Publication Information

{'id': 'https://openalex.org/W1966052055', 'doi': 'https://doi.org/10.1186/1471-2105-7-s1-s11', 'title': 'A Regression-based K nearest neighbor algorithm for gene function prediction from heterogeneous data', 'display_name': 'A Regression-based K nearest neighbor algorithm for gene function prediction from heterogeneous data', 'publication_year': 2006, 'publication_date': '2006-03-01', 'ids': {'openalex': 'https://openalex.org/W1966052055', 'doi': 'https://doi.org/10.1186/1471-2105-7-s1-s11', 'mag': '1966052055', 'pmid': 'https://pubmed.ncbi.nlm.nih.gov/16723004', 'pmcid': 'https://www.ncbi.nlm.nih.gov/pmc/articles/1810312'}, 'language': 'en', 'primary_location': {'is_oa': True, 'landing_page_url': 'https://doi.org/10.1186/1471-2105-7-s1-s11', 'pdf_url': 'https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-7-S1-S11', 'source': {'id': 'https://openalex.org/S19032547', 'display_name': 'BMC Bioinformatics', 'issn_l': '1471-2105', 'issn': ['1471-2105'], 'is_oa': True, 'is_in_doaj': True, 'is_core': True, 'host_organization': 'https://openalex.org/P4310320256', 'host_organization_name': 'BioMed Central', 'host_organization_lineage': ['https://openalex.org/P4310319965', 'https://openalex.org/P4310320256'], 'host_organization_lineage_names': ['Springer Nature', 'BioMed Central'], 'type': 'journal'}, 'license': 'cc-by', 'license_id': 'https://openalex.org/licenses/cc-by', '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': 'gold', 'oa_url': 'https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-7-S1-S11', 'any_repository_has_fulltext': True}, 'authorships': [{'author_position': 'first', 'author': {'id': 'https://openalex.org/A5045133318', 'display_name': 'Zizhen Yao', 'orcid': 'https://orcid.org/0000-0002-9361-5607'}, 'institutions': [{'id': 'https://openalex.org/I201448701', 'display_name': 'University of Washington', 'ror': 'https://ror.org/00cvxb145', 'country_code': 'US', 'type': 'education', 'lineage': ['https://openalex.org/I201448701']}], 'countries': ['US'], 'is_corresponding': False, 'raw_author_name': 'Zizhen Yao', 'raw_affiliation_strings': ['Department of Computer Science and Engineering, AC101 Paul G. Allen Center, University of Washington, Seattle, WA, 98195, USA'], 'affiliations': [{'raw_affiliation_string': 'Department of Computer Science and Engineering, AC101 Paul G. Allen Center, University of Washington, Seattle, WA, 98195, USA', 'institution_ids': ['https://openalex.org/I201448701']}]}, {'author_position': 'last', 'author': {'id': 'https://openalex.org/A5086685720', 'display_name': 'Walter L. Ruzzo', 'orcid': 'https://orcid.org/0000-0002-6260-2926'}, 'institutions': [{'id': 'https://openalex.org/I201448701', 'display_name': 'University of Washington', 'ror': 'https://ror.org/00cvxb145', 'country_code': 'US', 'type': 'education', 'lineage': ['https://openalex.org/I201448701']}], 'countries': ['US'], 'is_corresponding': False, 'raw_author_name': 'Walter L Ruzzo', 'raw_affiliation_strings': ['Department of Computer Science and Engineering, AC101 Paul G. Allen Center, University of Washington, Seattle, WA, 98195, USA'], 'affiliations': [{'raw_affiliation_string': 'Department of Computer Science and Engineering, AC101 Paul G. Allen Center, University of Washington, Seattle, WA, 98195, USA', 'institution_ids': ['https://openalex.org/I201448701']}]}], 'institution_assertions': [], 'countries_distinct_count': 1, 'institutions_distinct_count': 1, 'corresponding_author_ids': [], 'corresponding_institution_ids': [], 'apc_list': {'value': 1690, 'currency': 'GBP', 'value_usd': 2072, 'provenance': 'doaj'}, 'apc_paid': {'value': 1690, 'currency': 'GBP', 'value_usd': 2072, 'provenance': 'doaj'}, 'fwci': 2.282, 'has_fulltext': True, 'fulltext_origin': 'pdf', 'cited_by_count': 118, 'citation_normalized_percentile': {'value': 0.999981, 'is_in_top_1_percent': True, 'is_in_top_10_percent': True}, 'cited_by_percentile_year': {'min': 97, 'max': 98}, 'biblio': {'volume': '7', 'issue': 'S1', 'first_page': None, 'last_page': None}, 'is_retracted': False, 'is_paratext': False, 'primary_topic': {'id': 'https://openalex.org/T10885', 'display_name': 'Gene expression and cancer classification', '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/T10885', 'display_name': 'Gene expression and cancer classification', '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/T10887', 'display_name': 'Bioinformatics and Genomic Networks', 'score': 0.9992, '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/T12254', 'display_name': 'Machine Learning in Bioinformatics', 'score': 0.9989, '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/protein-function-prediction', 'display_name': 'Protein function prediction', 'score': 0.6961417}], 'concepts': [{'id': 'https://openalex.org/C41008148', 'wikidata': 'https://www.wikidata.org/wiki/Q21198', 'display_name': 'Computer science', 'level': 0, 'score': 0.7083596}, {'id': 'https://openalex.org/C207060522', 'wikidata': 'https://www.wikidata.org/wiki/Q7251473', 'display_name': 'Protein function prediction', 'level': 4, 'score': 0.6961417}, {'id': 'https://openalex.org/C12267149', 'wikidata': 'https://www.wikidata.org/wiki/Q282453', 'display_name': 'Support vector machine', 'level': 2, 'score': 0.59091175}, {'id': 'https://openalex.org/C124101348', 'wikidata': 'https://www.wikidata.org/wiki/Q172491', 'display_name': 'Data mining', 'level': 1, 'score': 0.56485295}, {'id': 'https://openalex.org/C154945302', 'wikidata': 'https://www.wikidata.org/wiki/Q11660', 'display_name': 'Artificial intelligence', 'level': 1, 'score': 0.53790367}, {'id': 'https://openalex.org/C119857082', 'wikidata': 'https://www.wikidata.org/wiki/Q2539', 'display_name': 'Machine learning', 'level': 1, 'score': 0.50414956}, {'id': 'https://openalex.org/C183115368', 'wikidata': 'https://www.wikidata.org/wiki/Q856577', 'display_name': 'Weighting', 'level': 2, 'score': 0.5028543}, {'id': 'https://openalex.org/C73555534', 'wikidata': 'https://www.wikidata.org/wiki/Q622825', 'display_name': 'Cluster analysis', 'level': 2, 'score': 0.47855502}, {'id': 'https://openalex.org/C113238511', 'wikidata': 'https://www.wikidata.org/wiki/Q1071612', 'display_name': 'k-nearest neighbors algorithm', 'level': 2, 'score': 0.4764983}, {'id': 'https://openalex.org/C176217482', 'wikidata': 'https://www.wikidata.org/wiki/Q860554', 'display_name': 'Metric (unit)', 'level': 2, 'score': 0.4445179}, {'id': 'https://openalex.org/C2776214188', 'wikidata': 'https://www.wikidata.org/wiki/Q408386', 'display_name': 'Inference', 'level': 2, 'score': 0.44278944}, {'id': 'https://openalex.org/C148483581', 'wikidata': 'https://www.wikidata.org/wiki/Q446488', 'display_name': 'Feature selection', 'level': 2, 'score': 0.4370798}, {'id': 'https://openalex.org/C153180895', 'wikidata': 'https://www.wikidata.org/wiki/Q7148389', 'display_name': 'Pattern recognition (psychology)', 'level': 2, 'score': 0.3589583}, {'id': 'https://openalex.org/C71924100', 'wikidata': 'https://www.wikidata.org/wiki/Q11190', 'display_name': 'Medicine', 'level': 0, 'score': 0.0}, {'id': 'https://openalex.org/C55493867', 'wikidata': 'https://www.wikidata.org/wiki/Q7094', 'display_name': 'Biochemistry', 'level': 1, 'score': 0.0}, {'id': 'https://openalex.org/C185592680', 'wikidata': 'https://www.wikidata.org/wiki/Q2329', 'display_name': 'Chemistry', 'level': 0, 'score': 0.0}, {'id': 'https://openalex.org/C21547014', 'wikidata': 'https://www.wikidata.org/wiki/Q1423657', 'display_name': 'Operations management', 'level': 1, 'score': 0.0}, {'id': 'https://openalex.org/C2986374874', 'wikidata': 'https://www.wikidata.org/wiki/Q8054', 'display_name': 'Protein function', 'level': 3, 'score': 0.0}, {'id': 'https://openalex.org/C126838900', 'wikidata': 'https://www.wikidata.org/wiki/Q77604', 'display_name': 'Radiology', 'level': 1, 'score': 0.0}, {'id': 'https://openalex.org/C162324750', 'wikidata': 'https://www.wikidata.org/wiki/Q8134', 'display_name': 'Economics', 'level': 0, 'score': 0.0}, {'id': 'https://openalex.org/C104317684', 'wikidata': 'https://www.wikidata.org/wiki/Q7187', 'display_name': 'Gene', 'level': 2, 'score': 0.0}], 'mesh': [{'descriptor_ui': 'D019295', 'descriptor_name': 'Computational Biology', 'qualifier_ui': 'Q000379', 'qualifier_name': 'methods', 'is_major_topic': True}, {'descriptor_ui': 'D000465', 'descriptor_name': 'Algorithms', 'qualifier_ui': '', 'qualifier_name': None, 'is_major_topic': False}, {'descriptor_ui': 'D001185', 'descriptor_name': 'Artificial Intelligence', 'qualifier_ui': '', 'qualifier_name': None, 'is_major_topic': False}, {'descriptor_ui': 'D016000', 'descriptor_name': 'Cluster Analysis', 'qualifier_ui': '', 'qualifier_name': None, 'is_major_topic': False}, {'descriptor_ui': 'D003198', 'descriptor_name': 'Computer Simulation', 'qualifier_ui': '', 'qualifier_name': None, 'is_major_topic': False}, {'descriptor_ui': 'D029968', 'descriptor_name': 'Escherichia coli Proteins', 'qualifier_ui': 'Q000737', 'qualifier_name': 'chemistry', 'is_major_topic': False}, {'descriptor_ui': 'D005786', 'descriptor_name': 'Gene Expression Regulation', 'qualifier_ui': '', 'qualifier_name': None, 'is_major_topic': False}, {'descriptor_ui': 'D005798', 'descriptor_name': 'Genes, Bacterial', 'qualifier_ui': '', 'qualifier_name': None, 'is_major_topic': False}, {'descriptor_ui': 'D016680', 'descriptor_name': 'Genome, Bacterial', 'qualifier_ui': '', 'qualifier_name': None, 'is_major_topic': False}, {'descriptor_ui': 'D008957', 'descriptor_name': 'Models, Genetic', 'qualifier_ui': '', 'qualifier_name': None, 'is_major_topic': False}, {'descriptor_ui': 'D016571', 'descriptor_name': 'Neural Networks, Computer', 'qualifier_ui': '', 'qualifier_name': None, 'is_major_topic': False}, {'descriptor_ui': 'D020411', 'descriptor_name': 'Oligonucleotide Array Sequence Analysis', 'qualifier_ui': '', 'qualifier_name': None, 'is_major_topic': False}, {'descriptor_ui': 'D010363', 'descriptor_name': 'Pattern Recognition, Automated', 'qualifier_ui': '', 'qualifier_name': None, 'is_major_topic': False}, {'descriptor_ui': 'D011336', 'descriptor_name': 'Probability', 'qualifier_ui': '', 'qualifier_name': None, 'is_major_topic': False}, {'descriptor_ui': 'D012044', 'descriptor_name': 'Regression Analysis', 'qualifier_ui': '', 'qualifier_name': None, 'is_major_topic': False}, {'descriptor_ui': 'D015203', 'descriptor_name': 'Reproducibility of Results', 'qualifier_ui': '', 'qualifier_name': None, 'is_major_topic': False}, {'descriptor_ui': 'D020539', 'descriptor_name': 'Sequence Analysis, Protein', 'qualifier_ui': '', 'qualifier_name': None, 'is_major_topic': False}], 'locations_count': 3, 'locations': [{'is_oa': True, 'landing_page_url': 'https://doi.org/10.1186/1471-2105-7-s1-s11', 'pdf_url': 'https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-7-S1-S11', 'source': {'id': 'https://openalex.org/S19032547', 'display_name': 'BMC Bioinformatics', 'issn_l': '1471-2105', 'issn': ['1471-2105'], 'is_oa': True, 'is_in_doaj': True, 'is_core': True, 'host_organization': 'https://openalex.org/P4310320256', 'host_organization_name': 'BioMed Central', 'host_organization_lineage': ['https://openalex.org/P4310319965', 'https://openalex.org/P4310320256'], 'host_organization_lineage_names': ['Springer Nature', 'BioMed Central'], 'type': 'journal'}, 'license': 'cc-by', 'license_id': 'https://openalex.org/licenses/cc-by', 'version': 'publishedVersion', 'is_accepted': True, 'is_published': True}, {'is_oa': True, 'landing_page_url': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC1810312', 'pdf_url': None, 'source': {'id': 'https://openalex.org/S2764455111', 'display_name': 'PubMed Central', 'issn_l': None, 'issn': None, 'is_oa': True, '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': 'publishedVersion', 'is_accepted': True, 'is_published': True}, {'is_oa': False, 'landing_page_url': 'https://pubmed.ncbi.nlm.nih.gov/16723004', '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/10.1186/1471-2105-7-s1-s11', 'pdf_url': 'https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-7-S1-S11', 'source': {'id': 'https://openalex.org/S19032547', 'display_name': 'BMC Bioinformatics', 'issn_l': '1471-2105', 'issn': ['1471-2105'], 'is_oa': True, 'is_in_doaj': True, 'is_core': True, 'host_organization': 'https://openalex.org/P4310320256', 'host_organization_name': 'BioMed Central', 'host_organization_lineage': ['https://openalex.org/P4310319965', 'https://openalex.org/P4310320256'], 'host_organization_lineage_names': ['Springer Nature', 'BioMed Central'], 'type': 'journal'}, 'license': 'cc-by', 'license_id': 'https://openalex.org/licenses/cc-by', 'version': 'publishedVersion', 'is_accepted': True, 'is_published': True}, 'sustainable_development_goals': [], 'grants': [], 'datasets': [], 'versions': [], 'referenced_works_count': 28, 'referenced_works': ['https://openalex.org/W1534476081', 'https://openalex.org/W1588911128', 'https://openalex.org/W1980654514', 'https://openalex.org/W1995117714', 'https://openalex.org/W2013502943', 'https://openalex.org/W2014725748', 'https://openalex.org/W2047028564', 'https://openalex.org/W2060861141', 'https://openalex.org/W2071828122', 'https://openalex.org/W2084619201', 'https://openalex.org/W2096863518', 'https://openalex.org/W2097282516', 'https://openalex.org/W2099435674', 'https://openalex.org/W2102794349', 'https://openalex.org/W2109831613', 'https://openalex.org/W2128036349', 'https://openalex.org/W2135046866', 'https://openalex.org/W2141362201', 'https://openalex.org/W2142022327', 'https://openalex.org/W2146312020', 'https://openalex.org/W2150926065', 'https://openalex.org/W2151326548', 'https://openalex.org/W2159482845', 'https://openalex.org/W2161012147', 'https://openalex.org/W2171088586', 'https://openalex.org/W2329094530', 'https://openalex.org/W4210464465', 'https://openalex.org/W4234698323'], 'related_works': ['https://openalex.org/W394483113', 'https://openalex.org/W2180954594', 'https://openalex.org/W2153677915', 'https://openalex.org/W2127804977', 'https://openalex.org/W2108418243', 'https://openalex.org/W2052835778', 'https://openalex.org/W2049003611', 'https://openalex.org/W164103134', 'https://openalex.org/W1612029326', 'https://openalex.org/W128856181'], 'abstract_inverted_index': {'As': [0], 'a': [1, 34, 103, 107, 111, 140], 'variety': [2], 'of': [3, 49, 70, 90, 110, 113, 152, 230], 'functional': [4, 17], 'genomic': [5], 'and': [6, 62, 186, 201, 238, 249], 'proteomic': [7], 'techniques': [8], 'become': [9], 'available,': [10], 'there': [11], 'is': [12, 51, 79, 82, 202], 'an': [13], 'increasing': [14], 'need': [15], 'for': [16, 37, 210], 'analysis': [18], 'methodologies': [19], 'that': [20, 80, 123, 148, 192, 217], 'integrate': [21], 'heterogeneous': [22, 77, 263], 'data': [23, 60, 221], 'sources.': [24], 'In': [25], 'this': [26, 30, 95, 164], 'paper,': [27], 'we': [28, 97], 'address': [29, 94], 'issue': [31], 'by': [32, 53, 179, 218], 'proposing': [33], 'general': [35, 252], 'framework': [36, 253], 'gene': [38, 167], 'function': [39, 168], 'prediction': [40, 169, 223, 242], 'based': [41], 'on': [42], 'the': [43, 85, 121, 130, 134, 150, 197], 'k-nearest-neighbor': [44], '(KNN)': [45], 'algorithm.': [46], 'The': [47, 154], 'choice': [48, 89], 'KNN': [50, 72, 199, 231], 'motivated': [52], 'its': [54], 'simplicity,': [55], 'flexibility': [56], 'to': [57, 64, 84, 101, 119, 127, 144, 158, 166, 171, 258], 'incorporate': [58], 'different': [59, 220], 'types': [61], 'adaptability': [63], 'irregular': [65], 'feature': [66, 234], 'spaces.': [67], 'A': [68], 'weakness': [69], 'traditional': [71], 'methods,': [73], 'especially': [74], 'when': [75], 'handling': [76], 'data,': [78], 'performance': [81], 'subject': [83], 'often': [86], 'ad': [87], 'hoc': [88], 'similarity': [91, 104, 115], 'metric.': [92], 'To': [93], 'weakness,': [96], 'apply': [98, 163], 'regression': [99], 'methods': [100, 200], 'infer': [102], 'metric': [105], 'as': [106, 133], 'weighted': [108], 'combination': [109], 'set': [112], 'base': [114], 'measures,': [116], 'which': [117], 'helps': [118], 'locate': [120], 'neighbors': [122], 'are': [124], 'most': [125], 'likely': [126], 'be': [128, 256], 'in': [129], 'same': [131], 'class': [132], 'target': [135], 'gene.': [136], 'We': [137, 162, 190, 214], 'also': [138, 215, 255], 'suggest': [139], 'novel': [141], 'voting': [142], 'scheme': [143], 'generate': [145], 'confidence': [146], 'scores': [147], 'estimate': [149], 'accuracy': [151, 224, 243], 'predictions.': [153], 'method': [155], 'gracefully': [156], 'extends': [157], 'multi-way': [159], 'classification': [160, 176, 260], 'problems.': [161], 'technique': [165], 'according': [170], 'three': [172], 'well-known': [173], 'Escherichia': [174], 'coli': [175], 'schemes': [177], 'suggested': [178], 'biologists,': [180], 'using': [181], 'information': [182], 'derived': [183], 'from': [184], 'microarray': [185], 'genome': [187], 'sequencing': [188], 'data.': [189, 213], 'demonstrate': [191], 'our': [193], 'algorithm': [194], 'dramatically': [195], 'outperforms': [196], 'naive': [198], 'competitive': [203], 'with': [204, 232], 'support': [205], 'vector': [206], 'machine': [207], '(SVM)': [208], 'algorithms': [209], 'integrating': [211], 'heterogenous': [212], 'show': [216], 'combining': [219], 'sources,': [222], 'can': [225, 254], 'improve': [226], 'significantly.': [227], 'Our': [228], 'extension': [229], 'automatic': [233], 'weighting,': [235], 'multi-class': [236], 'prediction,': [237], 'probabilistic': [239], 'inference,': [240], 'enhance': [241], 'significantly': [244], 'while': [245], 'remaining': [246], 'efficient,': [247], 'intuitive': [248], 'flexible.': [250], 'This': [251], 'applied': [257], 'similar': [259], 'problems': [261], 'involving': [262], 'datasets.': [264]}, 'cited_by_api_url': 'https://api.openalex.org/works?filter=cites:W1966052055', 'counts_by_year': [{'year': 2024, 'cited_by_count': 12}, {'year': 2023, 'cited_by_count': 18}, {'year': 2022, 'cited_by_count': 14}, {'year': 2021, 'cited_by_count': 24}, {'year': 2020, 'cited_by_count': 5}, {'year': 2019, 'cited_by_count': 4}, {'year': 2018, 'cited_by_count': 5}, {'year': 2017, 'cited_by_count': 5}, {'year': 2016, 'cited_by_count': 1}, {'year': 2015, 'cited_by_count': 2}, {'year': 2014, 'cited_by_count': 1}, {'year': 2013, 'cited_by_count': 2}, {'year': 2012, 'cited_by_count': 3}], 'updated_date': '2025-01-02T03:55:38.019440', 'created_date': '2016-06-24'}