CoNglyPred: Accurate Prediction of N‐Linked Glycosylation Sites Using ESM‐2 and Structural Features With Graph Network and Co‐Attention DOI

Hongmei Wang,

Long Zhao, Ziyuan Yu

et al.

PROTEOMICS, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 3, 2024

ABSTRACT N‐Linked glycosylation is crucial for various biological processes such as protein folding, immune response, and cellular transport. Traditional experimental methods determining N‐linked sites entail substantial time labor investment, which has led to the development of computational approaches a more efficient alternative. However, due limited availability 3D structural data, existing prediction often struggle fully utilize information fall short in integrating sequence effectively. Motivated by progress pretrained language models (pLMs) breakthrough structure prediction, we introduced high‐accuracy model called CoNglyPred. Having compared pLMs, opt large‐scale pLM ESM‐2 extract embeddings, thus mitigating certain limitations associated with manual feature extraction. Meanwhile, our approach employs graph transformer network process structures predicted AlphaFold2. The final output embedding are intricately integrated through co‐attention mechanism. Among series comprehensive experiments on independent test dataset, CoNglyPred outperforms state‐of‐the‐art demonstrates exceptional performance case study. In addition, first report uncertainty predictors using expected calibration error error.

Language: Английский

Decoding Sugars: Mass Spectrometric Advances in the Analysis of the Sugar Alphabet DOI Creative Commons

Jitske M. van Ede,

Dinko Šoić, Martin Pabst

et al.

Mass Spectrometry Reviews, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 19, 2025

ABSTRACT Monosaccharides play a central role in metabolic networks and the biosynthesis of glycomolecules, which perform essential functions across all domains life. Thus, identifying quantifying these building blocks is crucial both research industry. Routine methods have been established to facilitate analysis common monosaccharides. However, despite presence metabolites, most organisms utilize distinct sets monosaccharides derivatives. These molecules therefore display large diversity, potentially numbering hundreds or thousands, with many still unknown. This complexity presents significant challenges study particularly microbes, including pathogens those potential serve as novel model organisms. review discusses mass spectrometric techniques for isomer‐sensitive monosaccharides, their derivatives, activated forms. Although spectrometry allows untargeted sensitive detection complex matrices, stereoisomers extensive modifications necessitates integration advanced chromatographic, electrophoretic, ion mobility, spectroscopic methods. Furthermore, stable‐isotope incorporation studies are critical elucidating biosynthetic routes

Language: Английский

Citations

0
Advanced Mass Spectrometry Techniques for the Characterization of Carbohydrates DOI
Niklas Geue, Caitlin Walton‐Doyle,

Eleonora Renzi

et al.

Handbook of experimental pharmacology, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 1, 2025

Language: Английский

Citations

0
Integrating the analysis of human biopsies using post‐translational modifications proteomics DOI Creative Commons

Sonali Bhardwaj,

Mitchell Bulluss,

Ana D’Aubeterre

et al.

Protein Science, Journal Year: 2024, Volume and Issue: 33(4)

Published: March 27, 2024

Abstract Proteome diversities and their biological functions are significantly amplified by post‐translational modifications (PTMs) of proteins. Shotgun proteomics, which does not typically survey PTMs, provides an incomplete picture the complexity human biopsies in health disease. Recent advances mass spectrometry‐based proteomic techniques that enrich study PTMs helping to uncover molecular detail from cellular level system‐wide functions, including how microbiome impacts diseases. Protein heterogeneity disease challenging factors make it difficult characterize treat The search for clinical biomarkers mechanisms related patient diagnoses treatment has proven challenging. Knowledge is fundamentally lacking. Characterization complex samples clarify role diseases will result new discoveries. This review highlights key used unknown derived biopsies. Through integration diverse methods profile this explores genetic regulation proteoforms, cells origin expressing specific proteins, several bioactive subsequent analyses liquid chromatography tandem spectrometry.

Language: Английский

Citations

2
Optimization of glycopeptide enrichment techniques for the identification of clinical biomarkers DOI
Sherifdeen Onigbinde, Cristian D. Gutierrez Reyes,

Vishal Sandilya

et al.

Expert Review of Proteomics, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 22, 2024

The identification and characterization of glycopeptides through LC-MS/MS advanced enrichment techniques are crucial for advancing clinical glycoproteomics, significantly impacting the discovery disease biomarkers therapeutic targets. Despite progress in methods like Lectin Affinity Chromatography (LAC), Hydrophilic Interaction Liquid (HILIC), Electrostatic Repulsion (ERLIC), issues with specificity, efficiency, scalability remain, impeding thorough analysis complex glycosylation patterns understanding.

Language: Английский

Citations

1
CoNglyPred: Accurate Prediction of N‐Linked Glycosylation Sites Using ESM‐2 and Structural Features With Graph Network and Co‐Attention DOI

Hongmei Wang,

Long Zhao, Ziyuan Yu

et al.

PROTEOMICS, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 3, 2024

ABSTRACT N‐Linked glycosylation is crucial for various biological processes such as protein folding, immune response, and cellular transport. Traditional experimental methods determining N‐linked sites entail substantial time labor investment, which has led to the development of computational approaches a more efficient alternative. However, due limited availability 3D structural data, existing prediction often struggle fully utilize information fall short in integrating sequence effectively. Motivated by progress pretrained language models (pLMs) breakthrough structure prediction, we introduced high‐accuracy model called CoNglyPred. Having compared pLMs, opt large‐scale pLM ESM‐2 extract embeddings, thus mitigating certain limitations associated with manual feature extraction. Meanwhile, our approach employs graph transformer network process structures predicted AlphaFold2. The final output embedding are intricately integrated through co‐attention mechanism. Among series comprehensive experiments on independent test dataset, CoNglyPred outperforms state‐of‐the‐art demonstrates exceptional performance case study. In addition, first report uncertainty predictors using expected calibration error error.

Language: Английский

Citations

0