{"id":"https://openalex.org/W2771381340","doi":"https://doi.org/10.1093/bioinformatics/btx808","title":"Analyzing large scale genomic data on the cloud with Sparkhit","display_name":"Analyzing large scale genomic data on the cloud with Sparkhit","publication_year":2017,"publication_date":"2017-12-14","ids":{"openalex":"https://openalex.org/W2771381340","doi":"https://doi.org/10.1093/bioinformatics/btx808","mag":"2771381340","pmid":"https://pubmed.ncbi.nlm.nih.gov/29253074"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btx808","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btx808","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/34/9/1457/25120863/btx808.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"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/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/34/9/1457/25120863/btx808.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026988762","display_name":"Liren Huang","orcid":"https://orcid.org/0000-0003-4729-837X"},"institutions":[{"id":"https://openalex.org/I20121455","display_name":"Bielefeld University","ror":"https://ror.org/02hpadn98","country_code":"DE","type":"education","lineage":["https://openalex.org/I20121455"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Liren Huang","raw_affiliation_strings":["Center for Biotechnology \u2013 CeBiTec, Bielefeld University, Bielefeld, Germany","Computational Methods for the Analysis of the Diversity and Dynamics of Genomes, Bielefeld University, Bielefeld, Germany","Faculty of Technology, Bielefeld University, Bielefeld, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Biotechnology \u2013 CeBiTec, Bielefeld University, Bielefeld, Germany","institution_ids":["https://openalex.org/I20121455"]},{"raw_affiliation_string":"Computational Methods for the Analysis of the Diversity and Dynamics of Genomes, Bielefeld University, Bielefeld, Germany","institution_ids":["https://openalex.org/I20121455"]},{"raw_affiliation_string":"Faculty of Technology, Bielefeld University, Bielefeld, Germany","institution_ids":["https://openalex.org/I20121455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103015384","display_name":"Jan Walters Kruger","orcid":"https://orcid.org/0009-0006-4245-1653"},"institutions":[{"id":"https://openalex.org/I20121455","display_name":"Bielefeld University","ror":"https://ror.org/02hpadn98","country_code":"DE","type":"education","lineage":["https://openalex.org/I20121455"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Kr\u00fcger","raw_affiliation_strings":["Center for Biotechnology \u2013 CeBiTec, Bielefeld University, Bielefeld, Germany","Faculty of Technology, Bielefeld University, Bielefeld, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Biotechnology \u2013 CeBiTec, Bielefeld University, Bielefeld, Germany","institution_ids":["https://openalex.org/I20121455"]},{"raw_affiliation_string":"Faculty of Technology, Bielefeld University, Bielefeld, Germany","institution_ids":["https://openalex.org/I20121455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071017957","display_name":"Alexander Sczyrba","orcid":"https://orcid.org/0000-0002-4405-3847"},"institutions":[{"id":"https://openalex.org/I20121455","display_name":"Bielefeld University","ror":"https://ror.org/02hpadn98","country_code":"DE","type":"education","lineage":["https://openalex.org/I20121455"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Alexander Sczyrba","raw_affiliation_strings":["Center for Biotechnology \u2013 CeBiTec, Bielefeld University, Bielefeld, Germany","Computational Methods for the Analysis of the Diversity and Dynamics of Genomes, Bielefeld University, Bielefeld, Germany","Faculty of Technology, Bielefeld University, Bielefeld, Germany"],"raw_orcid":"https://orcid.org/0000-0002-4405-3847","affiliations":[{"raw_affiliation_string":"Center for Biotechnology \u2013 CeBiTec, Bielefeld University, Bielefeld, Germany","institution_ids":["https://openalex.org/I20121455"]},{"raw_affiliation_string":"Computational Methods for the Analysis of the Diversity and Dynamics of Genomes, Bielefeld University, Bielefeld, Germany","institution_ids":["https://openalex.org/I20121455"]},{"raw_affiliation_string":"Faculty of Technology, Bielefeld University, Bielefeld, Germany","institution_ids":["https://openalex.org/I20121455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5071017957"],"corresponding_institution_ids":["https://openalex.org/I20121455"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":0.811,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.71561253,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"34","issue":"9","first_page":"1457","last_page":"1465"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.29330000281333923,"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":0.29330000281333923,"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":0.14409999549388885,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.13079999387264252,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8129884004592896},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.7944722175598145},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6800287961959839},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6653404831886292},{"id":"https://openalex.org/keywords/upload","display_name":"Upload","score":0.6614476442337036},{"id":"https://openalex.org/keywords/terabyte","display_name":"Terabyte","score":0.598530113697052},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5346614122390747},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5089874267578125},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.4845834970474243},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4404018223285675},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42539355158805847},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3833633065223694},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.35859477519989014},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2798992395401001}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8129884004592896},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.7944722175598145},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6800287961959839},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6653404831886292},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.6614476442337036},{"id":"https://openalex.org/C199683683","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Terabyte","level":2,"score":0.598530113697052},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5346614122390747},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5089874267578125},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4845834970474243},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4404018223285675},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42539355158805847},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3833633065223694},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.35859477519989014},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2798992395401001},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D064307","descriptor_name":"Microbiota","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D064307","descriptor_name":"Microbiota","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D064307","descriptor_name":"Microbiota","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1093/bioinformatics/btx808","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btx808","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/34/9/1457/25120863/btx808.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"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/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:29253074","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29253074","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:europepmc.org:4855652","is_oa":false,"landing_page_url":"http://europepmc.org/pmc/articles/PMC5925781","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:pub.librecat.org:2915890","is_oa":false,"landing_page_url":"https://pub.uni-bielefeld.de/record/2915890","pdf_url":null,"source":{"id":"https://openalex.org/S4306401671","display_name":"PUB \u2013 Publications at Bielefeld University (Bielefeld University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I20121455","host_organization_name":"Bielefeld University","host_organization_lineage":["https://openalex.org/I20121455"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Huang L, Kr\u00fcger J, Sczyrba A. Analyzing large scale genomic data on the cloud with Sparkhit. &lt;em&gt;Bioinformatics&lt;/em&gt;. 2018;34(9):1457-1465.","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pubmedcentral.nih.gov:5925781","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5925781","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"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":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btx808","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btx808","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/34/9/1457/25120863/btx808.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"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/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.46000000834465027,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G2329091277","display_name":null,"funder_award_id":"GRK 1906/1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G2784112","display_name":null,"funder_award_id":"1906/1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G4580630416","display_name":null,"funder_award_id":"GRK 1906","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320308022","display_name":"California Department of Fish and Game","ror":"https://ror.org/02v6w2r95"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2771381340.pdf","grobid_xml":"https://content.openalex.org/works/W2771381340.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1513515886","https://openalex.org/W1966822396","https://openalex.org/W1990073900","https://openalex.org/W2011411346","https://openalex.org/W2023116290","https://openalex.org/W2033292629","https://openalex.org/W2081612620","https://openalex.org/W2082447166","https://openalex.org/W2093830129","https://openalex.org/W2103441770","https://openalex.org/W2104549677","https://openalex.org/W2108234281","https://openalex.org/W2109103692","https://openalex.org/W2119180969","https://openalex.org/W2121762798","https://openalex.org/W2139760555","https://openalex.org/W2147733682","https://openalex.org/W2157612734","https://openalex.org/W2159670728","https://openalex.org/W2159954944","https://openalex.org/W2166123725","https://openalex.org/W2167987829","https://openalex.org/W2170551349","https://openalex.org/W2171571559","https://openalex.org/W2173213060","https://openalex.org/W2184070407","https://openalex.org/W2296335794","https://openalex.org/W2303542186","https://openalex.org/W2323326409","https://openalex.org/W2398924165","https://openalex.org/W2437388877","https://openalex.org/W2508929473","https://openalex.org/W2568237575","https://openalex.org/W6670817290","https://openalex.org/W6682035847","https://openalex.org/W6697144307"],"related_works":["https://openalex.org/W2766461310","https://openalex.org/W4247566972","https://openalex.org/W2936171637","https://openalex.org/W1586214342","https://openalex.org/W4388692845","https://openalex.org/W3091344841","https://openalex.org/W2260589296","https://openalex.org/W3202731209","https://openalex.org/W3157828377","https://openalex.org/W3211874991"],"abstract_inverted_index":{"Motivation:":[0],"The":[1],"increasing":[2],"amount":[3],"of":[4,31,48,65,75,111,128,159],"next-generation":[5],"sequencing":[6,144],"data":[7,105,112,132,145,179],"poses":[8],"a":[9,58,73],"fundamental":[10],"challenge":[11],"on":[12,63,94,104,137],"large":[13,46,157],"scale":[14],"genomic":[15,115],"analytics.":[16],"Existing":[17],"tools":[18,33],"use":[19],"different":[20],"distributed":[21,59],"computational":[22],"platforms":[23],"to":[24,154],"scale-out":[25],"bioinformatics":[26,60],"workloads.":[27],"However,":[28],"the":[29,66,82,118,125,138],"scalability":[30],"these":[32,52],"is":[34,79,169],"not":[35],"efficient.":[36],"Moreover,":[37],"they":[38],"have":[39,55],"heavy":[40],"run":[41,126],"time":[42],"overheads":[43],"when":[44],"pre-processing":[45],"amounts":[47,158],"data.":[49,164],"To":[50],"address":[51],"limitations,":[53],"we":[54],"developed":[56],"Sparkhit:":[57],"framework":[61],"built":[62],"top":[64],"Apache":[67],"Spark":[68,83],"platform.":[69],"Results:":[70],"Sparkhit":[71,168],"integrates":[72],"variety":[74],"analytical":[76],"methods.":[77],"It":[78,87],"implemented":[80],"in":[81,117,120,148],"extended":[84],"MapReduce":[85],"model.":[86],"runs":[88],"92-157":[89],"times":[90,100,127],"faster":[91,101],"than":[92,102],"MetaSpark":[93],"metagenomic":[95],"fragment":[96],"recruitment":[97],"and":[98,131,166],"18-32":[99],"Crossbow":[103],"pre-processing.":[106],"We":[107],"analyzed":[108],"100":[109],"terabytes":[110],"across":[113],"four":[114],"projects":[116],"cloud":[119],"21":[121],"h,":[122,150],"which":[123],"includes":[124],"cluster":[129],"deployment":[130],"downloading.":[133],"Furthermore,":[134],"our":[135],"application":[136],"entire":[139],"Human":[140],"Microbiome":[141],"Project":[142],"shotgun":[143],"was":[146],"completed":[147],"2":[149],"presenting":[151],"an":[152],"approach":[153],"easily":[155],"associate":[156],"public":[160],"datasets":[161],"with":[162],"reference":[163],"Availability":[165],"implementation:":[167],"freely":[170],"available":[171,181],"at:":[172],"https://rhinempi.github.io/sparkhit/.":[173],"Contact:":[174],"asczyrba@cebitec.uni-bielefeld.de.":[175],"Supplementary":[176,178],"information:":[177],"are":[180],"at":[182],"Bioinformatics":[183],"online.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}
