Glycosylation prediction tool




















We evaluated SPRINT-Gly against consensus-based model as well as previous methods by submitting protein sequence entries from our independent test set to publicly accessible web servers. Logarithmic plots to clearly illustrate the regions with low false positive rates are also shown for N -linked sites in Supplementary Figure S3.

Here, we developed a machine-learning approach to predict N- and O- linked glycosylation sites in human and mouse glycoproteins. To improve the accuracy of our models, we constructed a glycosylation-site repository by merging data from six data resources, and integrated protein sequence and structure-based features to train deep neural network and SVM models. We have shown that the N- glycosylation model performs equally well for intra or cross-species datasets, however, the O- glycosylation models performs poorly for cross-species tests, indicating the species difference in O -glycosylation mechanism.

The dataset collected in this work is the largest available for predicting N- and O- linked glycosylation sites by machine learning. Previously, GlycoPP Chauhan et al. EnsembleGly Caragea et al. For N- linked sites, both human and mouse proteins were predicted with high sensitivity and precision. These results suggest that our predictions of N- linked sites are approaching experimental accuracy. This performance can be explained by the training set size, the implementation of DNN, and an expanded list of protein sequence and structural features such as orientation-dependent contact numbers HSE.

More data are needed to improve training. SPRINT-Gly will continue to expand and develop in conjunction with data deposited in UniCarbKB, which will improve the quality of the training datasets thereby improving the accuracy of the models discussed. By integrating such data and leveraging advancements in machine-learning SPRINT-Gly provides a unique and powerful approach for the prediction of potential glycosylation sites, which will have an impact on understanding the biological importance of glycosylation.

We also acknowledge the authors of previous methods for providing the webservers. Abadi M. Google Scholar. Google Preview. Aebi M. Trends Biochem. Altschul S. Nucleic Acids Res. Apweiler R. Beltrao P. Ben-Dor S. Glycobiology , 14 , 95 — Blom N. Proteomics , 4 , Campbell M.

Caragea C. BMC Bioinformatics , 8 , Chang C. ACM Trans. Chauhan J. PLoS One , 7 , e PLoS One , 8 , e Crooks G.

Genome Res. Gupta R. Hamby S. BMC Bioinformatics , 9 , Hamelryck T. Proteins , 59 , 38 — Hansen J. Hanson J. Bioinformatics , 33 , — Heffernan R. Huang K. Joshi H. Cell , , — e Julenius K. Glycobiology , 15 , — Kaji H. Springer, Tokyo , pp. Khatri K. Kudo M. Pattern Recognit. Lederkremer G. Bioinformatics , 31 , — Liu W. Neurocomputing , , 11 — Meiler J. Moremen K. Cell Biol. Murray A. O'Connell J. Proteins , 86 , — Petrescu A. Glycobiology , 14 , — Qiu W.

Quang D. Ruiz-Blanco Y. Amino Acids , 49 , — Schindler P. Protein Sci. Schjoldager K. Acta , , — Steen PVd. Suga A. Glycobiology , 8 , — Taherzadeh G. Model , 56 , — Bioinformatics , 34 , — Chem , 39 , — Thaysen-Andersen M. Glycobiology , 22 , — Vacic V. Bioinformatics , 22 , — Vapnik V. Varki A. In Essentials of Glycobiology. Cold Spring Harbor Laboratory Press.

Wang S. N-linked glycosylation refers to the attachment of oligosaccharides to a nitrogen atom, usually the N4 of asparagine residues. N-glycosylation occurs on secreted or membrane bound proteins, mainly in eukaryotes and archaea - most bacteria do not carry out this modification. In eukaryotes, N-glycosylation begins as a co-translational event in the endoplasmic reticulum, where preassembled blocks of 14 sugars including 2 N-acetylglucosamines, 9 mannoses and 3 glucoses are first added to the nascent polypeptide chain.

After cleavage of 3 glucose and 1 mannose residues, the protein is transferred to the Golgi apparatus where the glycans lose a variable number of mannose residues and acquire a more complex structure during a process called 'terminal glycosylation'. If the type of N-linked glycan is known, it is indicated in the 'Description' field using the terms 'high mannose', 'hybrid' or 'complex'.

Examples: P , P Predicted sites are only annotated in regions of proteins that are known or predicted to be extracellular, and are tagged as 'Sequence Analysis' Sequence model. In general, we avoid propagating N-glycosylation sites 'By similarity' to related proteins. Example: Q94BT2. O-linked glycosylation of secreted and membrane bound proteins is a post-translational event that takes place in the cis-Golgi compartment after N-glycosylation and folding of the protein.

It refers to the attachment of glycans to serine and threonine, and, to a lesser extent, to hydroxyproline and hydroxylysine. O-linked glycans play important roles in protein localization and trafficking, protein solubility, antigenicity and cell-cell interactions. O-linked glycans are built up in a stepwise fashion with sugars added incrementally. The most common type of O-glycosylation in secreted and membrane-bound mammalian proteins seems to be the addition of reducing terminal N-acetylgalactosamine GalNAc.

This type of O-linked glycan is also referred to as 'mucin-type' glycan. The reducing terminal GalNAc residue can be further extended with galactose Gal , N-acetylglucosamine GlcNAc or GlcNAc and Gal resulting in 8 common core structures, which are often further decorated with the addition of up to three sialic acid residues.

Example: P In addition to the mucin-type O-linked glycans, a variety of mammalian proteins are known to have mannose Man , fucose Fuc , glucose Glc , Gal or xylose Xyl as reducing terminal linkages. Some cytoplasmic and nuclear proteins have simple O-linked glycans in which a single N-acetylglucosamine residue is linked to a serine or a threonine.

This modification has been identified in a number of eukaryotes including plants and filamentous fungi, although its presence in S. This type of O-linked glycosylation plays an important role in the modulation of the biological activity of intracellular proteins; in some proteins the same residue may be subject to competing phosphorylation and O-linked glycosylation.

Moharir, A. The role of N-glycosylation in folding, trafficking, and functionality of lysosomal protein CLN5. PLoS One 8, e, doi: Marino, K. A systematic approach to protein glycosylation analysis: a path through the maze. Nat Chem Biol 6, —, doi: Moremen, K. Vertebrate protein glycosylation: diversity, synthesis and function.

Nature reviews. Molecular cell biology 13, —, doi: Kiermaier, E. Polysialylation controls dendritic cell trafficking by regulating chemokine recognition. Science , —, doi: Pinho, S. Glycosylation in cancer: mechanisms and clinical implications. Cancer 15, —, doi: Park, D. Association of alcoholism with the N-glycosylation polymorphism of pseudodeficient human arylsulfatase A. Alcoholism, clinical and experimental research 20, — Schedin-Weiss, S.

The role of protein glycosylation in Alzheimer disease. The FEBS journal , 46—62, doi: Gavel, Y. Protein engineering 3, — Aebi, M. N-linked protein glycosylation in the ER. Biochimica et biophysica acta , —, doi: Van den Steen, P. Concepts and principles of O-linked glycosylation. Critical reviews in biochemistry and molecular biology 33, —, doi: Li, B. Glycosylation of the nuclear pore. Traffic 15, —, doi: Halim, A. Discovery of a nucleocytoplasmic O-mannose glycoproteome in yeast.

Hurtado-Guerrero, R. Recent structural and mechanistic insights into protein O-GalNAc glycosylation.

Biochemical Society transactions 44, 61—67, doi: Bard, F. Trends in cell biology 26, —, doi: Thanka Christlet, T. Database analysis of O-glycosylation sites in proteins. Biophysical journal 80, — Apweiler, R. Biochimica et biophysica acta , 4—8 Nilsson, I. Determination of the distance between the oligosaccharyltransferase active site and the endoplasmic reticulum membrane.

The Journal of biological chemistry , — CAS Google Scholar. Petrescu, A. Statistical analysis of the protein environment of N-glycosylation sites: implications for occupancy, structure, and folding. Glycobiology 14, —, doi: Morelle, W. Analysis of protein glycosylation by mass spectrometry. Nature protocols 2, —, doi: Zhang, S. Characterization of protein glycosylation using chip-based nanoelectrospray with precursor ion scanning quadrupole linear ion trap mass spectrometry.

Journal of biomolecular techniques: JBT 16, — Wollscheid, B. Mass-spectrometric identification and relative quantification of N-linked cell surface glycoproteins.

Nature biotechnology 27, —, doi: Shubhakar, A. Chromatographia 78, —, doi: Sun, S. Analytical chemistry 87, —, doi: Jayakumar, D. Detection of site-specific glycosylation in proteins using flow cytometry. Tian, Y. Solid-phase extraction of N-linked glycopeptides. Li, Y. Detection and verification of glycosylation patterns of glycoproteins from clinical specimens using lectin microarrays and lectin-based immunosorbent assays. Analytical chemistry 83, —, doi: Kuno, A. Evanescent-field fluorescence-assisted lectin microarray: a new strategy for glycan profiling.

Nature methods 2, —, doi: Walt, D. Li, F. GlycoMine: a machine learning-based approach for predicting N-, C- and O-linked glycosylation in the human proteome. Bioinformatics 31, —, doi: Gupta, R. Prediction of glycosylation across the human proteome and the correlation to protein function. Pacific Symposium on Biocomputing.

Pacific Symposium on Biocomputing — Steentoft, C. The EMBO journal 32, —, doi: Caragea, C. Glycosylation site prediction using ensembles of Support Vector Machine classifiers. Bmc Bioinformatics 8, , doi: Hamby, S. Prediction of glycosylation sites using random forests.

Bmc Bioinformatics 9, , doi: Chuang, G. Computational prediction of N-linked glycosylation incorporating structural properties and patterns. Bioinformatics 28, —, doi: Brank, J. Feature selection using linear support vector machines Liu, H.

Incremental feature selection. Appl Intell 9, —, doi: Article Google Scholar. Nature methods 10, —, doi: Biswas, A. Machine learning approach to predict protein phosphorylation sites by incorporating evolutionary information. BMC bioinformatics 11, , doi: Chen, Z. Towards more accurate prediction of ubiquitination sites: a comprehensive review of current methods, tools and features. Briefings in bioinformatics 16, —, doi: Lu, D. How hydrophobicity and the glycosylation site of glycans affect protein folding and stability: a molecular dynamics simulation.

The journal of physical chemistry. B , —, doi: Mazumder, R. Proteome-wide analysis of single-nucleotide variations in the N-glycosylation sequon of human genes. PloS One 7, e, doi: Avanov, A.

Molekuliarnaia biologiia 25, — Lam, P. Structure-based comparative analysis and prediction of N-linked glycosylation sites in evolutionarily distant eukaryotes. Wolfert, M. Adaptive immune activation: glycosylation does matter. Nat Chem Biol 9, —, doi: Jayaraman, A.

Glycosylation at Asn91 of H1N1 haemagglutinin affects binding to glycan receptors. The Biochemical journal , —, doi: Kokatla, H. Structure-based design of novel human Toll-like receptor 8 agonists. ChemMedChem 9, —, doi: Bie, H. Insights into mucopolysaccharidosis I from the structure and action of alpha-L-iduronidase. Nature chemical biology 9, — Maita, N.

Human alpha-L-iduronidase uses its own N-glycan as a substrate-binding and catalytic module. Tanji, H. Structural reorganization of the Toll-like receptor 8 dimer induced by agonistic ligands. Chen, R. Glycoproteomics analysis of human liver tissue by combination of multiple enzyme digestion and hydrazide chemistry.

Journal of proteome research 8, —, doi: Berman, H. The Protein Data Bank. Nucleic acids research 28, — Huang da, W. Nature protocols 4, 44—57, doi: Bioinformatics enrichment tools: paths toward the comprehensive functional analysis of large gene lists. Nucleic acids research 37, 1—13, doi: Gill, D. Regulation of O-glycosylation through Golgi-to-ER relocation of initiation enzymes.

The Journal of cell biology , —, doi: Comer, F. O-Glycosylation of nuclear and cytosolic proteins. The Journal of biological chemistry , —, doi: R Traven, A. Protein hijacking: key proteins held captive against their will. Cancer cell 5, — Drake, R. Altered glycosylation in prostate cancer. Advances in cancer research , —, doi: Costa, C.

PloS One 10, e, doi: Bassaganas, S. Pancreatic cancer cell glycosylation regulates cell adhesion and invasion through the modulation of alpha2beta1 integrin and E-cadherin function.

PLoS One 9, e, doi: Yamamoto-Hino, M. Dynamic regulation of innate immune responses in Drosophila by Senju-mediated glycosylation. Lichtenstein, R. Glycobiology of cell death: when glycans and lectins govern cell fate. Cell death and differentiation 20, —, doi: Hart, G. Cross talk between O-GlcNAcylation and phosphorylation: roles in signaling, transcription, and chronic disease.

Annual review of biochemistry 80, —, doi: Hogue, D.



0コメント

  • 1000 / 1000