Mini-review: Recent advances in post-translational modification site prediction based on deep learning

Meng, Lingkuan; Chan, Wai-Sum; Huang, Lei; Liu, Linjing; Chen, Xingjian; Zhang, Weitong; Cheng, Ke; Sun, Hongyan; Wong, Ka-Chun

doi:10.1016/j.csbj.2022.06.045

Cited by 19 publications

(10 citation statements)

References 131 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, we will develop new tools for embedded motif analysis, batch searching function, and evolutionary analysis. Moreover, recent applications of deep learning algorithms in various prediction tasks of PTM sites [20, 35] have inspire us to take full advantage of cutting-edge artificial intelligent technologies in the accurate prediction of N -phosphorylation.…”

Section: Future Developmentmentioning

confidence: 99%

Nphos: Database and Predictor of ProteinN-phosphorylation

Zhao,

Ding,

Chen

et al. 2023

Preprint

View full text Add to dashboard Cite

ProteinN-phosphorylation widely present in nature and participates in various biological functions. However, current knowledge onN-phosphorylation is extremely limited compared to that onO-phosphorylation. In this study, we collected 11,710 experimentally verifiedN-phosphosites of 7344 proteins from 39 species and subsequently constructed the database Nphos to share up-to-date information on proteinN-phosphorylation. Upon these substantial data, we characterized the sequential and structural features of proteinN-phosphorylation. Moreover, after comparing of hundreds of learning models, we chose and optimized gradient boosting decision tree (GBDT) models to predict three types of humanN-phosphorylation, achieving mean areas under the receiver operating characteristic curve (AUC) of 90.56%, 91.24%, and 92.01% for pHis, pLys, and pArg, respectively. Meanwhile, we discovered 488,825 distinctN-phosphosites in the human proteome. The models were also deployed in Nphos for interactiveN-phosphosite prediction. In summary, this work provides new insights and points for both flexible and focused investigations ofN-phosphorylation. It will also facilitate a deeper and more systematic understanding of proteinN-phosphorylation modification by providing a data and technical foundation. Nphos is freely available athttp://www.bio-add.organdhttp://ppodd.org.cn/Nphos/.

show abstract

Section: Future Developmentmentioning

confidence: 99%

Nphos: Database and Predictor of ProteinN-phosphorylation

Zhao,

Ding,

Chen

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Moreover, iSNO-PseAAC [ 11 ] is another approach developed by Xu et al that uses PseAAC to represent protein sequences for prediction of protein S-nitrosylation sites. Recently, various deep learning-based methods [ 13 , 14 ] have been developed for prediction of various post-translation modification sites including SNO sites. In that regard, DeepNitro [ 15 ], a deep learning-based approach, developed by Xie et al for the prediction of protein S-nitrosylation sites uses four different types of features: one-hot encoding, Property Factor Representation (PFR), k-space spectrum, and PSSM encoding.…”

Section: Introductionmentioning

confidence: 99%

“…Lately, we have witnessed the development of exciting array of Natural Language Processing (NLP) algorithms and technologies including recent breakthroughs in the field of bioinformatics [ 14 , 18 – 20 ]. Among these developments, language models (LMs) have emerged as a powerful paradigm in NLP for learning embeddings directly from large, unlabeled natural language datasets.…”

Section: Introductionmentioning

confidence: 99%

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

et al. 2023

View full text Add to dashboard Cite

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.

show abstract

“…1) and exhibit interesting biological functions in epigenetics and metabolism. Signaling pathways involving distinct lysine PTMs are increasingly recognized to be interconnected in eukaryotes (L. Meng et al., 2022). Some of these acylations have been reported and are highly conserved across different species.…”

Section: Introductionmentioning

confidence: 99%

“…Posttranslational modifications (PTMs) of proteins are fundamental mechanisms that regulate cellular processes in all domains of life (L. Meng et al., 2022; Soufi et al., 2012). Fatty acylations on lysine residues have been recognized as crucial PTM marks with various regulatory effects on key biological pathways (Barnes et al., 2019; Sabari et al., 2015; Verdin & Ott, 2015).…”

Section: Introductionmentioning

confidence: 99%

New Histone Lysine Acylation Biomarkers and Their Roles in Epigenetic Regulation

Cat

Zheng

2023

Current Protocols

View full text Add to dashboard Cite

Protein posttranslational modification (PTM) is a biochemical mechanism benefitting cellular adaptation to dynamic intracellular and environmental conditions. Recently, several acylation marks have been identified as new protein PTMs occurring on specific lysine residues in mammalian cells: isobutyrylation, methacrylation, benzoylation, isonicotinylation, and lactylation. These acylation marks were initially discovered to occur on nucleosomal histones, but they potentially occur as prevalent biomarkers on non-histone proteins as well. The existence of these PTMs is a downstream consequence of metabolism and demonstrates the intimate crosstalk between active cellular metabolites and regulation of protein function. Emerging evidence indicates that these acylation marks on histones affect DNA transcription and are functionally distinct from the well-studied lysine acetylation. Herein, we discuss enzymatic regulation and metabolic etiology of these acylations, 'reader' proteins that recognize different acylations, and their possible physiological and pathological functions. Several of these modifications correlate with other well-studied acylations and fine-tune the regulation of gene expression. Overall, findings of these acylation marks reveal new molecular links between metabolism and epigenetics and open up many questions for future investigation.

show abstract

Mini-review: Recent advances in post-translational modification site prediction based on deep learning

Cited by 19 publications

References 131 publications

Nphos: Database and Predictor of ProteinN-phosphorylation

Nphos: Database and Predictor of ProteinN-phosphorylation

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

New Histone Lysine Acylation Biomarkers and Their Roles in Epigenetic Regulation

Contact Info

Product

Resources

About