{"id":"https://openalex.org/W2949216712","doi":"https://doi.org/10.1109/bhi.2018.8333418","title":"Kafka interfaces for composable streaming genomics pipelines","display_name":"Kafka interfaces for composable streaming genomics pipelines","publication_year":2018,"publication_date":"2018-03-01","ids":{"openalex":"https://openalex.org/W2949216712","doi":"https://doi.org/10.1109/bhi.2018.8333418","mag":"2949216712"},"language":"en","primary_location":{"id":"doi:10.1109/bhi.2018.8333418","doi":"https://doi.org/10.1109/bhi.2018.8333418","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bhi.2018.8333418","pdf_url":null,"source":{"id":"https://openalex.org/S4393918972","display_name":"IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI ...)","issn_l":"2641-3590","issn":["2641-3590"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE EMBS International Conference on Biomedical &amp; Health Informatics (BHI)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2017/08/29/182030.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010522931","display_name":"Francesco Versaci","orcid":"https://orcid.org/0000-0003-2513-3590","observed_orcids":["https://orcid.org/0000-0003-2513-3590"]},"institutions":[{"id":"https://openalex.org/I2800759272","display_name":"Center for Advanced Studies Research and Development in Sardinia","ror":"https://ror.org/03jdxdk20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2800759272"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Francesco Versaci","raw_affiliation_strings":["Distributed Computing Group CRS4 Pula","Distributed Computing Group, Pula, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Distributed Computing Group CRS4 Pula","institution_ids":["https://openalex.org/I2800759272"]},{"raw_affiliation_string":"Distributed Computing Group, Pula, Italy","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047833562","display_name":"Luca Pireddu","orcid":"https://orcid.org/0000-0002-4663-5613","observed_orcids":["https://orcid.org/0000-0002-4663-5613"]},"institutions":[{"id":"https://openalex.org/I2800759272","display_name":"Center for Advanced Studies Research and Development in Sardinia","ror":"https://ror.org/03jdxdk20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2800759272"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Luca Pireddu","raw_affiliation_strings":["Distributed Computing Group CRS4 Pula","Distributed Computing Group, Pula, Italy"],"raw_orcid":"https://orcid.org/0000-0002-4663-5613","affiliations":[{"raw_affiliation_string":"Distributed Computing Group CRS4 Pula","institution_ids":["https://openalex.org/I2800759272"]},{"raw_affiliation_string":"Distributed Computing Group, Pula, Italy","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073829656","display_name":"Gianluigi Zanetti","orcid":"https://orcid.org/0000-0003-1683-7350","observed_orcids":["https://orcid.org/0000-0003-1683-7350"]},"institutions":[{"id":"https://openalex.org/I2800759272","display_name":"Center for Advanced Studies Research and Development in Sardinia","ror":"https://ror.org/03jdxdk20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2800759272"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Gianluigi Zanetti","raw_affiliation_strings":["Distributed Computing Group CRS4 Pula","Distributed Computing Group, Pula, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Distributed Computing Group CRS4 Pula","institution_ids":["https://openalex.org/I2800759272"]},{"raw_affiliation_string":"Distributed Computing Group, Pula, Italy","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5010522931","https://openalex.org/A5047833562","https://openalex.org/A5073829656"],"corresponding_institution_ids":["https://openalex.org/I2800759272"],"apc_list":null,"apc_paid":null,"fwci":3.6238,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.93731563,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"38","issue":null,"first_page":"259","last_page":"262"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.6352999806404114,"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"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.6352999806404114,"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"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.23520000278949738,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.050700001418590546,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/apache-kafka","display_name":"Apache Kafka","score":0.7919999957084656},{"id":"https://openalex.org/keywords/stream-processing","display_name":"stream processing","score":0.9449999928474426},{"id":"https://openalex.org/keywords/genomic-data-processing","display_name":"genomic data processing","score":0.6660000085830688},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"fault tolerance","score":0.6499999761581421},{"id":"https://openalex.org/keywords/scalability","display_name":"scalability","score":0.6480000019073486},{"id":"https://openalex.org/keywords/yarn","display_name":"yarn","score":0.7160000205039978},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"sequence alignment","score":0.8050000071525574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8120068311691284},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6856119632720947},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5894749760627747},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.5720638036727905},{"id":"https://openalex.org/C107027933","wikidata":"https://www.wikidata.org/wiki/Q2006448","display_name":"Stream processing","level":2,"score":0.5153067111968994},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5117756724357605},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.491354376077652},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.47237470746040344},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.470704048871994},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.45475709438323975},{"id":"https://openalex.org/C2778814252","wikidata":"https://www.wikidata.org/wiki/Q5156715","display_name":"Composability","level":2,"score":0.44976550340652466},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26715677976608276},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.21926841139793396},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1577821969985962},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bhi.2018.8333418","doi":"https://doi.org/10.1109/bhi.2018.8333418","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bhi.2018.8333418","pdf_url":null,"source":{"id":"https://openalex.org/S4393918972","display_name":"IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI ...)","issn_l":"2641-3590","issn":["2641-3590"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE EMBS International Conference on Biomedical &amp; Health Informatics (BHI)","raw_type":"proceedings-article"},{"id":"doi:10.1101/182030","doi":"https://doi.org/10.1101/182030","is_oa":true,"landing_page_url":"https://doi.org/10.1101/182030","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2017/08/29/182030.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.1101/182030","doi":"https://doi.org/10.1101/182030","is_oa":true,"landing_page_url":"https://doi.org/10.1101/182030","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2017/08/29/182030.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2949216712.pdf","grobid_xml":"https://content.openalex.org/works/W2949216712.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1904861952","https://openalex.org/W1967841763","https://openalex.org/W1971962952","https://openalex.org/W1976821017","https://openalex.org/W1977046764","https://openalex.org/W1981509058","https://openalex.org/W1987370132","https://openalex.org/W1990073900","https://openalex.org/W2012016911","https://openalex.org/W2023969503","https://openalex.org/W2038492487","https://openalex.org/W2061680337","https://openalex.org/W2061906497","https://openalex.org/W2063220786","https://openalex.org/W2065853059","https://openalex.org/W2081930221","https://openalex.org/W2093931624","https://openalex.org/W2095680943","https://openalex.org/W2098380237","https://openalex.org/W2104846587","https://openalex.org/W2108234281","https://openalex.org/W2119180969","https://openalex.org/W2131229759","https://openalex.org/W2153805608","https://openalex.org/W2158336776","https://openalex.org/W2159670728","https://openalex.org/W2160363604","https://openalex.org/W2169594074","https://openalex.org/W2189371416","https://openalex.org/W2190569576","https://openalex.org/W2290761674","https://openalex.org/W2476433236","https://openalex.org/W2572878993","https://openalex.org/W2613297071","https://openalex.org/W2913854892","https://openalex.org/W2949811559","https://openalex.org/W4394666350"],"related_works":["https://openalex.org/W4231279042","https://openalex.org/W2156288405","https://openalex.org/W2063220786","https://openalex.org/W2346145536","https://openalex.org/W2949811559","https://openalex.org/W2794514292","https://openalex.org/W2782907190","https://openalex.org/W4249085588","https://openalex.org/W2189371416","https://openalex.org/W6901935247"],"abstract_inverted_index":{"Abstract":[0],"Modern":[1],"sequencing":[2],"machines":[3],"produce":[4],"order":[5,117],"of":[6,9,37,44,47,62,73,93],"a":[7,19,28],"terabyte":[8],"data":[10,48,140],"per":[11],"day,":[12],"which":[13,33],"need":[14],"subsequently":[15],"to":[16,59,76,118,143],"go":[17],"through":[18,113],"complex":[20],"processing":[21,96],"pipeline.":[22],"The":[23,131],"standard":[24],"workflow":[25],"begins":[26],"with":[27],"few":[29],"independent,":[30],"shared-memory":[31],"tools,":[32],"communicate":[34],"by":[35],"means":[36],"intermediate":[38],"files.":[39],"Given":[40],"the":[41,45,71,78,90,94,126],"constant":[42],"increase":[43],"amount":[46],"produced,":[49],"this":[50,67],"approach":[51],"is":[52,134],"proving":[53],"more":[54,56],"and":[55,64,84,100,104,106,123,141],"unmanageable,":[57],"due":[58],"its":[60,82,86],"lack":[61],"robustness":[63],"scalability.":[65],"In":[66],"work":[68],"we":[69,107],"propose":[70],"adoption":[72],"stream":[74],"computing":[75],"simplify":[77],"genomic":[79,95],"pipeline,":[80],"boost":[81],"performance":[83],"improve":[85],"fault-tolerance.":[87],"We":[88],"decompose":[89],"first":[91],"steps":[92],"in":[97,116,125],"two":[98],"distinct":[99],"specialized":[101],"modules":[102],"(preprocessing":[103],"alignment)":[105],"loosely":[108],"compose":[109],"them":[110],"via":[111],"communication":[112],"Kafka":[114],"streams,":[115],"allow":[119],"for":[120],"easy":[121],"composability":[122],"integration":[124],"already":[127],"existing":[128],"Hadoop-based":[129],"pipelines.":[130],"proposed":[132],"solution":[133],"then":[135],"experimentally":[136],"validated":[137],"on":[138],"real":[139],"shown":[142],"scale":[144],"almost":[145],"linearly.":[146]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1}],"updated_date":"2026-10-27T15:51:10.671819","created_date":"2019-06-27T00:00:00"}
