CoChat
Sign Up
Cited by 1Machine Learning in BioinformaticsGlycosylation and Glycoproteins Researchvaccines and immunoinformatics approaches

The DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.

StackGlyEmbed: prediction of N-linked glycosylation sites using protein language models

Open access
Nafi, Md Muhaiminul Islam, Rahman, M Saifur·2024·Bioinformatics Advances
DOI 10.1093/bioadv/vbaf146PMC PMC12237515

Published version of a preprint

Open this paper in CoChat — free account

Abstract

Motivation: N-linked glycosylation is one of the most basic post-translational modifications (PTMs) where oligosaccharides covalently bond with Asparagine (N). These are found in the conserved regions like N-X-S or N-X-T where X can be any residue except Proline (P). Prediction of N-linked glycosylation sites has great importance as these PTMs play a vital role in many biological processes and functionalities. Experimental methods, such as mass spectrometry, for detecting N-linked glycosylation sites are very expensive. Therefore, the prediction of N-linked glycosylation sites has become an important research field. Results: In this work, we propose StackGlyEmbed, a stacking ensemble machine learning model, to computationally predict N-linked glycosylation sites. We have explored embeddings from several protein language models and built the stacking ensemble using Support Vector Machine (SVM), Extreme Gradient Boosting (XGB) and K-nearest Neighbor (KNN) learners in the base layer, with a second SVM model in the meta layer. StackGlyEmbed achieves 98.2% sensitivity, 92.5% balanced accuracy, 89.1% F1-score and 82.6% Matthew’s correlation coefficient in independent testing, outperforming the existing state-of-the-art methods. Availability and implementation: StackGlyEmbed is freely available at: https://github.com/nafcoder/StackGlyEmbed.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1093/bioadv/vbaf146

Cites

2 of 2 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 58

  1. Hou, 2023, EMNGly: predicting N-linked glycosylation sites using the language models for feature extraction, Bioinformatics, 39, btad650, 10.1093/bioinformatics/btad650 · DOI
  2. Abdi, 2010, Principal component analysis, WIREs Comput Stats, 2, 433, 10.1002/wics.101 · DOI · Paper page
  3. Agarwal, 1969, Feline gastrin. An example of peptide sequence analysis by mass spectrometry, J Am Chem Soc, 91, 3096, 10.1021/ja01039a051 · DOI
  4. Altman, 1994, Diagnostic tests. 1: sensitivity and specificity, BMJ, 308, 1552, 10.1136/bmj.308.6943.1552 · DOI
  5. Brandes, 2022, ProteinBERT: a universal deep-learning model of protein sequence and function, Bioinformatics, 38, 2102, 10.1093/bioinformatics/btac020 · DOI · Paper page
  6. Chauhan, 2012, GlycoPP: a webserver for prediction of N-and O-glycosites in prokaryotic protein sequences, PLoS One, 7, e40155, 10.1371/journal.pone.0040155 · DOI
  7. Chauhan, 2013, In silico platform for prediction of N-, O-and C-glycosites in eukaryotic protein sequences, PLoS One, 8, e67008, 10.1371/journal.pone.0067008 · DOI
  8. Chien, 2020, N-GlycoGo: predicting protein N-glycosylation sites on imbalanced data sets by using heterogeneous and comprehensive strategy, IEEE Access, 8, 165944, 10.1109/ACCESS.2020.3022629 · DOI
  9. Chuang, 2012, Computational prediction of N-linked glycosylation incorporating structural properties and patterns, Bioinformatics, 28, 2249, 10.1093/bioinformatics/bts426 · DOI
  10. Consortium, 2019, UniProt: a worldwide hub of protein knowledge, Nucleic Acids Res, 47, D506, 10.1093/nar/gky1049 · DOI · Paper page
  11. Dang, 2024, xCAPT5: protein–protein interaction prediction using deep and wide multi-kernel pooling convolutional neural networks with protein language model, BMC Bioinform, 25, 106, 10.1186/s12859-024-05725-6 · DOI
  12. DeLano, 2002, Pymol: an open-source molecular graphics tool, CCP4 Newsl Protein Crystallogr, 40, 82
  13. Elnaggar, 2022, Prottrans: toward understanding the language of life through self-supervised learning, IEEE Trans Pattern Anal Mach Intell, 44, 7112, 10.1109/TPAMI.2021.3095381 · DOI · Paper page
  14. Fawcett, 2006, An introduction to ROC analysis, Pattern Recognit Lett, 27, 861, 10.1016/j.patrec.2005.10.010 · DOI · Paper page
  15. Gavel, 1990, Sequence differences between glycosylated and non-glycosylated Asn-X-Thr/ser acceptor sites: implications for protein engineering, Protein Eng, 3, 433, 10.1093/protein/3.5.433 · DOI
  16. Goodfellow, 2016, Deep Learning
  17. Gupta, 2001, Biocomputing 2002, 310, 10.1142/9789812799623_0029 · DOI
  18. Gupta, 2004, Prediction of N-glycosylation sites in human proteins, Pac Symp Biocomput, 9, 310
  19. Gurung, 2024, 2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 6893, 10.1109/BIBM62325.2024.10822503 · DOI
  20. Huang, 2010, CD-HIT suite: a web server for clustering and comparing biological sequences, Bioinformatics, 26, 680, 10.1093/bioinformatics/btq003 · DOI
  21. Keilwagen, 2014, Area under precision-recall curves for weighted and unweighted data, PLoS One, 9, e92209, 10.1371/journal.pone.0092209 · DOI
  22. Kim, 2023, AttSec: protein secondary structure prediction by capturing local patterns from attention map, BMC Bioinform, 24, 183, 10.1186/s12859-023-05310-3 · DOI
  23. Kowarik, 2006, Definition of the bacterial N-glycosylation site consensus sequence, EMBO J, 25, 1957, 10.1038/sj.emboj.7601087 · DOI
  24. Li, 2015, GlycoMine: a machine learning-based approach for predicting N-, C-and O-linked glycosylation in the human proteome, Bioinformatics, 31, 1411, 10.1093/bioinformatics/btu852 · DOI
  25. Li, 2006, Cd-hit: a fast program for clustering and comparing large sets of protein or nucleotide sequences, Bioinformatics, 22, 1658, 10.1093/bioinformatics/btl158 · DOI
  26. Liu, 2024, Viruspredictor: xgboost-based software to predict virus-related sequences in human data, Bioinformatics, 40, btae192, 10.1093/bioinformatics/btae192 · DOI
  27. Lundberg, 2017, A unified approach to interpreting model predictions, Adv Neural Inf Process Syst, 30, 4765
  28. Marquet, 2022, Embeddings from protein language models predict conservation and variant effects, Hum Genet, 141, 1629, 10.1007/s00439-021-02411-y · DOI
  29. Medzihradszky, 2005, Peptide sequence analysis, Methods Enzymol, 402, 209, 10.1016/S0076-6879(05)02007-0 · DOI
  30. Mishra, 2024, 2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 6127, 10.1109/BIBM62325.2024.10821747 · DOI
  31. Nita-Lazar, 2005, The NXS/T consensus sequence is required but not sufficient for bacterial N-linked protein glycosylation, Glycobiology, 15, 361, 10.1093/glycob/cwi019 · DOI
  32. Pakhrin, 2021, DeepNGlyPred: a deep neural network-based approach for human N-linked glycosylation site prediction, Molecules, 26, 7314, 10.3390/molecules26237314 · DOI
  33. Pakhrin, 2023, LMNglyPred: prediction of human N-linked glycosylation sites using embeddings from a pre-trained protein language model, Glycobiology, 33, 411, 10.1093/glycob/cwad033 · DOI
  34. Palmisano, 2012, Chemical deamidation: a common pitfall in large-scale N-linked glycoproteomic mass spectrometry-based analyses, J Proteome Res, 11, 1949, 10.1021/pr2011268 · DOI
  35. Petrescu, 2004, Statistical analysis of the protein environment of N-glycosylation sites: implications for occupancy, structure, and folding, Glycobiology, 14, 103, 10.1093/glycob/cwh008 · DOI
  36. Pitti, 2019, N-GlyDE: a two-stage N-linked glycosylation site prediction incorporating gapped dipeptides and pattern-based encoding, Sci Rep, 9, 15975, 10.1038/s41598-019-52341-z · DOI
  37. Pugalenthi, 2020, Nglyc: a random Forest method for prediction of N-glycosylation sites in eukaryotic protein sequence, Protein Pept Lett, 27, 178, 10.2174/0929866526666191002111404 · DOI
  38. Ramazi, 2021, Post-translational modifications in proteins: resources, tools and prediction methods, Database, 2021, baab012, 10.1093/database/baab012 · DOI
  39. Rukh, 2024, StackedEnC-AOP: prediction of antioxidant proteins using transform evolutionary and sequential features based multi-scale vector with stacked ensemble learning, BMC Bioinform, 25, 256, 10.1186/s12859-024-05884-6 · DOI
  40. Schmirler, 2024, Fine-tuning protein language models boosts predictions across diverse tasks, Nat Commun, 15, 7407, 10.1038/s41467-024-51844-2 · DOI · Paper page
  41. Schulz, 2012, Glycosylation, 21
  42. Simon, 2024, 2024 16th International Conference on COMmunication Systems & NETworkS (COMSNETS), 436, 10.1109/COMSNETS59351.2024.10427536 · DOI
  43. Slade, 2014, Chemical and biological methods to detect post-translational modifications of arginine, Biopolymers, 101, 133, 10.1002/bip.22256 · DOI
  44. Sun, 2019, N-GlycositeAtlas: a database resource for mass spectrometry-based human N-linked glycoprotein and glycosylation site mapping, Clin Proteomics, 16, 35, 10.1186/s12014-019-9254-0 · DOI
  45. Sun, 2024, GraphPBSP: protein binding site prediction based on graph attention network and pre-trained model ProstT5, Int J Biol Macromol, 282, 136933, 10.1016/j.ijbiomac.2024.136933 · DOI
  46. Susanty, 2024, Classifying alkaliphilic proteins using embeddings from protein language model, Comput Biol Med, 173, 108385, 10.1016/j.compbiomed.2024.108385 · DOI
  47. Taherzadeh, 2019, SPRINT-Gly: predicting N-and O-linked glycosylation sites of human and mouse proteins by using sequence and predicted structural properties, Bioinformatics, 35, 4140, 10.1093/bioinformatics/btz215 · DOI
  48. Thumuluri, 2022, DeepLoc 2.0: multi-label subcellular localization prediction using protein language models, Nucleic Acids Res, 50, W228, 10.1093/nar/gkac278 · DOI
  49. Tran, 2024, Sa-ttca: an SVM-based approach for tumor t-cell antigen classification using features extracted from biological sequencing and natural language processing, Comput Biol Med, 174, 108408, 10.1016/j.compbiomed.2024.108408 · DOI
  50. Uddin, 2024, A hybrid residue based sequential encoding mechanism with XGBoost improved ensemble model for identifying 5-hydroxymethylcytosine modifications, Sci Rep, 14, 20819, 10.1038/s41598-024-71568-z · DOI
  51. Vergara, 2014, A review of feature selection methods based on mutual information, Neural Comput Applic, 24, 175, 10.1007/s00521-013-1368-0 · DOI
  52. Wacker, 2006, Substrate specificity of bacterial oligosaccharyltransferase suggests a common transfer mechanism for the bacterial and eukaryotic systems, Proc Nat Acad Sci USA, 103, 7088, 10.1073/pnas.0509207103 · DOI
  53. Wang, 2025, CoNglyPred: accurate prediction of N-Linked glycosylation sites using ESM-2 and structural features with graph network and Co-Attention, Proteomics, 25, e202400210, 10.1002/pmic.202400210 · DOI
  54. Wu, 2024, 2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 258, 10.1109/BIBM62325.2024.10821845 · DOI
  55. Xia, 2020, Protein–ligand binding residue prediction enhancement through hybrid deep heterogeneous learning of sequence and structure data, Bioinformatics, 36, 3018, 10.1093/bioinformatics/btaa110 · DOI
  56. Yadav, 2024, PMTPred: machine-learning-based prediction of protein methyltransferases using the composition of k-spaced amino acid pairs, Mol Divers, 28, 2301, 10.1007/s11030-024-10937-2 · DOI
  57. Yeo, 2000, A new family of power transformations to improve normality or symmetry, Biometrika, 87, 954, 10.1093/biomet/87.4.954 · DOI
  58. Zielinska, 2010, Precision mapping of an in vivo N-glycoproteome reveals rigid topological and sequence constraints, Cell, 141, 897, 10.1016/j.cell.2010.04.012 · DOI

Metadata

Authors
Nafi, M. M. I., & Rahman, M. S.
Affiliations
Bangladesh University of Engineering and Technology (BD)
Corresponding author
Rahman, M Saifur
ORCID
Venue
Bioinformatics Advances
Publisher
Oxford University Press (OUP)
Published
2024-12-26
Volume
5
Issue
1
Pages
vbaf146-vbaf146
ISSN
2635-0041 (ISSN-L)
DOI
10.1093/bioadv/vbaf146
PMC
PMC12237515
OpenAlex
W4411750234
Cited by
1
References
2
Citations by year
2026: 1
FWCI
0.14
Type
journal article
Language
en
Open access
Licence
Locations
  • Bioinformatics Advances (publishedVersion, cc-by)
  • bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
Funders
Bangladesh University of Engineering and Technology
Topics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Machine Learning in Bioinformatics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Glycosylation and Glycoproteins Research
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › vaccines and immunoinformatics approaches
Keywords
N-glycosylation, glycosylation site prediction, protein language models, protein embeddings, stacking ensemble, post-translational modification, asparagine-linked glycosylation

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review