{"id":"https://openalex.org/W2950226278","doi":"https://doi.org/10.1186/s12859-017-1881-8","title":"K-mer clustering algorithm using a MapReduce framework: application to the parallelization of the Inchworm module of Trinity","display_name":"K-mer clustering algorithm using a MapReduce framework: application to the parallelization of the Inchworm module of Trinity","publication_year":2017,"publication_date":"2017-11-03","ids":{"openalex":"https://openalex.org/W2950226278","doi":"https://doi.org/10.1186/s12859-017-1881-8","mag":"2950226278","pmid":"https://pubmed.ncbi.nlm.nih.gov/29100493"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-017-1881-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-017-1881-8","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-017-1881-8","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/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-017-1881-8","any_repository_has_fulltext":true},"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"]},{"id":"https://openalex.org/I4210129527","display_name":"Cancer Research UK Manchester Institute","ror":"https://ror.org/037405c78","country_code":"GB","type":"facility","lineage":["https://openalex.org/I2801316944","https://openalex.org/I4210129527"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chang Sik Kim","raw_affiliation_strings":["Present addresse Cancer Research UK Manchester Institute, The University of Manchester, M20 4BX, Manchester, UK","The Hartree Centre and Scientific Computing Department, STFC Daresbury Laboratory, Warrington, WA4 4AD, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Present addresse Cancer Research UK Manchester Institute, The University of Manchester, M20 4BX, Manchester, UK","institution_ids":["https://openalex.org/I4210129527"]},{"raw_affiliation_string":"The Hartree Centre and Scientific Computing Department, STFC Daresbury Laboratory, Warrington, 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":true,"raw_author_name":"Martyn D. Winn","raw_affiliation_strings":["The Hartree Centre and Scientific Computing Department, STFC Daresbury Laboratory, Warrington, WA4 4AD, UK. martyn.winn@stfc.ac.uk","The Hartree Centre and Scientific Computing Department, STFC Daresbury Laboratory, Warrington, WA4 4AD, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hartree Centre and Scientific Computing Department, STFC Daresbury Laboratory, Warrington, WA4 4AD, UK. martyn.winn@stfc.ac.uk","institution_ids":["https://openalex.org/I2802015276"]},{"raw_affiliation_string":"The Hartree Centre and Scientific Computing Department, STFC Daresbury Laboratory, Warrington, 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"]},{"id":"https://openalex.org/I4210094840","display_name":"Silicon Therapeutics (United States)","ror":"https://ror.org/00rbf3t83","country_code":"US","type":"company","lineage":["https://openalex.org/I4210094840"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vipin Sachdeva","raw_affiliation_strings":["Computational Science Center, IBM T.J. Watson Research, Cambridge, MA, USA","Present addresse Silicon Therapeutics, 300 A Street, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Science Center, IBM T.J. Watson Research, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"Present addresse Silicon Therapeutics, 300 A Street, Boston, MA, USA","institution_ids":["https://openalex.org/I4210094840"]}]},{"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, IBM T.J. Watson Research, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Science Center, IBM T.J. Watson Research, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5052155666"],"corresponding_institution_ids":["https://openalex.org/I2802015276"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":0.4054,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.61313098,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"18","issue":"1","first_page":"467","last_page":"467"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.808899998664856,"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":0.808899998664856,"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":0.10620000213384628,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.01850000023841858,"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/computer-science","display_name":"Computer science","score":0.8594489097595215},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6882969737052917},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6606820225715637},{"id":"https://openalex.org/keywords/de-bruijn-graph","display_name":"De Bruijn graph","score":0.5410616993904114},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.49823927879333496},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49049490690231323},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.48856601119041443},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4833804965019226},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4454852342605591},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37143561244010925},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35539576411247253},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.31393367052078247},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.12803715467453003},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10621729493141174},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.08696472644805908}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8594489097595215},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6882969737052917},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6606820225715637},{"id":"https://openalex.org/C20218877","wikidata":"https://www.wikidata.org/wiki/Q3066095","display_name":"De Bruijn graph","level":3,"score":0.5410616993904114},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.49823927879333496},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49049490690231323},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.48856601119041443},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4833804965019226},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4454852342605591},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37143561244010925},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35539576411247253},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.31393367052078247},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.12803715467453003},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10621729493141174},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.08696472644805908},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural 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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012313","descriptor_name":"RNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012313","descriptor_name":"RNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012313","descriptor_name":"RNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012313","descriptor_name":"RNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D012313","descriptor_name":"RNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D012313","descriptor_name":"RNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059467","descriptor_name":"Transcriptome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059467","descriptor_name":"Transcriptome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059467","descriptor_name":"Transcriptome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":7,"locations":[{"id":"doi:10.1186/s12859-017-1881-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-017-1881-8","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-017-1881-8","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/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:29100493","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29100493","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"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":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:3ab8751957744ec3a613a650d5a1716b","is_oa":true,"landing_page_url":"https://doaj.org/article/3ab8751957744ec3a613a650d5a1716b","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 18, Iss 1, Pp 1-15 (2017)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:4599253","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5670514","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/7f37d60a-d5f6-4213-9287-a0f2829443d9","is_oa":true,"landing_page_url":"https://research.manchester.ac.uk/en/publications/7f37d60a-d5f6-4213-9287-a0f2829443d9","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Kim, C S, Winn, M D, Sachdeva, V & Jordan, K E 2017, 'K-mer clustering algorithm using a MapReduce framework : Application to the parallelization of the Inchworm module of Trinity', BMC Bioinformatics, vol. 18, no. 1, 467. https://doi.org/10.1186/s12859-017-1881-8","raw_type":"article"},{"id":"pmh:oai:pure.atira.dk:publications/7f37d60a-d5f6-4213-9287-a0f2829443d9","is_oa":true,"landing_page_url":"http://www.scopus.com/inward/record.url?scp=85032732251&partnerID=8YFLogxK","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Kim, C S, Winn, M D, Sachdeva, V & Jordan, K E 2017, 'K-mer clustering algorithm using a MapReduce framework : Application to the parallelization of the Inchworm module of Trinity', BMC Bioinformatics, vol. 18, no. 1, 467. https://doi.org/10.1186/s12859-017-1881-8","raw_type":"article"},{"id":"pmh:oai:purl.org/net/epubs:work/35556030","is_oa":false,"landing_page_url":"http://purl.org/net/epubs/work/35556030","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":{"id":"doi:10.1186/s12859-017-1881-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-017-1881-8","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-017-1881-8","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/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320314070","display_name":"Broad Institute","ror":"https://ror.org/05a0ya142"},{"id":"https://openalex.org/F4320334632","display_name":"Science and Technology Facilities Council","ror":"https://ror.org/057g20z61"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2950226278.pdf","grobid_xml":"https://content.openalex.org/works/W2950226278.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W163621170","https://openalex.org/W1598064945","https://openalex.org/W1912338927","https://openalex.org/W1966822396","https://openalex.org/W1999574084","https://openalex.org/W1999780947","https://openalex.org/W2000875411","https://openalex.org/W2002055996","https://openalex.org/W2015553373","https://openalex.org/W2019724001","https://openalex.org/W2025191288","https://openalex.org/W2058835062","https://openalex.org/W2061537056","https://openalex.org/W2065348251","https://openalex.org/W2066671865","https://openalex.org/W2096128575","https://openalex.org/W2103993217","https://openalex.org/W2104644701","https://openalex.org/W2105371278","https://openalex.org/W2105656684","https://openalex.org/W2107564978","https://openalex.org/W2110392562","https://openalex.org/W2112491476","https://openalex.org/W2113915152","https://openalex.org/W2114720692","https://openalex.org/W2116899182","https://openalex.org/W2118058166","https://openalex.org/W2118874738","https://openalex.org/W2119180969","https://openalex.org/W2122056961","https://openalex.org/W2126419817","https://openalex.org/W2127421473","https://openalex.org/W2127963635","https://openalex.org/W2136145671","https://openalex.org/W2141458291","https://openalex.org/W2149993795","https://openalex.org/W2152556446","https://openalex.org/W2153268494","https://openalex.org/W2155804510","https://openalex.org/W2156841387","https://openalex.org/W2160969485","https://openalex.org/W2161546116","https://openalex.org/W2163830511","https://openalex.org/W2166837162","https://openalex.org/W2171815584","https://openalex.org/W2172649569","https://openalex.org/W2173213060","https://openalex.org/W2276982311","https://openalex.org/W2467009323","https://openalex.org/W4256452935"],"related_works":["https://openalex.org/W1975912699","https://openalex.org/W2594227215","https://openalex.org/W2949604727","https://openalex.org/W2105656684","https://openalex.org/W2562683361","https://openalex.org/W1640935858","https://openalex.org/W2179933869","https://openalex.org/W4386259219","https://openalex.org/W3125399386","https://openalex.org/W3037187668"],"abstract_inverted_index":{"BACKGROUND:":[0],"De":[1],"novo":[2,18],"transcriptome":[3],"assembly":[4,228],"is":[5,120,135,221],"an":[6],"important":[7],"technique":[8],"for":[9,56,103,199,226],"understanding":[10],"gene":[11,83],"expression":[12],"in":[13,53,156,175],"non-model":[14],"organisms.":[15],"Many":[16],"de":[17,22],"assemblers":[19],"using":[20,99,126],"the":[21,29,43,54,73,96,100,105,112,123,127,143,147,154,157,160,176,213],"Bruijn":[23],"graph":[24],"of":[25,28,36,46,82,107,114,159,169,185,206],"a":[26,66,167,186,222],"set":[27,45],"RNA":[30],"sequences":[31],"rely":[32],"on":[33,166,212],"in-memory":[34],"representation":[35],"this":[37,138],"graph.":[38],"However,":[39],"current":[40],"methods":[41],"analyse":[42],"complete":[44],"read-derived":[47],"k-mer":[48],"sequence":[49],"at":[50],"once,":[51],"resulting":[52],"need":[55],"computer":[57],"hardware":[58,134],"with":[59],"large":[60,108,173],"shared":[61],"memory.":[62],"RESULTS:":[63],"We":[64,94],"introduce":[65],"novel":[67],"approach":[68,102],"that":[69,193,218],"clusters":[70,77],"k-mers":[71],"as":[72],"first":[74],"step.":[75],"The":[76,117],"correspond":[78],"to":[79,90],"small":[80],"sets":[81],"products,":[84],"which":[85,110],"can":[86],"be":[87],"processed":[88],"quickly":[89],"give":[91],"candidate":[92],"transcripts.":[93],"implement":[95],"clustering":[97,195,220],"step":[98,225],"MapReduce":[101],"parallelising":[104],"analysis":[106],"datasets,":[109],"enables":[111],"use":[113,184],"compute":[115,124,187],"clusters.":[116],"computational":[118],"task":[119],"distributed":[121],"across":[122],"system":[125],"industry-standard":[128],"MPI":[129],"protocol,":[130],"and":[131,152,178],"no":[132],"specialised":[133],"required.":[136],"Using":[137],"approach,":[139],"we":[140,209,216],"have":[141,210],"re-implemented":[142],"Inchworm":[144],"module":[145],"from":[146],"widely":[148],"used":[149],"Trinity":[150,162,214],"pipeline,":[151],"tested":[153],"method":[155],"context":[158],"full":[161],"pipeline.":[163],"Validation":[164],"tests":[165],"range":[168],"real":[170],"datasets":[171],"show":[172],"reductions":[174],"runtime":[177],"per-node":[179],"memory":[180],"requirements,":[181],"when":[182],"making":[183],"cluster.":[188],"CONCLUSIONS:":[189],"Our":[190],"study":[191],"shows":[192],"MapReduce-based":[194],"has":[196],"great":[197],"potential":[198],"distributing":[200],"challenging":[201],"sequencing":[202],"problems,":[203],"without":[204],"loss":[205],"accuracy.":[207],"Although":[208],"focussed":[211],"package,":[215],"propose":[217],"such":[219],"useful":[223],"initial":[224],"other":[227],"pipelines.":[229]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}