation networks; interlinked redox signaling (via nitrosylation‑carbonylation); and novel nitrosylation and carbonylation sites in individual proteins.

SIGNIFICANCE

This study elucidates the role of redox PTMs in hypoxia signaling favoring tolerance and survival. Also, we demonstrated direct and indirect interplay between nitrosylation and carbonylation is crucial to extended hypoxia tolerance.

DeepSADPr: A hybrid-learning architecture for serine ADP-ribosylation site prediction

Protein adenosine diphosphate-ribosylation (ADPr) is caused by the covalent binding of one or more ADP-ribose moieties to a target protein and regulates the biological functions of the target protein. To fully understand the regulatory mechanism of ADP-ribosylation, the essential step is the identification of the ADPr sites from the proteome. As the experimental approaches are costly and time-consuming, it is necessary to develop a computational tool to predict ADPr sites. Recently, serine has been found to be the major residue type for ADP-ribosylation but no predictor is available. In this study, we collected thousands of experimentally validated human ADPr sites on serine residue and constructed several different machine-learning classifiers. We found that the hybrid model, dubbed DeepSADPr, which integrated the one-dimensional convolutional neural network (CNN) with the One-Hot encoding approach and the word-embedding approach, compared favourably to other models in terms of both ten-fold cross-validation and independent test. Its AUC values reached 0.935 for ten-fold cross-validation. Its values of sensitivity, accuracy and Matthews's correlation coefficient reached 0.933, 0.867 and 0.740, respectively, with the fixed specificity value of 0.80. Overall, DeepSADPr is the first classifier for predicting Serine ADPr sites, which is available at http://www.bioinfogo.org/DeepSADPr.

TIRAP in the Mechanism of Inflammation

The Toll-interleukin-1 Receptor (TIR) domain-containing adaptor protein (TIRAP) represents a key intracellular signalling molecule regulating diverse immune responses. Its capacity to function as an adaptor molecule has been widely investigated in relation to Toll-like Receptor (TLR)-mediated innate immune signalling. Since the discovery of TIRAP in 2001, initial studies were mainly focused on its role as an adaptor protein that couples Myeloid differentiation factor 88 (MyD88) with TLRs, to activate MyD88-dependent TLRs signalling. Subsequent studies delineated TIRAP’s role as a transducer of signalling events through its interaction with non-TLR signalling mediators. Indeed, the ability of TIRAP to interact with an array of intracellular signalling mediators suggests its central role in various immune responses. Therefore, continued studies that elucidate the molecular basis of various TIRAP-protein interactions and how they affect the signalling magnitude, should provide key information on the inflammatory disease mechanisms. This review summarizes the TIRAP recruitment to activated receptors and discusses the mechanism of interactions in relation to the signalling that precede acute and chronic inflammatory diseases. Furthermore, we highlighted the significance of TIRAP-TIR domain containing binding sites for several intracellular inflammatory signalling molecules. Collectively, we discuss the importance of the TIR domain in TIRAP as a key interface involved in protein interactions which could hence serve as a therapeutic target to dampen the extent of acute and chronic inflammatory conditions.

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/.

Yin and Yang in Post-Translational Modifications of Human D-Amino Acid Oxidase

In the central nervous system, the flavoprotein D-amino acid oxidase is responsible for catabolizing D-serine, the main endogenous coagonist of N-methyl-D-aspartate receptor. Dysregulation of D-serine brain levels in humans has been associated with neurodegenerative and psychiatric disorders. This D-amino acid is synthesized by the enzyme serine racemase, starting from the corresponding L-enantiomer, and degraded by both serine racemase (via an elimination reaction) and the flavoenzyme D-amino acid oxidase. To shed light on the role of human D-amino acid oxidase (hDAAO) in D-serine metabolism, the structural/functional relationships of this enzyme have been investigated in depth and several strategies aimed at controlling the enzymatic activity have been identified. Here, we focused on the effect of post-translational modifications: by using a combination of structural analyses, biochemical methods, and cellular studies, we investigated whether hDAAO is subjected to nitrosylation, sulfhydration, and phosphorylation. hDAAO is S-nitrosylated and this negatively affects its activity. In contrast, the hydrogen sulfide donor NaHS seems to alter the enzyme conformation, stabilizing a species with higher affinity for the flavin adenine dinucleotide cofactor and thus positively affecting enzymatic activity. Moreover, hDAAO is phosphorylated in cerebellum; however, the protein kinase involved is still unknown. Taken together, these findings indicate that D-serine levels can be also modulated by post-translational modifications of hDAAO as also known for the D-serine synthetic enzyme serine racemase.

DeepVISP: Deep Learning for Virus Site Integration Prediction and Motif Discovery

Approximately 15% of human cancers are estimated to be attributed to viruses. Virus sequences can be integrated into the host genome, leading to genomic instability and carcinogenesis. Here, a new deep convolutional neural network (CNN) model is developed with attention architecture, namely DeepVISP, for accurately predicting oncogenic virus integration sites (VISs) in the human genome. Using the curated benchmark integration data of three viruses, hepatitis B virus (HBV), human herpesvirus (HPV), and Epstein-Barr virus (EBV), DeepVISP achieves high accuracy and robust performance for all three viruses through automatically learning informative features and essential genomic positions only from the DNA sequences. In comparison, DeepVISP outperforms conventional machine learning methods by 8.43-34.33% measured by area under curve (AUC) value enhancement in three viruses. Moreover, DeepVISP can decode cis-regulatory factors that are potentially involved in virus integration and tumorigenesis, such as HOXB7, IKZF1, and LHX6. These findings are supported by multiple lines of evidence in literature. The clustering analysis of the informative motifs reveales that the representative k-mers in clusters could help guide virus recognition of the host genes. A user-friendly web server is developed for predicting putative oncogenic VISs in the human genome using DeepVISP.

PredNTS: Improved and Robust Prediction of Nitrotyrosine Sites by Integrating Multiple Sequence Features

Nitrotyrosine, which is generated by numerous reactive nitrogen species, is a type of protein post-translational modification. Identification of site-specific nitration modification on tyrosine is a prerequisite to understanding the molecular function of nitrated proteins. Thanks to the progress of machine learning, computational prediction can play a vital role before the biological experimentation. Herein, we developed a computational predictor PredNTS by integrating multiple sequence features including K-mer, composition of k-spaced amino acid pairs (CKSAAP), AAindex, and binary encoding schemes. The important features were selected by the recursive feature elimination approach using a random forest classifier. Finally, we linearly combined the successive random forest (RF) probability scores generated by the different, single encoding-employing RF models. The resultant PredNTS predictor achieved an area under a curve (AUC) of 0.910 using five-fold cross validation. It outperformed the existing predictors on a comprehensive and independent dataset. Furthermore, we investigated several machine learning algorithms to demonstrate the superiority of the employed RF algorithm. The PredNTS is a useful computational resource for the prediction of nitrotyrosine sites. The web-application with the curated datasets of the PredNTS is publicly available.

pCysMod: Prediction of Multiple Cysteine Modifications Based on Deep Learning Framework

Thiol groups on cysteines can undergo multiple post-translational modifications (PTMs), acting as a molecular switch to maintain redox homeostasis and regulating a series of cell signaling transductions. Identification of sophistical protein cysteine modifications is crucial for dissecting its underlying regulatory mechanism. Instead of a time-consuming and labor-intensive experimental method, various computational methods have attracted intense research interest due to their convenience and low cost. Here, we developed the first comprehensive deep learning based tool pCysMod for multiple protein cysteine modification prediction, including S-nitrosylation, S-palmitoylation, S-sulfenylation, S-sulfhydration, and S-sulfinylation. Experimentally verified cysteine sites curated from literature and sites collected by other databases and predicting tools were integrated as benchmark dataset. Several protein sequence features were extracted and united into a deep learning model, and the hyperparameters were optimized by particle swarm optimization algorithms. Cross-validations indicated our model showed excellent robustness and outperformed existing tools, which was able to achieve an average AUC of 0.793, 0.807, 0.796, 0.793, and 0.876 for S-nitrosylation, S-palmitoylation, S-sulfenylation, S-sulfhydration, and S-sulfinylation, demonstrating pCysMod was stable and suitable for protein cysteine modification prediction. Besides, we constructed a comprehensive protein cysteine modification prediction web server based on this model to benefit the researches finding the potential modification sites of their interested proteins, which could be accessed at http://pcysmod.omicsbio.info. This work will undoubtedly greatly promote the study of protein cysteine modification and contribute to clarifying the biological regulation mechanisms of cysteine modification within and among the cells.

Nitric oxide signaling in the plant nucleus: the function of nitric oxide in chromatin modulation and transcription

Nitric oxide (NO) is involved in a vast number of physiologically important processes in plants, such as organ development, stress resistance, and immunity. Transduction of NO bioactivity is generally achieved by post-translational modification of proteins, with S-nitrosation of cysteine residues as the predominant form. While traditionally the subcellular location of the factors involved was of lesser importance, recent studies identified the connection between NO and transcriptional activity and thereby raised the question about the route of NO into the nuclear sphere. Identification of NO-affected transcription factors and chromatin-modifying histone deacetylases implicated the important role of NO signaling in the plant nucleus as a regulator of epigenetic mechanisms and gene transcription. Here, we discuss the relationship between NO and its directly regulated protein targets in the nuclear environment, focusing on S-nitrosated chromatin modulators and transcription factors.

Recent Advances in Predicting Protein S-Nitrosylation Sites

Protein S-nitrosylation (SNO) is a process of covalent modification of nitric oxide (NO) and its derivatives and cysteine residues. SNO plays an essential role in reversible posttranslational modifications of proteins. The accurate prediction of SNO sites is crucial in revealing a certain biological mechanism of NO regulation and related drug development. Identification of the sites of SNO in proteins is currently a very hot topic. In this review, we briefly summarize recent advances in computationally identifying SNO sites. The challenges and future perspectives for identifying SNO sites are also discussed. We anticipate that this review will provide insights into research on SNO site prediction.

Human carbonic anhydrases and post-translational modifications: a hidden world possibly affecting protein properties and functions

Human carbonic anhydrases (CAs) have become a well-recognized target for the design of inhibitors and activators with biomedical applications. Accordingly, an enormous amount of literature is available on their biochemical, functional and structural aspects. Nevertheless post-translational modifications (PTMs) occurring on these enzymes and their functional implications have been poorly investigated so far. To fill this gap, in this review we have analysed all PTMs occurring on human CAs, as deriving from the search in dedicated databases, showing a widespread occurrence of modification events in this enzyme family. By combining these data with sequence alignments, inspection of 3 D structures and available literature, we have summarised the possible functional implications of these PTMs. Although in some cases a clear correlation between a specific PTM and the CA function has been highlighted, many modification events still deserve further dedicated studies.

DeepCSO: A Deep-Learning Network Approach to Predicting Cysteine S-Sulphenylation Sites

Cysteine S-sulphenylation (CSO), as a novel post-translational modification (PTM), has emerged as a potential mechanism to regulate protein functions and affect signal networks. Because of its functional significance, several prediction approaches have been developed. Nevertheless, they are based on a limited dataset from Homo sapiens and there is a lack of prediction tools for the CSO sites of other species. Recently, this modification has been investigated at the proteomics scale for a few species and the number of identified CSO sites has significantly increased. Thus, it is essential to explore the characteristics of this modification across different species and construct prediction models with better performances based on the enlarged dataset. In this study, we constructed several classifiers and found that the long short-term memory model with the word-embedding encoding approach, dubbed LSTM_WE, performs favorably to the traditional machine-learning models and other deep-learning models across different species, in terms of cross-validation and independent test. The area under the receiver operating characteristic (ROC) curve for LSTM_WE ranged from 0.82 to 0.85 for different organisms, which was superior to the reported CSO predictors. Moreover, we developed the general model based on the integrated data from different species and it showed great universality and effectiveness. We provided the on-line prediction service called DeepCSO that included both species-specific and general models, which is accessible through http://www.bioinfogo.org/DeepCSO.

Prediction of bio-sequence modifications and the associations with diseases

Modifications of protein, RNA and DNA play an important role in many biological processes and are related to some diseases. Therefore, accurate identification and comprehensive understanding of protein, RNA and DNA modification sites can promote research on disease treatment and prevention. With the development of sequencing technology, the number of known sequences has continued to increase. In the past decade, many computational tools that can be used to predict protein, RNA and DNA modification sites have been developed. In this review, we comprehensively summarized the modification site predictors for three different biological sequences and the association with diseases. The relevant web server is accessible at http://lab.malab.cn/∼acy/PTM_data/ some sample data on protein, RNA and DNA modification can be downloaded from that website.

3-Nitrotyrosine and related derivatives in proteins: precursors, radical intermediates and impact in function

Oxidative post-translational modification of proteins by molecular oxygen (O2)- and nitric oxide (•NO)-derived reactive species is a usual process that occurs in mammalian tissues under both physiological and pathological conditions and can exert either regulatory or cytotoxic effects. Although the side chain of several amino acids is prone to experience oxidative modifications, tyrosine residues are one of the preferred targets of one-electron oxidants, given the ability of their phenolic side chain to undergo reversible one-electron oxidation to the relatively stable tyrosyl radical. Naturally occurring as reversible catalytic intermediates at the active site of a variety of enzymes, tyrosyl radicals can also lead to the formation of several stable oxidative products through radical-radical reactions, as is the case of 3-nitrotyrosine (NO2Tyr). The formation of NO2Tyr mainly occurs through the fast reaction between the tyrosyl radical and nitrogen dioxide (•NO2). One of the key endogenous nitrating agents is peroxynitrite (ONOO-), the product of the reaction of superoxide radical (O2•-) with •NO, but ONOO--independent mechanisms of nitration have been also disclosed. This chemical modification notably affects the physicochemical properties of tyrosine residues and because of this, it can have a remarkable impact on protein structure and function, both in vitro and in vivo. Although low amounts of NO2Tyr are detected under basal conditions, significantly increased levels are found at pathological states related with an overproduction of reactive species, such as cardiovascular and neurodegenerative diseases, inflammation and aging. While NO2Tyr is a well-established stable oxidative stress biomarker and a good predictor of disease progression, its role as a pathogenic mediator has been laboriously defined for just a small number of nitrated proteins and awaits further studies.

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.

DeepKhib: A Deep-Learning Framework for Lysine 2-Hydroxyisobutyrylation Sites Prediction

As a novel type of post-translational modification, lysine 2-Hydroxyisobutyrylation (K hib ) plays an important role in gene transcription and signal transduction. In order to understand its regulatory mechanism, the essential step is the recognition of K hib sites. Thousands of K hib sites have been experimentally verified across five different species. However, there are only a couple traditional machine-learning algorithms developed to predict K hib sites for limited species, lacking a general prediction algorithm. We constructed a deep-learning algorithm based on convolutional neural network with the one-hot encoding approach, dubbed CNN OH . It performs favorably to the traditional machine-learning models and other deep-learning models across different species, in terms of cross-validation and independent test. The area under the ROC curve (AUC) values for CNN OH ranged from 0.82 to 0.87 for different organisms, which is superior to the currently available K hib predictors. Moreover, we developed the general model based on the integrated data from multiple species and it showed great universality and effectiveness with the AUC values in the range of 0.79-0.87. Accordingly, we constructed the on-line prediction tool dubbed DeepKhib for easily identifying K hib sites, which includes both species-specific and general models. DeepKhib is available at http://www.bioinfogo.org/DeepKhib.

DeepTL-Ubi: A novel deep transfer learning method for effectively predicting ubiquitination sites of multiple species

Ubiquitination is one of the most important post-translational modifications which involves in many biological processes. Because mass spectrometry-based ubiquitination site identification methods are costly and time consuming, computational approaches provide alternative ways to the determination of ubiquitination sites. Although machine learning based methods can effectively predict ubiquitination sites, most of them rely on feature engineering, which may lead to bias or incomplete feature. Recently, deep learning has achieved great success in prediction of post-translational modification sites. However, deep learning method has not been explored in the prediction of species-specific ubiquitination sites. In this paper, we propose a novel transfer deep learning method, named DeepTL-Ubi, for predicting ubiquitination sites of multiple species. DeepTL-Ubi enhances the performance of species-specific ubiquitination site prediction by transferring common knowledge from the large amount of human data to other species, which effectively solves the problem of insufficient training data for other species. Besides, we train and test our model by collecting ubiquitination sites for multiple species from several sources. Experiment results show that our transfer learning technique can effectively improve the predictive performance of species with small sample size, and DeepTL-Ubi is superior to existing tools in many species. The source code and training data of DeepTL-Ubi are publicly deposited at https://github.com/USTC-HIlab/DeepTL-Ubi.

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.

Incorporating hybrid models into lysine malonylation sites prediction on mammalian and plant proteins

Protein malonylation, a reversible post-translational modification of lysine residues, is associated with various biological functions, such as cellular regulation and pathogenesis. In proteomics, to improve our understanding of the mechanisms of malonylation at the molecular level, the identification of malonylation sites via an efficient methodology is essential. However, experimental identification of malonylated substrates via mass spectrometry is time-consuming, labor-intensive, and expensive. Although numerous methods have been developed to predict malonylation sites in mammalian proteins, the computational resource for identifying plant malonylation sites is very limited. In this study, a hybrid model incorporating multiple convolutional neural networks (CNNs) with physicochemical properties, evolutionary information, and sequenced-based features was developed for identifying protein malonylation sites in mammals. For plant malonylation, multiple CNNs and random forests were integrated into a secondary modeling phase using a support vector machine. The independent testing has demonstrated that the mammalian and plant malonylation models can yield the area under the receiver operating characteristic curves (AUC) at 0.943 and 0.772, respectively. The proposed scheme has been implemented as a web-based tool, Kmalo (https://fdblab.csie.ncu.edu.tw/kmalo/home.html), which can help facilitate the functional investigation of protein malonylation on mammals and plants.