{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T01:57:39Z","timestamp":1778637459501,"version":"3.51.4"},"reference-count":88,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2019,3,6]],"date-time":"2019-03-06T00:00:00Z","timestamp":1551830400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2019,3,6]],"date-time":"2019-03-06T00:00:00Z","timestamp":1551830400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["LP110200333"],"award-info":[{"award-number":["LP110200333"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP120104460"],"award-info":[{"award-number":["DP120104460"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Health and Medical Research Council of Australia","award":["4909809"],"award-info":[{"award-number":["4909809"]}]},{"name":"National Institute of Allergy and Infectious Diseases of the National Institutes of Health","award":["R01 AI111965"],"award-info":[{"award-number":["R01 AI111965"]}]},{"name":"Major Inter-Disciplinary Research (IDR) project"},{"name":"NHMRC Principal Research Fellowship","award":["1137739"],"award-info":[{"award-number":["1137739"]}]},{"name":"NHMRC CJ Martin Early Career Research Fellow","award":["1143366"],"award-info":[{"award-number":["1143366"]}]},{"name":"ARC Australian Laureate Fellow","award":["FL130100038"],"award-info":[{"award-number":["FL130100038"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1186\/s12859-019-2700-1","type":"journal-article","created":{"date-parts":[[2019,3,6]],"date-time":"2019-03-06T13:04:31Z","timestamp":1551877471000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":62,"title":["Positive-unlabelled learning of glycosylation sites in the human proteome"],"prefix":"10.1186","volume":"20","author":[{"given":"Fuyi","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anthony W.","family":"Purcell","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Geoffrey I.","family":"Webb","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kuo-Chen","family":"Chou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Trevor","family":"Lithgow","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8031-9086","authenticated-orcid":false,"given":"Jiangning","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,3,6]]},"reference":[{"issue":"7","key":"2700_CR1","doi-asserted-by":"crossref","first-page":"448","DOI":"10.1038\/nrm3383","volume":"13","author":"KW Moremen","year":"2012","unstructured":"Moremen KW, Tiemeyer M, Nairn AV. Vertebrate protein glycosylation: diversity, synthesis and function. Nat Rev Mol Cell Biol. 2012;13(7):448\u201362.","journal-title":"Nat Rev Mol Cell Biol"},{"key":"2700_CR2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/978-1-4939-6493-2_1","volume":"1503","author":"J Kristic","year":"2017","unstructured":"Kristic J, Lauc G. Ubiquitous importance of protein glycosylation. Methods Mol Biol. 2017;1503:1\u201312.","journal-title":"Methods Mol Biol"},{"issue":"16","key":"2700_CR3","doi-asserted-by":"crossref","first-page":"3183","DOI":"10.1016\/j.jmb.2016.02.030","volume":"428","author":"X Zhang","year":"2016","unstructured":"Zhang X, Wang Y. Glycosylation quality control by the Golgi structure. J Mol Biol. 2016;428(16):3183\u201393.","journal-title":"J Mol Biol"},{"issue":"5","key":"2700_CR4","doi-asserted-by":"crossref","first-page":"855","DOI":"10.1016\/j.cell.2006.08.019","volume":"126","author":"K Ohtsubo","year":"2006","unstructured":"Ohtsubo K, Marth JD. Glycosylation in cellular mechanisms of health and disease. Cell. 2006;126(5):855\u201367.","journal-title":"Cell"},{"key":"2700_CR5","first-page":"43","volume":"96","author":"RA Dwek","year":"1998","unstructured":"Dwek RA. Biological importance of glycosylation. Dev Biol Stand. 1998;96:43\u20137.","journal-title":"Dev Biol Stand"},{"key":"2700_CR6","doi-asserted-by":"crossref","first-page":"431","DOI":"10.1016\/bs.mie.2016.11.006","volume":"585","author":"L Veillon","year":"2017","unstructured":"Veillon L, Zhou S, Mechref Y. Quantitative Glycomics: a combined analytical and bioinformatics approach. Methods Enzymol. 2017;585:431\u201377.","journal-title":"Methods Enzymol"},{"issue":"6","key":"2700_CR7","first-page":"514","volume":"8","author":"KF Aoki-Kinoshita","year":"2006","unstructured":"Aoki-Kinoshita KF, Kanehisa M. Bioinformatics approaches in glycomics and drug discovery. Curr Opin Mol Ther. 2006;8(6):514\u201320.","journal-title":"Curr Opin Mol Ther"},{"issue":"2","key":"2700_CR8","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1093\/bib\/5.2.164","volume":"5","author":"CW von der Lieth","year":"2004","unstructured":"von der Lieth CW, Bohne-Lang A, Lohmann KK, Frank M. Bioinformatics for glycomics: status, methods, requirements and perspectives. Brief Bioinform. 2004;5(2):164\u201378.","journal-title":"Brief Bioinform"},{"issue":"9","key":"2700_CR9","doi-asserted-by":"crossref","first-page":"540","DOI":"10.1038\/nrc3982","volume":"15","author":"SS Pinho","year":"2015","unstructured":"Pinho SS, Reis CA. Glycosylation in cancer: mechanisms and clinical implications. Nat Rev Cancer. 2015;15(9):540\u201355.","journal-title":"Nat Rev Cancer"},{"issue":"12","key":"2700_CR10","doi-asserted-by":"crossref","first-page":"742","DOI":"10.1038\/nrm4073","volume":"16","author":"C Xu","year":"2015","unstructured":"Xu C, Ng DT. Glycosylation-directed quality control of protein folding. Nat Rev Mol Cell Biol. 2015;16(12):742\u201352.","journal-title":"Nat Rev Mol Cell Biol"},{"key":"2700_CR11","doi-asserted-by":"crossref","unstructured":"Bao W, Yuan C-A, Zhang Y, Han K, Nandi AK, Honig B, Ds H. Mutli-features Predction of protein translational modification sites. IEEE\/ACM transactions on computational biology and bioinformatics. 2017.","DOI":"10.1109\/TCBB.2017.2752703"},{"key":"2700_CR12","doi-asserted-by":"crossref","unstructured":"Li F, Fan C, Marquez-Lago TT, Leier A, Revote J, Jia C, Zhu Y, Smith AI, Webb GI, et al. PRISM: a comprehensive 3D structure database for post-translational modifications and mutations with functional impact. bioRxiv. 2019:523308.","DOI":"10.1101\/523308"},{"issue":"3","key":"2700_CR13","doi-asserted-by":"crossref","first-page":"410","DOI":"10.4103\/ijem.IJEM_2_17","volume":"21","author":"K Neelofar","year":"2017","unstructured":"Neelofar K, Ahmad J. Glycosylation gap in patients with diabetes with chronic kidney disease and healthy participants: a comparative study. Indian J Endocrinol Metab. 2017;21(3):410\u20134.","journal-title":"Indian J Endocrinol Metab"},{"key":"2700_CR14","doi-asserted-by":"crossref","unstructured":"Sadurni A, Kehr G, Ahlqvist M, Peilot Sjogren H, Kankkonen C, Knerr L, Gilmour R. Fluorine-directed glycosylation enables the Stereocontrolled synthesis of selective SGLT2 inhibitors for type II diabetes. Chemistry. 2017.","DOI":"10.1002\/chem.201705373"},{"issue":"1","key":"2700_CR15","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1042\/bj2450243","volume":"245","author":"SP Wolff","year":"1987","unstructured":"Wolff SP, Dean RT. Glucose autoxidation and protein modification. The potential role of 'autoxidative glycosylation' in diabetes. Biochem J. 1987;245(1):243\u201350.","journal-title":"Biochem J"},{"issue":"4","key":"2700_CR16","doi-asserted-by":"crossref","first-page":"1436","DOI":"10.1021\/acs.jproteome.6b00775","volume":"16","author":"A Drabik","year":"2017","unstructured":"Drabik A, Bodzon-Kulakowska A, Suder P, Silberring J, Kulig J, Sierzega M. Glycosylation changes in serum proteins identify patients with pancreatic Cancer. J Proteome Res. 2017;16(4):1436\u201344.","journal-title":"J Proteome Res"},{"key":"2700_CR17","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1016\/j.canlet.2016.01.044","volume":"387","author":"JA Ferreira","year":"2017","unstructured":"Ferreira JA, Magalhaes A, Gomes J, Peixoto A, Gaiteiro C, Fernandes E, Santos LL, Reis CA. Protein glycosylation in gastric and colorectal cancers: toward cancer detection and targeted therapeutics. Cancer Lett. 2017;387:32\u201345.","journal-title":"Cancer Lett"},{"issue":"6","key":"2700_CR18","doi-asserted-by":"crossref","first-page":"733","DOI":"10.1016\/j.ccell.2017.05.012","volume":"31","author":"A Magalhaes","year":"2017","unstructured":"Magalhaes A, Duarte HO, Reis CA. Aberrant glycosylation in Cancer: a novel molecular mechanism controlling metastasis. Cancer Cell. 2017;31(6):733\u20135.","journal-title":"Cancer Cell"},{"key":"2700_CR19","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1016\/j.semcancer.2017.03.002","volume":"44","author":"L Oliveira-Ferrer","year":"2017","unstructured":"Oliveira-Ferrer L, Legler K, Milde-Langosch K. Role of protein glycosylation in cancer metastasis. Semin Cancer Biol. 2017;44:141\u201352.","journal-title":"Semin Cancer Biol"},{"issue":"5","key":"2700_CR20","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1046\/j.1525-1500.1998.00054.x","volume":"22","author":"JD Roberts","year":"1998","unstructured":"Roberts JD, Klein JL, Palmantier R, Dhume ST, George MD, Olden K. The role of protein glycosylation inhibitors in the prevention of metastasis and therapy of cancer. Cancer Detect Prev. 1998;22(5):455\u201362.","journal-title":"Cancer Detect Prev"},{"issue":"10","key":"2700_CR21","doi-asserted-by":"crossref","first-page":"1478","DOI":"10.1038\/emboj.2013.79","volume":"32","author":"C Steentoft","year":"2013","unstructured":"Steentoft C, Vakhrushev SY, Joshi HJ, Kong Y, Vester-Christensen MB, Schjoldager KT, Lavrsen K, Dabelsteen S, Pedersen NB, Marcos-Silva L, et al. Precision mapping of the human O-GalNAc glycoproteome through SimpleCell technology. EMBO J. 2013;32(10):1478\u201388.","journal-title":"EMBO J"},{"key":"2700_CR22","doi-asserted-by":"crossref","unstructured":"Vergroesen RD, Slot LM, Hafkenscheid L, Koning MT, Scherer HU, Toes REM. Response to: 'Acquiring new N-glycosylation sites in variable regions of immunoglobulin genes by somatic hypermutation is a common feature of autoimmune diseases' by Visser et al. Ann Rheum Dis. 2017.","DOI":"10.1136\/annrheumdis-2017-212583"},{"key":"2700_CR23","doi-asserted-by":"crossref","unstructured":"Visser A, Hamza N, Kroese FGM, Bos NA: Acquiring new N-glycosylation sites in variable regions of immunoglobulin genes by somatic hypermutation is a common feature of autoimmune diseases. Ann Rheum Dis 2017.","DOI":"10.1136\/annrheumdis-2017-212568"},{"key":"2700_CR24","unstructured":"Gupta R, Brunak S. Prediction of glycosylation across the human proteome and the correlation to protein function. Pac Symp Biocomput. 2002:310\u201322."},{"key":"2700_CR25","doi-asserted-by":"crossref","first-page":"438","DOI":"10.1186\/1471-2105-8-438","volume":"8","author":"C Caragea","year":"2007","unstructured":"Caragea C, Sinapov J, Silvescu A, Dobbs D, Honavar V. Glycosylation site prediction using ensembles of support vector machine classifiers. BMC Bioinformatics. 2007;8:438.","journal-title":"BMC Bioinformatics"},{"key":"2700_CR26","doi-asserted-by":"crossref","first-page":"500","DOI":"10.1186\/1471-2105-9-500","volume":"9","author":"SE Hamby","year":"2008","unstructured":"Hamby SE, Hirst JD. Prediction of glycosylation sites using random forests. BMC Bioinformatics. 2008;9:500.","journal-title":"BMC Bioinformatics"},{"issue":"6","key":"2700_CR27","doi-asserted-by":"crossref","first-page":"e67008","DOI":"10.1371\/journal.pone.0067008","volume":"8","author":"JS Chauhan","year":"2013","unstructured":"Chauhan JS, Rao A, Raghava GP. In silico platform for prediction of N-, O- and C-glycosites in eukaryotic protein sequences. PLoS One. 2013;8(6):e67008.","journal-title":"PLoS One"},{"issue":"8","key":"2700_CR28","doi-asserted-by":"crossref","first-page":"1077","DOI":"10.1002\/pro.2494","volume":"23","author":"V Pejaver","year":"2014","unstructured":"Pejaver V, Hsu WL, Xin FX, Dunker AK, Uversky VN, Radivojac P. The structural and functional signatures of proteins that undergo multiple events of post-translational modification. Protein Sci. 2014;23(8):1077\u201393.","journal-title":"Protein Sci"},{"issue":"9","key":"2700_CR29","doi-asserted-by":"crossref","first-page":"1411","DOI":"10.1093\/bioinformatics\/btu852","volume":"31","author":"F Li","year":"2015","unstructured":"Li F, Li C, Wang M, Webb GI, Zhang Y, Whisstock JC, Song J. GlycoMine: a machine learning-based approach for predicting N-, C- and O-linked glycosylation in the human proteome. Bioinformatics. 2015;31(9):1411\u20139.","journal-title":"Bioinformatics"},{"key":"2700_CR30","doi-asserted-by":"crossref","first-page":"34595","DOI":"10.1038\/srep34595","volume":"6","author":"F Li","year":"2016","unstructured":"Li F, Li C, Revote J, Zhang Y, Webb GI, Li J, Song J, Lithgow T. GlycoMine(struct): a new bioinformatics tool for highly accurate mapping of the human N-linked and O-linked glycoproteomes by incorporating structural features. Sci Rep. 2016;6:34595.","journal-title":"Sci Rep"},{"key":"2700_CR31","doi-asserted-by":"crossref","unstructured":"De Comit\u00e9 F, Denis F, Gilleron R, Letouzey F: Positive and unlabeled examples help learning. In: Algorithmic Learning Theory: 1999. Springer: 219\u2013230.","DOI":"10.1007\/3-540-46769-6_18"},{"key":"2700_CR32","unstructured":"Niu G, du Plessis MC, Sakai T, Ma Y, Sugiyama M: Theoretical comparisons of positive-unlabeled learning against positive-negative learning. In: Advances in neural information processing systems: 2016. 1199\u20131207."},{"key":"2700_CR33","unstructured":"Menon A, Rooyen BV, Ong CS, Williamson B: Learning from Corrupted Binary Labels via Class-Probability Estimation. In: Proceedings of the 32nd International Conference on Machine Learning; Proceedings of Machine Learning Research: Edited by Francis B, David B. PMLR 2015: 125--134."},{"key":"2700_CR34","doi-asserted-by":"crossref","unstructured":"Jain S, White M, Radivojac P: Recovering true classifier performance in positive-unlabeled learning. In: AAAI: 2017. 2066\u20132072.","DOI":"10.1609\/aaai.v31i1.10937"},{"key":"2700_CR35","doi-asserted-by":"crossref","unstructured":"Pejaver V, Urresti J, Lugo-Martinez J, Pagel KA, Lin GN, Nam H-J, Mort M, Cooper DN, Sebat J, Iakoucheva LM, et al. MutPred2: inferring the molecular and phenotypic impact of amino acid variants. bioRxiv:2017.","DOI":"10.1101\/134981"},{"key":"2700_CR36","doi-asserted-by":"crossref","unstructured":"Elkan C, Noto K: Learning classifiers from only positive and unlabeled data. In: Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining: 2008. ACM: 213\u2013220.","DOI":"10.1145\/1401890.1401920"},{"key":"2700_CR37","doi-asserted-by":"crossref","unstructured":"Chang S, Zhang Y, Tang J, Yin D, Chang Y, Hasegawa-Johnson MA, Huang TS: Positive-unlabeled learning in streaming networks. In: Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining: 2016. ACM: 755\u2013764.","DOI":"10.1145\/2939672.2939744"},{"issue":"7","key":"2700_CR38","doi-asserted-by":"crossref","first-page":"1111","DOI":"10.1093\/bioinformatics\/btu772","volume":"31","author":"YY Xu","year":"2015","unstructured":"Xu YY, Yang F, Zhang Y, Shen HB. Bioimaging-based detection of mislocalized proteins in human cancers by semi-supervised learning. Bioinformatics. 2015;31(7):1111\u20139.","journal-title":"Bioinformatics"},{"issue":"D1","key":"2700_CR39","doi-asserted-by":"crossref","first-page":"D158","DOI":"10.1093\/nar\/gkw1099","volume":"45","author":"The UniProt C","year":"2017","unstructured":"The UniProt C. UniProt: the universal protein knowledgebase. Nucleic Acids Res. 2017;45(D1):D158\u201369.","journal-title":"Nucleic Acids Res"},{"issue":"8","key":"2700_CR40","doi-asserted-by":"crossref","first-page":"1226","DOI":"10.1109\/TPAMI.2005.159","volume":"27","author":"HC Peng","year":"2005","unstructured":"Peng HC, Long FH, Ding C. Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy. Ieee T Pattern Anal. 2005;27(8):1226\u201338.","journal-title":"Ieee T Pattern Anal"},{"key":"2700_CR41","doi-asserted-by":"crossref","unstructured":"Li F, Li C, Marquez-Lago TT, Leier A, Akutsu T, Purcell AW, Smith AI, Lithgow T, Daly RJ, Song J, et al. Quokka: a comprehensive tool for rapid and accurate prediction of kinase family-specific phosphorylation sites in the human proteome. Bioinformatics. 2018.","DOI":"10.1093\/bioinformatics\/bty522"},{"key":"2700_CR42","doi-asserted-by":"crossref","unstructured":"Chen Z, Liu X, Li F, Li C, Marquez-Lago T, Leier A, Akutsu T, Webb GI, Xu D, Smith AI, et al. Large-scale comparative assessment of computational predictors for lysine post-translational modification sites. Brief Bioinform. 2018.","DOI":"10.1093\/bib\/bby089"},{"issue":"4","key":"2700_CR43","doi-asserted-by":"crossref","first-page":"684","DOI":"10.1093\/bioinformatics\/btx670","volume":"34","author":"J Song","year":"2018","unstructured":"Song J, Li F, Leier A, Marquez-Lago TT, Akutsu T, Haffari G, Chou KC, Webb GI, Pike RN, Hancock J. PROSPERous: high-throughput prediction of substrate cleavage sites for 90 proteases with improved accuracy. Bioinformatics. 2018;34(4):684\u20137.","journal-title":"Bioinformatics"},{"key":"2700_CR44","doi-asserted-by":"crossref","unstructured":"Song J, Wang Y, Li F, Akutsu T, Rawlings ND, Webb GI, Chou K-C: iProt-Sub: a comprehensive package for accurately mapping and predicting protease-specific substrates and cleavage sites. Briefings in Bioinformatics 2018:bby028-bby028.","DOI":"10.1093\/bib\/bby028"},{"key":"2700_CR45","doi-asserted-by":"crossref","unstructured":"Li F, Wang Y, Li C, Marquez-Lago TT, Leier A, Rawlings ND, Haffari G, Revote J, Akutsu T, Chou K-C et al: Twenty years of bioinformatics research for protease-specific substrate and cleavage site prediction: a comprehensive revisit and benchmarking of existing methods. Briefings in Bioinformatics 2018:bby077-bby077.","DOI":"10.1093\/bib\/bby077"},{"issue":"1","key":"2700_CR46","doi-asserted-by":"crossref","first-page":"24","DOI":"10.3390\/ijms17010024","volume":"17","author":"M Fanchi","year":"2015","unstructured":"Fanchi M, Insung N, Lukasz K, Uversky VN. Compartmentalization and functionality of nuclear disorder: intrinsic disorder and protein-protein interactions in intra-nuclear compartments. Int J Mol Sci. 2015;17(1):24.","journal-title":"Int J Mol Sci"},{"issue":"D1","key":"2700_CR47","doi-asserted-by":"crossref","first-page":"D435","DOI":"10.1093\/nar\/gkv1240","volume":"44","author":"KY Huang","year":"2016","unstructured":"Huang KY, Su MG, Kao HJ, Hsieh YC, Jhong JH, Cheng KH, Huang HD, Lee TY. dbPTM 2016: 10-year anniversary of a resource for post-translational modification of proteins. Nucleic Acids Res. 2016;44(D1):D435\u201346.","journal-title":"Nucleic Acids Res"},{"issue":"Database issue","key":"2700_CR48","doi-asserted-by":"crossref","first-page":"D512","DOI":"10.1093\/nar\/gku1267","volume":"43","author":"PV Hornbeck","year":"2015","unstructured":"Hornbeck PV, Zhang B, Murray B, Kornhauser JM, Latham V, Skrzypek E. PhosphoSitePlus, 2014: mutations, PTMs and recalibrations. Nucleic Acids Res. 2015;43(Database issue):D512\u201320.","journal-title":"Nucleic Acids Res"},{"issue":"23","key":"2700_CR49","doi-asserted-by":"crossref","first-page":"3150","DOI":"10.1093\/bioinformatics\/bts565","volume":"28","author":"L Fu","year":"2012","unstructured":"Fu L, Niu B, Zhu Z, Wu S, Li W. CD-HIT: accelerated for clustering the next-generation sequencing data. Bioinformatics. 2012;28(23):3150\u20132.","journal-title":"Bioinformatics"},{"issue":"22","key":"2700_CR50","doi-asserted-by":"crossref","first-page":"3524","DOI":"10.1093\/bioinformatics\/btx476","volume":"33","author":"X Cheng","year":"2017","unstructured":"Cheng X, Zhao S-G, Lin W-Z, Xiao X, Chou K-C. pLoc-mAnimal: predict subcellular localization of animal proteins with both single and multiple sites. Bioinformatics. 2017;33(22):3524\u201331.","journal-title":"Bioinformatics"},{"issue":"1","key":"2700_CR51","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1093\/oxfordjournals.jbchem.a135454","volume":"99","author":"H Nakashima","year":"1986","unstructured":"Nakashima H, Nishikawa K, Ooi T. The folding type of a protein is relevant to the amino acid composition. J Biochem. 1986;99(1):153\u201362.","journal-title":"J Biochem"},{"issue":"3","key":"2700_CR52","doi-asserted-by":"crossref","first-page":"246","DOI":"10.1002\/prot.1035","volume":"43","author":"KC Chou","year":"2001","unstructured":"Chou KC. Prediction of protein cellular attributes using pseudo-amino acid composition. Proteins: Structure, Function, and Bioinformatics. 2001;43(3):246\u201355.","journal-title":"Proteins: Structure, Function, and Bioinformatics"},{"issue":"4","key":"2700_CR53","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1023\/A:1007091128394","volume":"19","author":"Z-P Feng","year":"2000","unstructured":"Feng Z-P, Zhang C-T. Prediction of membrane protein types based on the hydrophobic index of amino acids. J Protein Chem. 2000;19(4):269\u201375.","journal-title":"J Protein Chem"},{"key":"2700_CR54","doi-asserted-by":"crossref","unstructured":"Chen Z, Zhao P, Li F, Leier A, Marquez-Lago TT, Wang Y, Webb GI, Smith AI, Daly RJ, Chou KC, et al. iFeature: a python package and web server for features extraction and selection from protein and peptide sequences. Bioinformatics. 2018.","DOI":"10.1093\/bioinformatics\/bty140"},{"issue":"3","key":"2700_CR55","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1002\/bip.360270308","volume":"27","author":"DS Horne","year":"1988","unstructured":"Horne DS. Prediction of protein helix content from an autocorrelation analysis of sequence hydrophobicities. Biopolymers. 1988;27(3):451\u201377.","journal-title":"Biopolymers"},{"issue":"1","key":"2700_CR56","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1002\/ajpa.20250","volume":"129","author":"RR Sokal","year":"2006","unstructured":"Sokal RR, Thomson BA. Population structure inferred by local spatial autocorrelation: an example from an Amerindian tribal population. Am J Phys Anthropol. 2006;129(1):121\u201331.","journal-title":"Am J Phys Anthropol"},{"issue":"4","key":"2700_CR57","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1002\/(SICI)1097-0134(19990601)35:4<401::AID-PROT3>3.0.CO;2-K","volume":"35","author":"I Dubchak","year":"1999","unstructured":"Dubchak I, Muchnik I, Mayor C, Dralyuk I, Kim SH. Recognition of a protein fold in the context of the SCOP classification. Proteins: Structure, Function, and Bioinformatics. 1999;35(4):401\u20137.","journal-title":"Proteins: Structure, Function, and Bioinformatics"},{"issue":"2","key":"2700_CR58","doi-asserted-by":"crossref","first-page":"477","DOI":"10.1006\/bbrc.2000.3815","volume":"278","author":"K-C Chou","year":"2000","unstructured":"Chou K-C. Prediction of protein subcellular locations by incorporating quasi-sequence-order effect. Biochem Biophys Res Commun. 2000;278(2):477\u201383.","journal-title":"Biochem Biophys Res Commun"},{"issue":"Database issue","key":"2700_CR59","first-page":"D202","volume":"36","author":"S Kawashima","year":"2008","unstructured":"Kawashima S, Pokarowski P, Pokarowska M, Kolinski A, Katayama T, Kanehisa M. AAindex: amino acid index database, progress report 2008. Nucleic Acids Res. 2008;36(Database issue):D202\u20135.","journal-title":"Nucleic Acids Res"},{"key":"2700_CR60","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1016\/j.compbiolchem.2016.07.004","volume":"64","author":"GH Jowkar","year":"2016","unstructured":"Jowkar GH, Mansoori EG. Perceptron ensemble of graph-based positive-unlabeled learning for disease gene identification. Comput Biol Chem. 2016;64:263\u201370.","journal-title":"Comput Biol Chem"},{"issue":"5","key":"2700_CR61","doi-asserted-by":"crossref","first-page":"e97079","DOI":"10.1371\/journal.pone.0097079","volume":"9","author":"P Yang","year":"2014","unstructured":"Yang P, Li X, Chua HN, Kwoh CK, Ng SK. Ensemble positive unlabeled learning for disease gene identification. PLoS One. 2014;9(5):e97079.","journal-title":"PLoS One"},{"issue":"20","key":"2700_CR62","doi-asserted-by":"crossref","first-page":"2640","DOI":"10.1093\/bioinformatics\/bts504","volume":"28","author":"P Yang","year":"2012","unstructured":"Yang P, Li XL, Mei JP, Kwoh CK, Ng SK. Positive-unlabeled learning for disease gene identification. Bioinformatics. 2012;28(20):2640\u20137.","journal-title":"Bioinformatics"},{"key":"2700_CR63","first-page":"4525786","volume":"2016","author":"M Jiang","year":"2016","unstructured":"Jiang M, Cao JZ. Positive-unlabeled learning for Pupylation sites prediction. Biomed Res Int. 2016;2016:4525786.","journal-title":"Biomed Res Int"},{"key":"2700_CR64","doi-asserted-by":"crossref","unstructured":"Nan X, Bao L, Zhao X, Zhao X, Sangaiah AK, Wang GG, Ma Z. EPuL: An Enhanced Positive-Unlabeled Learning Algorithm for the Prediction of Pupylation Sites. Molecules. 2017;(9):22.","DOI":"10.3390\/molecules22091463"},{"issue":"2","key":"2700_CR65","doi-asserted-by":"crossref","first-page":"252","DOI":"10.1093\/bioinformatics\/btv550","volume":"32","author":"P Yang","year":"2016","unstructured":"Yang P, Humphrey SJ, James DE, Yang YH, Jothi R. Positive-unlabeled ensemble learning for kinase substrate prediction from dynamic phosphoproteomics data. Bioinformatics. 2016;32(2):252\u20139.","journal-title":"Bioinformatics"},{"issue":"14","key":"2700_CR66","doi-asserted-by":"crossref","first-page":"2184","DOI":"10.1093\/bioinformatics\/btw219","volume":"32","author":"Y-Y Xu","year":"2016","unstructured":"Xu Y-Y, Yang F, Shen H-B. Incorporating organelle correlations into semi-supervised learning for protein subcellular localization prediction. Bioinformatics. 2016;32(14):2184\u201392.","journal-title":"Bioinformatics"},{"issue":"1","key":"2700_CR67","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1186\/s12859-017-1546-7","volume":"18","author":"PN Hameed","year":"2017","unstructured":"Hameed PN, Verspoor K, Kusljic S, Halgamuge S. Positive-unlabeled learning for inferring drug interactions based on heterogeneous attributes. BMC Bioinformatics. 2017;18(1):140.","journal-title":"BMC Bioinformatics"},{"key":"2700_CR68","unstructured":"Quinlan JR: C4. 5: programs for machine learning: Elsevier; 2014."},{"key":"2700_CR69","unstructured":"Langley P, Iba W, Thompson K: An analysis of Bayesian classifiers. In: Aaai: 1992. 223\u2013228."},{"issue":"1","key":"2700_CR70","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1016\/j.tcs.2005.09.007","volume":"348","author":"F Denis","year":"2005","unstructured":"Denis F, Gilleron R, Letouzey F. Learning from positive and unlabeled examples. Theor Comput Sci. 2005;348(1):70\u201383.","journal-title":"Theor Comput Sci"},{"key":"2700_CR71","doi-asserted-by":"crossref","unstructured":"He J, Zhang Y, Li X, Wang Y: Bayesian classifiers for positive unlabeled learning. In: International Conference on Web-Age Information Management: 2011. Springer: 81\u201393.","DOI":"10.1007\/978-3-642-23535-1_9"},{"key":"2700_CR72","unstructured":"Li F, Song J, Li C, Akutsu T, Zhang Y: PAnDE: Averaged n-Dependence Estimators for Positive Unlabeled Learning. ICIC Express Letters Part B: Applications, 8(9):11."},{"issue":"2","key":"2700_CR73","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1007\/s10994-011-5263-6","volume":"86","author":"GI Webb","year":"2012","unstructured":"Webb GI, Boughton JR, Zheng F, Ting KM, Salem H. Learning by extrapolation from marginal to full-multivariate probability distributions: decreasingly naive Bayesian classification. Mach Learn. 2012;86(2):233\u201372.","journal-title":"Mach Learn"},{"key":"2700_CR74","unstructured":"Jain S, White M, Trosset MW, Radivojac P: Nonparametric semi-supervised learning of class proportions. arXiv preprint arXiv:160101944 2016."},{"key":"2700_CR75","unstructured":"Jain S, White M, Radivojac P: Estimating the class prior and posterior from noisy positives and unlabeled data. In: Advances in Neural Information Processing Systems: 2016. 2693\u20132701."},{"key":"2700_CR76","unstructured":"Denis F, Laurent A, Gilleron R, Tommasi M: Text classification and co-training from positive and unlabeled examples. In: Proceedings of the ICML 2003 workshop: the continuum from labeled to unlabeled data: 2003. 80\u201387."},{"key":"2700_CR77","doi-asserted-by":"crossref","unstructured":"Webb GI, Pazzani MJ: Adjusted probability naive Bayesian induction. In: Australian Joint Conference on Artificial Intelligence: 1998. Springer: 285\u2013295.","DOI":"10.1007\/BFb0095060"},{"issue":"2\u20133","key":"2700_CR78","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1023\/A:1007465528199","volume":"29","author":"N Friedman","year":"1997","unstructured":"Friedman N, Geiger D, Goldszmidt M. Bayesian network classifiers. Mach Learn. 1997;29(2\u20133):131\u201363.","journal-title":"Mach Learn"},{"key":"2700_CR79","doi-asserted-by":"crossref","unstructured":"Su J, Zhang H: Full Bayesian network classifiers. In: Proceedings of the 23rd international conference on Machine learning: 2006. ACM: 897\u2013904.","DOI":"10.1145\/1143844.1143957"},{"issue":"11","key":"2700_CR80","doi-asserted-by":"crossref","first-page":"735","DOI":"10.1093\/protein\/gzt042","volume":"26","author":"HL Xie","year":"2013","unstructured":"Xie HL, Fu L, Nie XD. Using ensemble SVM to identify human GPCRs N-linked glycosylation sites based on the general form of Chou's PseAAC. Protein Eng Des Sel. 2013;26(11):735\u201342.","journal-title":"Protein Eng Des Sel"},{"key":"2700_CR81","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1016\/j.jtbi.2018.01.023","volume":"443","author":"J Song","year":"2018","unstructured":"Song J, Li F, Takemoto K, Haffari G, Akutsu T, Chou KC, Webb GI. PREvaIL, an integrative approach for inferring catalytic residues using sequence, structural, and network features in a machine-learning framework. J Theor Biol. 2018;443:125\u201337.","journal-title":"J Theor Biol"},{"key":"2700_CR82","doi-asserted-by":"crossref","unstructured":"Wei L, Hu J, Li F, Song J, Su R, Zou Q. Comparative analysis and prediction of quorum-sensing peptides using feature representation learning and machine learning algorithms. Brief Bioinform. 2018.","DOI":"10.1093\/bib\/bby107"},{"key":"2700_CR83","doi-asserted-by":"crossref","unstructured":"Zhang M, Li F, Marquez-Lago TT, Leier A, Fan C, Kwoh CK, Chou KC, Song J, Jia C. MULTiPly: a novel multi-layer predictor for discovering general and specific types of promoters. Bioinformatics. 2019.","DOI":"10.1093\/bioinformatics\/btz016"},{"key":"2700_CR84","doi-asserted-by":"crossref","unstructured":"Witten IH, Frank E, Hall MA, Pal CJ: Data mining: practical machine learning tools and techniques: Morgan Kaufmann; 2016.","DOI":"10.1016\/B978-0-12-804291-5.00010-6"},{"key":"2700_CR85","doi-asserted-by":"crossref","unstructured":"Abe N, Zadrozny B, Langford J: Outlier detection by active learning. In: Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining: 2006. ACM: 504\u2013509.","DOI":"10.1145\/1150402.1150459"},{"issue":"2","key":"2700_CR86","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1080\/00224065.1997.11979756","volume":"29","author":"DM Sebert","year":"1997","unstructured":"Sebert DM. Outliers in statistical data. J Qual Technol. 1997;29(2):230.","journal-title":"J Qual Technol"},{"issue":"Dec","key":"2700_CR87","first-page":"139","volume":"2","author":"LM Manevitz","year":"2001","unstructured":"Manevitz LM, Yousef M. One-class SVMs for document classification. J Mach Learn Res. 2001;2(Dec):139\u201354.","journal-title":"J Mach Learn Res"},{"key":"2700_CR88","doi-asserted-by":"crossref","unstructured":"Hempstalk K, Frank E, Witten IH: One-class classification by combining density and class probability estimation. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases: 2008. Springer: 505\u2013519.","DOI":"10.1007\/978-3-540-87479-9_51"}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-019-2700-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s12859-019-2700-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-019-2700-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,14]],"date-time":"2023-09-14T05:33:43Z","timestamp":1694669623000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/s12859-019-2700-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,3,6]]},"references-count":88,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2019,12]]}},"alternative-id":["2700"],"URL":"https:\/\/doi.org\/10.1186\/s12859-019-2700-1","relation":{},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,3,6]]},"assertion":[{"value":"5 July 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 February 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 March 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Not applicable.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"J.S. is an Associate Editor of BMC Bioinformatics.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Publisher\u2019s Note"}}],"article-number":"112"}}