Publication Information

{'id': 'https://openalex.org/W2789316776', 'doi': 'https://doi.org/10.1093/bioinformatics/bty039', 'title': 'O-GlcNAcPRED-II: an integrated classification algorithm for identifying O-GlcNAcylation sites based on fuzzy undersampling and a <i>K</i>-means PCA oversampling technique', 'display_name': 'O-GlcNAcPRED-II: an integrated classification algorithm for identifying O-GlcNAcylation sites based on fuzzy undersampling and a <i>K</i>-means PCA oversampling technique', 'publication_year': 2018, 'publication_date': '2018-02-06', 'ids': {'openalex': 'https://openalex.org/W2789316776', 'doi': 'https://doi.org/10.1093/bioinformatics/bty039', 'mag': '2789316776', 'pmid': 'https://pubmed.ncbi.nlm.nih.gov/29420699'}, 'language': 'en', 'primary_location': {'is_oa': True, 'landing_page_url': 'https://doi.org/10.1093/bioinformatics/bty039', 'pdf_url': 'https://academic.oup.com/bioinformatics/article-pdf/34/12/2029/25047864/bty039.pdf', 'source': {'id': 'https://openalex.org/S52395412', 'display_name': 'Bioinformatics', 'issn_l': '1367-4803', 'issn': ['1367-4803', '1367-4811'], 'is_oa': True, 'is_in_doaj': True, 'is_core': True, 'host_organization': 'https://openalex.org/P4310311648', 'host_organization_name': 'Oxford University Press', 'host_organization_lineage': ['https://openalex.org/P4310311647', 'https://openalex.org/P4310311648'], 'host_organization_lineage_names': ['University of Oxford', 'Oxford University Press'], 'type': 'journal'}, 'license': None, 'license_id': None, 'version': 'publishedVersion', 'is_accepted': True, 'is_published': True}, 'type': 'article', 'type_crossref': 'journal-article', 'indexed_in': ['crossref', 'pubmed'], 'open_access': {'is_oa': True, 'oa_status': 'bronze', 'oa_url': 'https://academic.oup.com/bioinformatics/article-pdf/34/12/2029/25047864/bty039.pdf', 'any_repository_has_fulltext': False}, 'authorships': [{'author_position': 'first', 'author': {'id': 'https://openalex.org/A5066126756', 'display_name': 'Cangzhi Jia', 'orcid': 'https://orcid.org/0000-0002-4682-2881'}, 'institutions': [{'id': 'https://openalex.org/I43313876', 'display_name': 'Dalian Maritime University', 'ror': 'https://ror.org/002b7nr53', 'country_code': 'CN', 'type': 'education', 'lineage': ['https://openalex.org/I43313876']}], 'countries': ['CN'], 'is_corresponding': True, 'raw_author_name': 'Cangzhi Jia', 'raw_affiliation_strings': ['Department of Mathematics, Dalian Maritime University, Dalian, China'], 'affiliations': [{'raw_affiliation_string': 'Department of Mathematics, Dalian Maritime University, Dalian, China', 'institution_ids': ['https://openalex.org/I43313876']}]}, {'author_position': 'middle', 'author': {'id': 'https://openalex.org/A5065888073', 'display_name': 'Yun Zuo', 'orcid': 'https://orcid.org/0009-0009-3877-8102'}, 'institutions': [{'id': 'https://openalex.org/I43313876', 'display_name': 'Dalian Maritime University', 'ror': 'https://ror.org/002b7nr53', 'country_code': 'CN', 'type': 'education', 'lineage': ['https://openalex.org/I43313876']}], 'countries': ['CN'], 'is_corresponding': False, 'raw_author_name': 'Yun Zuo', 'raw_affiliation_strings': ['Department of Mathematics, Dalian Maritime University, Dalian, China'], 'affiliations': [{'raw_affiliation_string': 'Department of Mathematics, Dalian Maritime University, Dalian, China', 'institution_ids': ['https://openalex.org/I43313876']}]}, {'author_position': 'last', 'author': {'id': 'https://openalex.org/A5017426085', 'display_name': 'Quan Zou', 'orcid': 'https://orcid.org/0000-0001-6406-1142'}, 'institutions': [], 'countries': ['CN'], 'is_corresponding': True, 'raw_author_name': 'Quan Zou', 'raw_affiliation_strings': ['School of Computer Science and Technology, Tianjin University, Tianjin, China'], 'affiliations': [{'raw_affiliation_string': 'School of Computer Science and Technology, Tianjin University, Tianjin, China', 'institution_ids': []}]}], 'institution_assertions': [], 'countries_distinct_count': 1, 'institutions_distinct_count': 1, 'corresponding_author_ids': ['https://openalex.org/A5066126756', 'https://openalex.org/A5017426085'], 'corresponding_institution_ids': ['https://openalex.org/I43313876'], 'apc_list': {'value': 3618, 'currency': 'USD', 'value_usd': 3618, 'provenance': 'doaj'}, 'apc_paid': None, 'fwci': 7.794, 'has_fulltext': True, 'fulltext_origin': 'ngrams', 'cited_by_count': 125, 'citation_normalized_percentile': {'value': 0.999983, 'is_in_top_1_percent': True, 'is_in_top_10_percent': True}, 'cited_by_percentile_year': {'min': 98, 'max': 99}, 'biblio': {'volume': '34', 'issue': '12', 'first_page': '2029', 'last_page': '2036'}, 'is_retracted': False, 'is_paratext': False, 'primary_topic': {'id': 'https://openalex.org/T12254', 'display_name': 'Machine Learning in Bioinformatics', 'score': 0.9997, 'subfield': {'id': 'https://openalex.org/subfields/1312', 'display_name': 'Molecular Biology'}, 'field': {'id': 'https://openalex.org/fields/13', 'display_name': 'Biochemistry, Genetics and Molecular Biology'}, 'domain': {'id': 'https://openalex.org/domains/1', 'display_name': 'Life Sciences'}}, 'topics': [{'id': 'https://openalex.org/T12254', 'display_name': 'Machine Learning in Bioinformatics', 'score': 0.9997, 'subfield': {'id': 'https://openalex.org/subfields/1312', 'display_name': 'Molecular Biology'}, 'field': {'id': 'https://openalex.org/fields/13', 'display_name': 'Biochemistry, Genetics and Molecular Biology'}, 'domain': {'id': 'https://openalex.org/domains/1', 'display_name': 'Life Sciences'}}, {'id': 'https://openalex.org/T10602', 'display_name': 'Glycosylation and Glycoproteins Research', 'score': 0.9972, 'subfield': {'id': 'https://openalex.org/subfields/1312', 'display_name': 'Molecular Biology'}, 'field': {'id': 'https://openalex.org/fields/13', 'display_name': 'Biochemistry, Genetics and Molecular Biology'}, 'domain': {'id': 'https://openalex.org/domains/1', 'display_name': 'Life Sciences'}}, {'id': 'https://openalex.org/T10015', 'display_name': 'Genomics and Phylogenetic Studies', 'score': 0.9947, 'subfield': {'id': 'https://openalex.org/subfields/1312', 'display_name': 'Molecular Biology'}, 'field': {'id': 'https://openalex.org/fields/13', 'display_name': 'Biochemistry, Genetics and Molecular Biology'}, 'domain': {'id': 'https://openalex.org/domains/1', 'display_name': 'Life Sciences'}}], 'keywords': [{'id': 'https://openalex.org/keywords/oversampling', 'display_name': 'Oversampling', 'score': 0.82746017}], 'concepts': [{'id': 'https://openalex.org/C136536468', 'wikidata': 'https://www.wikidata.org/wiki/Q1225894', 'display_name': 'Undersampling', 'level': 2, 'score': 0.9015566}, {'id': 'https://openalex.org/C197323446', 'wikidata': 'https://www.wikidata.org/wiki/Q331222', 'display_name': 'Oversampling', 'level': 3, 'score': 0.82746017}, {'id': 'https://openalex.org/C169258074', 'wikidata': 'https://www.wikidata.org/wiki/Q245748', 'display_name': 'Random forest', 'level': 2, 'score': 0.730026}, {'id': 'https://openalex.org/C52001869', 'wikidata': 'https://www.wikidata.org/wiki/Q812530', 'display_name': 'Naive Bayes classifier', 'level': 3, 'score': 0.7215066}, {'id': 'https://openalex.org/C27438332', 'wikidata': 'https://www.wikidata.org/wiki/Q2873', 'display_name': 'Principal component analysis', 'level': 2, 'score': 0.6602342}, {'id': 'https://openalex.org/C41008148', 'wikidata': 'https://www.wikidata.org/wiki/Q21198', 'display_name': 'Computer science', 'level': 0, 'score': 0.62095183}, {'id': 'https://openalex.org/C154945302', 'wikidata': 'https://www.wikidata.org/wiki/Q11660', 'display_name': 'Artificial intelligence', 'level': 1, 'score': 0.57017756}, {'id': 'https://openalex.org/C12267149', 'wikidata': 'https://www.wikidata.org/wiki/Q282453', 'display_name': 'Support vector machine', 'level': 2, 'score': 0.5132284}, {'id': 'https://openalex.org/C21200559', 'wikidata': 'https://www.wikidata.org/wiki/Q7451068', 'display_name': 'Sensitivity (control systems)', 'level': 2, 'score': 0.50637376}, {'id': 'https://openalex.org/C95623464', 'wikidata': 'https://www.wikidata.org/wiki/Q1096149', 'display_name': 'Classifier (UML)', 'level': 2, 'score': 0.49083313}, {'id': 'https://openalex.org/C58166', 'wikidata': 'https://www.wikidata.org/wiki/Q224821', 'display_name': 'Fuzzy logic', 'level': 2, 'score': 0.480074}, {'id': 'https://openalex.org/C153180895', 'wikidata': 'https://www.wikidata.org/wiki/Q7148389', 'display_name': 'Pattern recognition (psychology)', 'level': 2, 'score': 0.4683836}, {'id': 'https://openalex.org/C119857082', 'wikidata': 'https://www.wikidata.org/wiki/Q2539', 'display_name': 'Machine learning', 'level': 1, 'score': 0.4248745}, {'id': 'https://openalex.org/C117220453', 'wikidata': 'https://www.wikidata.org/wiki/Q5172842', 'display_name': 'Correlation', 'level': 2, 'score': 0.41086754}, {'id': 'https://openalex.org/C124101348', 'wikidata': 'https://www.wikidata.org/wiki/Q172491', 'display_name': 'Data mining', 'level': 1, 'score': 0.38856953}, {'id': 'https://openalex.org/C11413529', 'wikidata': 'https://www.wikidata.org/wiki/Q8366', 'display_name': 'Algorithm', 'level': 1, 'score': 0.36891755}, {'id': 'https://openalex.org/C33923547', 'wikidata': 'https://www.wikidata.org/wiki/Q395', 'display_name': 'Mathematics', 'level': 0, 'score': 0.28364652}, {'id': 'https://openalex.org/C2776257435', 'wikidata': 'https://www.wikidata.org/wiki/Q1576430', 'display_name': 'Bandwidth (computing)', 'level': 2, 'score': 0.120090485}, {'id': 'https://openalex.org/C31258907', 'wikidata': 'https://www.wikidata.org/wiki/Q1301371', 'display_name': 'Computer network', 'level': 1, 'score': 0.0}, {'id': 'https://openalex.org/C24326235', 'wikidata': 'https://www.wikidata.org/wiki/Q126095', 'display_name': 'Electronic engineering', 'level': 1, 'score': 0.0}, {'id': 'https://openalex.org/C127413603', 'wikidata': 'https://www.wikidata.org/wiki/Q11023', 'display_name': 'Engineering', 'level': 0, 'score': 0.0}, {'id': 'https://openalex.org/C2524010', 'wikidata': 'https://www.wikidata.org/wiki/Q8087', 'display_name': 'Geometry', 'level': 1, 'score': 0.0}], 'mesh': [{'descriptor_ui': 'D019295', 'descriptor_name': 'Computational Biology', 'qualifier_ui': 'Q000379', 'qualifier_name': 'methods', 'is_major_topic': True}, {'descriptor_ui': 'D011499', 'descriptor_name': 'Protein Processing, Post-Translational', 'qualifier_ui': '', 'qualifier_name': None, 'is_major_topic': True}, {'descriptor_ui': 'D040901', 'descriptor_name': 'Proteomics', 'qualifier_ui': 'Q000379', 'qualifier_name': 'methods', 'is_major_topic': True}, {'descriptor_ui': 'D060388', 'descriptor_name': 'Support Vector Machine', 'qualifier_ui': '', 'qualifier_name': None, 'is_major_topic': True}, {'descriptor_ui': 'D000117', 'descriptor_name': 'Acetylglucosamine', 'qualifier_ui': '', 'qualifier_name': None, 'is_major_topic': False}, {'descriptor_ui': 'D001499', 'descriptor_name': 'Bayes Theorem', 'qualifier_ui': '', 'qualifier_name': None, 'is_major_topic': False}, {'descriptor_ui': 'D019295', 'descriptor_name': 'Computational Biology', 'qualifier_ui': '', 'qualifier_name': None, 'is_major_topic': False}, {'descriptor_ui': 'D008954', 'descriptor_name': 'Models, Biological', 'qualifier_ui': '', 'qualifier_name': None, 'is_major_topic': False}, {'descriptor_ui': 'D040901', 'descriptor_name': 'Proteomics', 'qualifier_ui': '', 'qualifier_name': None, 'is_major_topic': False}], 'locations_count': 2, 'locations': [{'is_oa': True, 'landing_page_url': 'https://doi.org/10.1093/bioinformatics/bty039', 'pdf_url': 'https://academic.oup.com/bioinformatics/article-pdf/34/12/2029/25047864/bty039.pdf', 'source': {'id': 'https://openalex.org/S52395412', 'display_name': 'Bioinformatics', 'issn_l': '1367-4803', 'issn': ['1367-4803', '1367-4811'], 'is_oa': True, 'is_in_doaj': True, 'is_core': True, 'host_organization': 'https://openalex.org/P4310311648', 'host_organization_name': 'Oxford University Press', 'host_organization_lineage': ['https://openalex.org/P4310311647', 'https://openalex.org/P4310311648'], 'host_organization_lineage_names': ['University of Oxford', 'Oxford University Press'], 'type': 'journal'}, 'license': None, 'license_id': None, 'version': 'publishedVersion', 'is_accepted': True, 'is_published': True}, {'is_oa': False, 'landing_page_url': 'https://pubmed.ncbi.nlm.nih.gov/29420699', 'pdf_url': None, 'source': {'id': 'https://openalex.org/S4306525036', 'display_name': 'PubMed', 'issn_l': None, 'issn': None, 'is_oa': False, 'is_in_doaj': False, 'is_core': False, 'host_organization': 'https://openalex.org/I1299303238', 'host_organization_name': 'National Institutes of Health', 'host_organization_lineage': ['https://openalex.org/I1299303238'], 'host_organization_lineage_names': ['National Institutes of Health'], 'type': 'repository'}, 'license': None, 'license_id': None, 'version': None, 'is_accepted': False, 'is_published': False}], 'best_oa_location': {'is_oa': True, 'landing_page_url': 'https://doi.org/10.1093/bioinformatics/bty039', 'pdf_url': 'https://academic.oup.com/bioinformatics/article-pdf/34/12/2029/25047864/bty039.pdf', 'source': {'id': 'https://openalex.org/S52395412', 'display_name': 'Bioinformatics', 'issn_l': '1367-4803', 'issn': ['1367-4803', '1367-4811'], 'is_oa': True, 'is_in_doaj': True, 'is_core': True, 'host_organization': 'https://openalex.org/P4310311648', 'host_organization_name': 'Oxford University Press', 'host_organization_lineage': ['https://openalex.org/P4310311647', 'https://openalex.org/P4310311648'], 'host_organization_lineage_names': ['University of Oxford', 'Oxford University Press'], 'type': 'journal'}, 'license': None, 'license_id': None, 'version': 'publishedVersion', 'is_accepted': True, 'is_published': True}, 'sustainable_development_goals': [{'id': 'https://metadata.un.org/sdg/15', 'score': 0.59, 'display_name': 'Life on land'}], 'grants': [{'funder': 'https://openalex.org/F4320335787', 'funder_display_name': 'Fundamental Research Funds for the Central Universities', 'award_id': '3132016306, 3132017048 and 3132017085'}, {'funder': 'https://openalex.org/F4320335869', 'funder_display_name': 'National Social Science Fund of China', 'award_id': '15CGL031'}], 'datasets': [], 'versions': [], 'referenced_works_count': 56, 'referenced_works': ['https://openalex.org/W1194137360', 'https://openalex.org/W1494484168', 'https://openalex.org/W1652316604', 'https://openalex.org/W1984148780', 'https://openalex.org/W1995173448', 'https://openalex.org/W1998064689', 'https://openalex.org/W2018559830', 'https://openalex.org/W2022965734', 'https://openalex.org/W2025379444', 'https://openalex.org/W2028549892', 'https://openalex.org/W2029119755', 'https://openalex.org/W2030776726', 'https://openalex.org/W2048356293', 'https://openalex.org/W2052892694', 'https://openalex.org/W2053765706', 'https://openalex.org/W2074328536', 'https://openalex.org/W2079074163', 'https://openalex.org/W2085195990', 'https://openalex.org/W2088456241', 'https://openalex.org/W2097606916', 'https://openalex.org/W2098376021', 'https://openalex.org/W2100683979', 'https://openalex.org/W2103525038', 'https://openalex.org/W2111705855', 'https://openalex.org/W2114024619', 'https://openalex.org/W2118729365', 'https://openalex.org/W2121464890', 'https://openalex.org/W2124266758', 'https://openalex.org/W2129137060', 'https://openalex.org/W2145957695', 'https://openalex.org/W2149376055', 'https://openalex.org/W2150757437', 'https://openalex.org/W2154139219', 'https://openalex.org/W2154522012', 'https://openalex.org/W2157658519', 'https://openalex.org/W2161621183', 'https://openalex.org/W2164412127', 'https://openalex.org/W2168012258', 'https://openalex.org/W2170747616', 'https://openalex.org/W2172162168', 'https://openalex.org/W2217361398', 'https://openalex.org/W2387572940', 'https://openalex.org/W2436244623', 'https://openalex.org/W2439245561', 'https://openalex.org/W2465012682', 'https://openalex.org/W2471518332', 'https://openalex.org/W2472513547', 'https://openalex.org/W2528774686', 'https://openalex.org/W2530181556', 'https://openalex.org/W2605516250', 'https://openalex.org/W2607357445', 'https://openalex.org/W2608035254', 'https://openalex.org/W2608745162', 'https://openalex.org/W2614370829', 'https://openalex.org/W2911964244', 'https://openalex.org/W4230694935'], 'related_works': ['https://openalex.org/W80466363', 'https://openalex.org/W4390415670', 'https://openalex.org/W4389233021', 'https://openalex.org/W4308469503', 'https://openalex.org/W4288337828', 'https://openalex.org/W4287816717', 'https://openalex.org/W32988189', 'https://openalex.org/W2947132063', 'https://openalex.org/W2904737874', 'https://openalex.org/W2399571531'], 'abstract_inverted_index': {'Abstract': [0], 'Motivation': [1], 'Protein': [2], 'O-GlcNAcylation': [3, 60, 93], '(O-GlcNAc)': [4], 'is': [5, 48], 'an': [6, 86], 'important': [7], 'post-translational': [8], 'modification': [9], 'of': [10, 77, 117, 130, 140, 166, 169, 172, 178], 'serine': [11], '(S)/threonine': [12], '(T)': [13], 'residues': [14], 'that': [15, 26, 161, 198], 'involves': [16], 'multiple': [17], 'molecular': [18], 'and': [19, 35, 57, 103, 111, 121, 155, 174, 208], 'cellular': [20], 'processes.': [21], 'Recent': [22], 'studies': [23], 'have': [24, 66], 'suggested': [25], 'abnormal': [27], 'O-G1cNAcylation': [28, 43], 'causes': [29], 'many': [30], 'diseases,': [31], 'such': [32], 'as': [33], 'cancer': [34], 'various': [36], 'neurodegenerative': [37], 'diseases.': [38], 'With': [39], 'the': [40, 115, 118, 137, 187, 199], 'available': [41, 216], 'protein': [42], 'sites': [44], 'experimentally': [45], 'verified,': [46], 'it': [47], 'highly': [49], 'desired': [50], 'to': [51, 55, 90, 113, 135], 'develop': [52], 'automated': [53], 'methods': [54, 65], 'rapidly': [56], 'effectively': [58], 'identify': [59, 91], 'sites.': [61, 94], 'Although': [62], 'some': [63], 'computational': [64], 'been': [67, 72], 'proposed,': [68], 'their': [69], 'performance': [70], 'has': [71], 'unsatisfactory,': [73], 'particularly': [74], 'in': [75], 'terms': [76], 'prediction': [78, 205], 'sensitivity.': [79], 'Results': [80], 'In': [81], 'this': [82], 'study,': [83], 'we': [84], 'developed': [85], 'ensemble': [87], 'model': [88], 'O-GlcNAcPRED-II': [89, 162, 191], 'potential': [92], 'A': [95], 'K-means': [96], 'principal': [97], 'component': [98], 'analysis': [99], 'oversampling': [100], 'technique': [101], '(KPCA)': [102], 'fuzzy': [104], 'undersampling': [105], 'method': [106], '(FUS)': [107], 'were': [108], 'first': [109], 'proposed': [110, 200], 'incorporated': [112], 'reduce': [114], 'proportion': [116], 'original': [119], 'positive': [120], 'negative': [122], 'training': [123], 'samples.': [124], 'Then,': [125], 'rotation': [126], 'forest,': [127, 150], 'a': [128, 164], 'type': [129], 'classifier-integrated': [131], 'system,': [132], 'was': [133], 'adopted': [134], 'divide': [136], 'eight': [138], 'types': [139], 'feature': [141], 'space': [142], 'into': [143], 'several': [144], 'subsets': [145], 'using': [146], 'four': [147], 'sub-classifiers:': [148], 'random': [149], 'k-nearest': [151], 'neighbour,': [152], 'naive': [153], 'Bayesian': [154], 'support': [156], 'vector': [157], 'machine.': [158], 'We': [159], 'observed': [160], 'achieved': [163], 'sensitivity': [165], '81.05%,': [167], 'specificity': [168], '95.91%,': [170], 'accuracy': [171], '91.43%': [173], 'Matthew’s': [175], 'correlation': [176], 'coefficient': [177], '0.7928': [179], 'for': [180], 'five-fold': [181], 'cross-validation': [182], 'run': [183], '10': [184], 'times.': [185], 'Additionally,': [186], 'results': [188], 'obtained': [189], 'by': [190], 'on': [192], 'two': [193], 'independent': [194], 'datasets': [195], 'also': [196], 'indicated': [197], 'predictor': [201], 'outperformed': [202], 'five': [203], 'published': [204], 'tools.': [206], 'Availability': [207], 'implementation': [209], 'http://121.42.167.206/OGlcPred/': [210], 'Supplementary': [211, 213], 'information': [212], 'data': [214], 'are': [215], 'at': [217], 'Bioinformatics': [218], 'online.': [219]}, 'cited_by_api_url': 'https://api.openalex.org/works?filter=cites:W2789316776', 'counts_by_year': [{'year': 2024, 'cited_by_count': 8}, {'year': 2023, 'cited_by_count': 13}, {'year': 2022, 'cited_by_count': 15}, {'year': 2021, 'cited_by_count': 20}, {'year': 2020, 'cited_by_count': 24}, {'year': 2019, 'cited_by_count': 22}, {'year': 2018, 'cited_by_count': 23}], 'updated_date': '2024-12-12T07:45:59.639918', 'created_date': '2018-03-29'}