{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T10:34:14Z","timestamp":1776854054466,"version":"3.51.2"},"reference-count":34,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2025,1,29]],"date-time":"2025-01-29T00:00:00Z","timestamp":1738108800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100014726","name":"National Institute for Innovation in Manufacturing Biopharmaceuticals","doi-asserted-by":"publisher","award":["70NANB17H002"],"award-info":[{"award-number":["70NANB17H002"]}],"id":[{"id":"10.13039\/100014726","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,2,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>The accurate prediction of O-GlcNAcylation sites is crucial for understanding disease mechanisms and developing effective treatments. Previous machine learning (ML) models primarily relied on primary or secondary protein structural and related properties, which have limitations in capturing the spatial interactions of neighboring amino acids. This study introduces local environmental features as a novel approach that incorporates three-dimensional spatial information, significantly improving model performance by considering the spatial context around the target site. Additionally, we utilize sparse recurrent neural networks to effectively capture sequential nature of the proteins and to identify key factors influencing O-GlcNAcylation as an explainable ML model.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>Our findings demonstrate the effectiveness of our proposed features with the model achieving an F1 score of 28.3%, as well as feature selection capability with the model using only the top 20% of features achieving the highest F1 score of 32.02%, a 1.4-fold improvement over existing PTM models. Statistical analysis of the top 20 features confirmed their consistency with literature. This method not only boosts prediction accuracy but also paves the way for further research in understanding and targeting O-GlcNAcylation.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>The entire code, data, features used in this study are available in the GitHub repository: https:\/\/github.com\/pseokyoung\/o-glcnac-prediction<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaf034","type":"journal-article","created":{"date-parts":[[2025,1,29]],"date-time":"2025-01-29T16:04:13Z","timestamp":1738166653000},"source":"Crossref","is-referenced-by-count":2,"title":["Enhanced O-glycosylation site prediction using explainable machine learning technique with spatial local environment"],"prefix":"10.1093","volume":"41","author":[{"given":"Seokyoung","family":"Hong","sequence":"first","affiliation":[{"name":"Department of Chemical Engineering, Massachusetts Institute of Technology , Cambridge, MA 02139,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Krishna Gopal","family":"Chattaraj","sequence":"additional","affiliation":[{"name":"Department of Chemical Engineering, Massachusetts Institute of Technology , Cambridge, MA 02139,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Guo","sequence":"additional","affiliation":[{"name":"Department of Chemical Engineering, Massachusetts Institute of Technology , Cambridge, MA 02139,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bernhardt L","family":"Trout","sequence":"additional","affiliation":[{"name":"Department of Chemical Engineering, Massachusetts Institute of Technology , Cambridge, MA 02139,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4304-3484","authenticated-orcid":false,"given":"Richard D","family":"Braatz","sequence":"additional","affiliation":[{"name":"Department of Chemical Engineering, Massachusetts Institute of Technology , Cambridge, MA 02139,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2025,1,29]]},"reference":[{"key":"2025051303572331000_btaf034-B1","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1038\/s41586-024-07487-w","article-title":"Accurate structure prediction of biomolecular interactions with AlphaFold 3","volume":"630","author":"Abramson","year":"2024","journal-title":"Nature"},{"key":"2025051303572331000_btaf034-B2","doi-asserted-by":"crossref","first-page":"2045","DOI":"10.1109\/TCBB.2020.2968441","article-title":"Using Chou\u2019s 5-Steps rule to predict O-linked serine glycosylation sites by blending position relative features and statistical moment","volume":"18","author":"Akmal","year":"2021","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"key":"2025051303572331000_btaf034-B3","doi-asserted-by":"crossref","first-page":"469","DOI":"10.3390\/axioms11090469","article-title":"PTG-PLM: predicting post-translational glycosylation and glycation sites using protein language models and deep learning","volume":"11","author":"Alkuhlani","year":"2022","journal-title":"Axioms"},{"key":"2025051303572331000_btaf034-B4","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1093\/nar\/28.1.235","article-title":"The protein data bank","volume":"28","author":"Berman","year":"2000","journal-title":"Nucleic Acids Res"},{"key":"2025051303572331000_btaf034-B5","doi-asserted-by":"crossref","first-page":"438","DOI":"10.1186\/1471-2105-8-438","article-title":"Glycosylation site prediction using ensembles of support vector machine classifiers","volume":"8","author":"Caragea","year":"2007","journal-title":"BMC Bioinformatics"},{"key":"2025051303572331000_btaf034-B6","doi-asserted-by":"crossref","first-page":"142368","DOI":"10.1109\/ACCESS.2019.2944411","article-title":"DeepGly: a deep learning framework with recurrent and convolutional neural networks to identify protein glycation sites from imbalanced data","volume":"7","author":"Chen","year":"2019","journal-title":"IEEE Access"},{"key":"2025051303572331000_btaf034-B7","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1186\/s12864-019-6413-7","article-title":"The advantages of the matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation","volume":"21","author":"Chicco","year":"2020","journal-title":"BMC Genomics"},{"key":"2025051303572331000_btaf034-B8","doi-asserted-by":"crossref","first-page":"104629","DOI":"10.1016\/j.jbc.2023.104629","article-title":"Exploration of O-GlcNAc transferase glycosylation sites reveals a target sequence compositional bias","volume":"299","author":"Chong","year":"2023","journal-title":"J Biol Chem"},{"key":"2025051303572331000_btaf034-B9","doi-asserted-by":"crossref","first-page":"99","DOI":"10.3389\/fendo.2013.00099","article-title":"O-GlcNAcylation: a new cancer hallmark?","volume":"4","author":"Fardini","year":"2013","journal-title":"Front Endocrinol (Lausanne)"},{"key":"2025051303572331000_btaf034-B10","first-page":"310","article-title":"Prediction of glycosylation across the human proteome and the correlation to protein function","volume":"7","author":"Gupta","year":"2001","journal-title":"Pac Symp Biocomput"},{"key":"2025051303572331000_btaf034-B11","doi-asserted-by":"crossref","first-page":"1009","DOI":"10.1093\/glycob\/9.10.1009","article-title":"Scanning the available Dictyostelium discoideum proteome for O-linked GlcNAc glycosylation sites using neural networks","volume":"9","author":"Gupta","year":"1999","journal-title":"Glycobiology"},{"key":"2025051303572331000_btaf034-B12","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1023\/A:1006960004440","article-title":"NetOglyc: prediction of mucin type O-glycosylation sites based on sequence context and surface accessibility","volume":"15","author":"Hansen","year":"1998","journal-title":"Glycoconj J"},{"key":"2025051303572331000_btaf034-B13","doi-asserted-by":"crossref","first-page":"4806","DOI":"10.1109\/ACCESS.2019.2962617","article-title":"The Real-World-Weight Cross-Entropy loss function: modeling the costs of mislabeling","volume":"8","author":"Ho","year":"2020","journal-title":"IEEE Access"},{"key":"2025051303572331000_btaf034-B14","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1021\/acs.jproteome.3c00458","article-title":"O-GlcNAcPRED-DL: prediction of protein O-GlcNAcylation sites based on an ensemble model of deep learning","volume":"23","author":"Hu","year":"2024","journal-title":"J Proteome Res"},{"key":"2025051303572331000_btaf034-B15","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1038\/nmeth.4067","article-title":"CHARMM36m: an improved force field for folded and intrinsically disordered proteins","volume":"14","author":"Huang","year":"2017","journal-title":"Nat Methods"},{"key":"2025051303572331000_btaf034-B16","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1016\/0263-7855(96)00018-5","article-title":"VMD: visual molecular dynamics","volume":"14","author":"Humphrey","year":"1996","journal-title":"J Mol Graph"},{"key":"2025051303572331000_btaf034-B17","doi-asserted-by":"crossref","first-page":"2029","DOI":"10.1093\/bioinformatics\/bty039","article-title":"O-GlcNAcPRED-II: an integrated classification algorithm for identifying O-GlcNAcylation sites based on fuzzy undersampling and a K-means PCA oversampling technique","volume":"34","author":"Jia","year":"2018","journal-title":"Bioinformatics"},{"key":"2025051303572331000_btaf034-B18","doi-asserted-by":"crossref","first-page":"416","DOI":"10.1016\/j.bbapap.2013.12.002","article-title":"Validation of the reliability of computational O-GlcNAc prediction","volume":"1844","author":"Jochmann","year":"2014","journal-title":"Biochim Biophys Acta"},{"key":"2025051303572331000_btaf034-B19","doi-asserted-by":"crossref","first-page":"7830","DOI":"10.1021\/jp101759q","article-title":"Update of the CHARMM All-Atom additive force field for lipids: validation on six lipid types","volume":"114","author":"Klauda","year":"2010","journal-title":"J Phys Chem B"},{"key":"2025051303572331000_btaf034-B20","first-page":"50","author":"Lamy","year":"2019"},{"key":"2025051303572331000_btaf034-B21","doi-asserted-by":"crossref","first-page":"34595","DOI":"10.1038\/srep34595","article-title":"GlycoMine struct: a new bioinformatics tool for highly accurate mapping of the human N-linked and O-linked glycoproteomes by incorporating structural features","volume":"6","author":"Li","year":"2016","journal-title":"Sci Rep"},{"key":"2025051303572331000_btaf034-B22","first-page":"87","article-title":"O-GlcNAcylation prediction: an unattained objective","volume":"14","author":"Mauri","year":"2021","journal-title":"Adv Appl Bioinform Chem"},{"key":"2025051303572331000_btaf034-B23","doi-asserted-by":"crossref","first-page":"100031","DOI":"10.1074\/mcp.R120.002206","article-title":"Methods for enrichment and assignment of N-Acetylglucosamine modification sites","volume":"20","author":"Maynard","year":"2021","journal-title":"Mol Cell Proteomics"},{"key":"2025051303572331000_btaf034-B24","doi-asserted-by":"crossref","DOI":"10.1093\/bioinformatics\/btae643","article-title":"Prediction of human O-linked glycosylation sites using stacked generalization and embeddings from pre-trained protein language model","volume":"40","author":"Pakhrin","year":"2024","journal-title":"Bioinformatics"},{"key":"2025051303572331000_btaf034-B25","doi-asserted-by":"crossref","first-page":"648","DOI":"10.1093\/bioinformatics\/btab712","article-title":"BERT-Kcr: prediction of lysine crotonylation sites by a transfer learning method with pre-trained BERT models","volume":"38","author":"Qiao","year":"2022","journal-title":"Bioinformatics"},{"key":"2025051303572331000_btaf034-B26","doi-asserted-by":"crossref","first-page":"108206","DOI":"10.1016\/j.biotechadv.2023.108206","article-title":"Glycosylation shapes the efficacy and safety of diverse protein, gene and cell therapies","volume":"67","author":"Rocamora","year":"2023","journal-title":"Biotechnol Adv"},{"key":"2025051303572331000_btaf034-B27","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/j.neucom.2017.02.029","article-title":"Group sparse regularization for deep neural networks","volume":"241","author":"Scardapane","year":"2017","journal-title":"Neurocomputing"},{"key":"2025051303572331000_btaf034-B28","doi-asserted-by":"crossref","first-page":"108818","DOI":"10.1016\/j.compchemeng.2024.108818","article-title":"Recurrent neural network-based prediction of O-GlcNAcylation sites in mammalian proteins","volume":"189","author":"Seber","year":"2024","journal-title":"Comput Chem. Eng"},{"key":"2025051303572331000_btaf034-B29","doi-asserted-by":"crossref","first-page":"6699","DOI":"10.1038\/s41467-024-51071-9","article-title":"Post-translational modification prediction via prompt-based fine-tuning of a GPT-2 model","volume":"15","author":"Shrestha","year":"2024","journal-title":"Nat Commun"},{"key":"2025051303572331000_btaf034-B30","doi-asserted-by":"crossref","first-page":"4140","DOI":"10.1093\/bioinformatics\/btz215","article-title":"SPRINT-Gly: predicting N- and O-linked glycosylation sites of human and mouse proteins by using sequence and predicted structural properties","volume":"35","author":"Taherzadeh","year":"2019","journal-title":"Bioinformatics"},{"key":"2025051303572331000_btaf034-B31","doi-asserted-by":"crossref","first-page":"S1","DOI":"10.1186\/1471-2105-15-S16-S1","article-title":"Characterization and identification of protein O-GlcNAcylation sites with substrate specificity","volume":"15","author":"Wu","year":"2014","journal-title":"BMC Bioinformatics"},{"key":"2025051303572331000_btaf034-B32","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1038\/s41597-021-00810-4","article-title":"The human O-GlcNAcome database and meta-analysis","volume":"8","author":"Wulff-Fuentes","year":"2021","journal-title":"Sci Data"},{"key":"2025051303572331000_btaf034-B33","first-page":"112","article-title":"Monte carlo cross-validation for selecting a model and estimating the prediction error in multivariate calibration","volume":"18","author":"Xu","year":"2004","journal-title":"J. Chemom. J. Chemom. Soc"},{"key":"2025051303572331000_btaf034-B34","first-page":"022022","article-title":"An overview of overfitting and its solutions","volume":"1168","author":"Ying","year":"2019","journal-title":"J Phys: Conf Ser"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaf034\/61683442\/btaf034.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/2\/btaf034\/61683442\/btaf034.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/2\/btaf034\/61683442\/btaf034.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T07:57:32Z","timestamp":1747123052000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btaf034\/7989290"}},"subtitle":[],"editor":[{"given":"Jianlin","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2025,1,29]]},"references-count":34,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,2,4]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaf034","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,2]]},"published":{"date-parts":[[2025,1,29]]},"article-number":"btaf034"}}