{"id":"https://openalex.org/W2081589865","doi":"https://doi.org/10.1109/bibm.2014.6999390","title":"K-mer clustering algorithm using a MapReduce approach","display_name":"K-mer clustering algorithm using a MapReduce approach","publication_year":2014,"publication_date":"2014-11-01","ids":{"openalex":"https://openalex.org/W2081589865","doi":"https://doi.org/10.1109/bibm.2014.6999390","mag":"2081589865"},"language":"en","primary_location":{"id":"doi:10.1109/bibm.2014.6999390","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2014.6999390","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5019199401","display_name":"Chang Sik Kim","orcid":"https://orcid.org/0000-0001-9595-244X"},"institutions":[{"id":"https://openalex.org/I2802015276","display_name":"Daresbury Laboratory","ror":"https://ror.org/0089bg420","country_code":"GB","type":"facility","lineage":["https://openalex.org/I162524378","https://openalex.org/I2802015276","https://openalex.org/I4210087105"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chang Sik Kim","raw_affiliation_strings":["The Hartree Centre, STFC Daresbury Laboratory, Cheshire, UK","The Hartree Centre, STFC Daresbury Laboratory, Warrington, Cheshire WA4 4AD, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hartree Centre, STFC Daresbury Laboratory, Cheshire, UK","institution_ids":["https://openalex.org/I2802015276"]},{"raw_affiliation_string":"The Hartree Centre, STFC Daresbury Laboratory, Warrington, Cheshire WA4 4AD, UK","institution_ids":["https://openalex.org/I2802015276"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052155666","display_name":"Martyn Winn","orcid":"https://orcid.org/0000-0003-0496-6796"},"institutions":[{"id":"https://openalex.org/I2802015276","display_name":"Daresbury Laboratory","ror":"https://ror.org/0089bg420","country_code":"GB","type":"facility","lineage":["https://openalex.org/I162524378","https://openalex.org/I2802015276","https://openalex.org/I4210087105"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Martyn D. Winn","raw_affiliation_strings":["The Hartree Centre, STFC Daresbury Laboratory, Cheshire, UK","The Hartree Centre, STFC Daresbury Laboratory, Warrington, Cheshire WA4 4AD, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hartree Centre, STFC Daresbury Laboratory, Cheshire, UK","institution_ids":["https://openalex.org/I2802015276"]},{"raw_affiliation_string":"The Hartree Centre, STFC Daresbury Laboratory, Warrington, Cheshire WA4 4AD, UK","institution_ids":["https://openalex.org/I2802015276"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023900951","display_name":"Vipin Sachdeva","orcid":"https://orcid.org/0000-0001-7914-0185"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vipin Sachdeva","raw_affiliation_strings":["Computational Science Center, T.J. Watson Research Center, Cambridge, MA, USA","Computational Science Center, IBM T.J. Watson Research Center, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Science Center, T.J. Watson Research Center, Cambridge, MA, USA","institution_ids":[]},{"raw_affiliation_string":"Computational Science Center, IBM T.J. Watson Research Center, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040280528","display_name":"Kirk E. Jordan","orcid":"https://orcid.org/0000-0001-5148-4437"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kirk E. Jordan","raw_affiliation_strings":["Computational Science Center, T.J. Watson Research Center, Cambridge, MA, USA","Computational Science Center, IBM T.J. Watson Research Center, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Science Center, T.J. Watson Research Center, Cambridge, MA, USA","institution_ids":[]},{"raw_affiliation_string":"Computational Science Center, IBM T.J. Watson Research Center, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9932000041007996,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9932000041007996,"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/T10885","display_name":"Gene expression and cancer classification","score":0.9929999709129333,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9900000095367432,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7703353762626648},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6739997863769531},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5981492400169373},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5826362371444702},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5576298236846924},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4438056945800781},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3818746507167816},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20822420716285706},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.08375737071037292},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07750743627548218}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7703353762626648},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6739997863769531},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5981492400169373},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5826362371444702},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5576298236846924},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4438056945800781},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3818746507167816},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20822420716285706},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.08375737071037292},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07750743627548218},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bibm.2014.6999390","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2014.6999390","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},{"id":"pmh:oai:purl.org/net/epubs:work/28671071","is_oa":false,"landing_page_url":"http://purl.org/net/epubs/work/28671071","pdf_url":null,"source":{"id":"https://openalex.org/S4306400334","display_name":"Science and Technology Facilities Council","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2025191288","https://openalex.org/W2096128575","https://openalex.org/W2126419817","https://openalex.org/W2166837162","https://openalex.org/W2246488289"],"related_works":["https://openalex.org/W4298130764","https://openalex.org/W2136583354","https://openalex.org/W2804364458","https://openalex.org/W2111238207","https://openalex.org/W2132641928","https://openalex.org/W4310225030","https://openalex.org/W2760721665","https://openalex.org/W2090259340","https://openalex.org/W1926736923","https://openalex.org/W2158836806"],"abstract_inverted_index":{"With":[0],"recent":[1],"advances":[2],"in":[3],"high":[4],"throughput":[5],"sequencing":[6],"platforms,":[7],"it":[8],"is":[9],"possible":[10],"to":[11,23],"sequence":[12,33],"RNA":[13,32],"obtained":[14],"from":[15],"biological":[16],"samples":[17],"more":[18,46],"cost-effectively":[19],"and":[20,39],"comprehensively.":[21],"Due":[22],"the":[24,27,43],"ubiquity":[25],"of":[26,31],"technology,":[28],"massive":[29],"volumes":[30],"data":[34],"are":[35],"now":[36],"being":[37],"generated,":[38],"as":[40],"a":[41],"result":[42],"need":[44],"for":[45],"efficient":[47],"analysis":[48],"software":[49],"has":[50],"become":[51],"an":[52],"urgent":[53],"challenge.":[54]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
