{"id":"https://openalex.org/W2069082987","doi":"https://doi.org/10.1145/2808719.2811430","title":"Unsupervised identification of redundant domain entries in InterPro database using clustering techniques","display_name":"Unsupervised identification of redundant domain entries in InterPro database using clustering techniques","publication_year":2015,"publication_date":"2015-09-09","ids":{"openalex":"https://openalex.org/W2069082987","doi":"https://doi.org/10.1145/2808719.2811430","mag":"2069082987"},"language":"en","primary_location":{"id":"doi:10.1145/2808719.2811430","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2808719.2811430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082878067","display_name":"Ahmet S\u00fcreyya Rifaio\u011flu","orcid":"https://orcid.org/0000-0001-6717-4767"},"institutions":[{"id":"https://openalex.org/I201799495","display_name":"Middle East Technical University","ror":"https://ror.org/014weej12","country_code":"TR","type":"education","lineage":["https://openalex.org/I201799495"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Ahmet S\u00fcreyya Rifaio\u011flu","raw_affiliation_strings":["Middle East Technical University, \u00c7ankaya, Ankara, Turkey"],"affiliations":[{"raw_affiliation_string":"Middle East Technical University, \u00c7ankaya, Ankara, Turkey","institution_ids":["https://openalex.org/I201799495"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003981652","display_name":"Tunca Do\u011fan","orcid":"https://orcid.org/0000-0002-1298-9763"},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tunca Do\u011fan","raw_affiliation_strings":["European Bioinformatics Institute, Hinxton, Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"European Bioinformatics Institute, Hinxton, Cambridge, UK","institution_ids":["https://openalex.org/I1303153112"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045764563","display_name":"Tolga Can","orcid":"https://orcid.org/0000-0002-5532-0154"},"institutions":[{"id":"https://openalex.org/I201799495","display_name":"Middle East Technical University","ror":"https://ror.org/014weej12","country_code":"TR","type":"education","lineage":["https://openalex.org/I201799495"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Tolga Can","raw_affiliation_strings":["Middle East Technical University, \u00c7ankaya Ankara, Turkey"],"affiliations":[{"raw_affiliation_string":"Middle East Technical University, \u00c7ankaya Ankara, Turkey","institution_ids":["https://openalex.org/I201799495"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5082878067"],"corresponding_institution_ids":["https://openalex.org/I201799495"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05144847,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"505","last_page":"506"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.998199999332428,"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":0.9948999881744385,"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/cluster-analysis","display_name":"Cluster analysis","score":0.7352710962295532},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7167311906814575},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6807217001914978},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6265589594841003},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4865078330039978},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.47431159019470215},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46505531668663025},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46388134360313416},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.4414994716644287},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3459157347679138},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.10856509208679199}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7352710962295532},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7167311906814575},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6807217001914978},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6265589594841003},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4865078330039978},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.47431159019470215},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46505531668663025},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46388134360313416},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.4414994716644287},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3459157347679138},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.10856509208679199},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2808719.2811430","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2808719.2811430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},{"id":"pmh:oai:open.metu.edu.tr:11511/31766","is_oa":false,"landing_page_url":"https://hdl.handle.net/11511/31766","pdf_url":null,"source":{"id":"https://openalex.org/S4306402495","display_name":"OpenMETU (Middle East Technical University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I201799495","host_organization_name":"Middle East Technical University","host_organization_lineage":["https://openalex.org/I201799495"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2102027645","https://openalex.org/W2124166542","https://openalex.org/W2145268834","https://openalex.org/W2147526198","https://openalex.org/W2164461702"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2358755282","https://openalex.org/W2625833328","https://openalex.org/W1533177136","https://openalex.org/W4380994516","https://openalex.org/W3200375535"],"abstract_inverted_index":{"InterPro":[0,64,139],"is":[1,106],"a":[2,24,93,109,129,154],"widely":[3],"used":[4,150],"database":[5,26],"that":[6,92,111],"integrates":[7],"functional":[8,28],"signatures":[9,36,86,119],"provided":[10],"by":[11,151],"different":[12],"protein":[13],"sequence":[14,29],"annotation":[15],"databases":[16],"with":[17,120],"manual":[18],"curation;":[19],"in":[20,42,62,78,128],"order":[21,79],"to":[22,80,82,107,141],"present":[23],"comprehensive":[25],"of":[27,34,57,96,115,134,160],"annotation.":[30],"However,":[31],"the":[32,35,54,63,113,135,143,158],"integration":[33,159],"causes":[37],"inconsistent":[38,58,118],"and/or":[39],"redundant":[40,60,98,116],"annotations":[41],"some":[43],"cases.":[44],"In":[45],"this":[46],"study,":[47],"we":[48],"proposed":[49],"an":[50],"unsupervised":[51],"method":[52],"for":[53],"automatic":[55],"detection":[56],"and":[59,73,117],"entries":[61,99],"database.":[65],"Two":[66],"clustering":[67,75],"methods:":[68],"Markov":[69],"Cluster":[70],"Algorithm":[71],"(MCL)":[72],"hierarchical":[74],"are":[76],"employed":[77],"investigate":[81],"what":[83],"extent":[84],"these":[85],"can":[87,100],"be":[88,101,149],"detected.":[89],"Results":[90],"show":[91],"considerable":[94],"amount":[95],"(~75%)":[97],"identified.":[102],"The":[103,132],"future":[104],"goal":[105],"develop":[108],"system":[110],"does":[112],"identification":[114],"very":[121],"high":[122],"performance":[123],"using":[124],"machine":[125],"learning":[126],"techniques":[127],"supervised":[130],"fashion.":[131],"findings":[133],"study":[136],"may":[137,147],"aid":[138],"curators":[140,152],"fix":[142],"problematic":[144],"entries.":[145],"It":[146],"also":[148],"as":[153],"road":[155],"map":[156],"before":[157],"new":[161],"signatures.":[162]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}