{"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","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bhi.2018.8333418","pdf_url":null,"source":null,"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"},"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/A5010522931","display_name":"Francesco Versaci","orcid":"https://orcid.org/0000-0003-2513-3590"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Francesco Versaci","raw_affiliation_strings":["Distributed Computing Group, Pula, Italy"],"raw_orcid":null,"affiliations":[{"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"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luca Pireddu","raw_affiliation_strings":["Distributed Computing Group, Pula, Italy"],"raw_orcid":null,"affiliations":[{"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"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gianluigi Zanetti","raw_affiliation_strings":["Distributed Computing Group, Pula, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Distributed Computing Group, Pula, Italy","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3345,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.59729511,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"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/T11407","display_name":"Innovative Microfluidic and Catalytic Techniques Innovation","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11407","display_name":"Innovative Microfluidic and Catalytic Techniques Innovation","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9943000078201294,"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/T11287","display_name":"Cancer Genomics and Diagnostics","score":0.9825999736785889,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"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":0.8120068311691284},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6856119632720947},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5894749760627747},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.5720638036727905},{"id":"https://openalex.org/keywords/stream-processing","display_name":"Stream processing","score":0.5153067111968994},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5117756724357605},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.491354376077652},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.47237470746040344},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.470704048871994},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.45475709438323975},{"id":"https://openalex.org/keywords/composability","display_name":"Composability","score":0.44976550340652466},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.26715677976608276},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.21926841139793396},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1577821969985962}],"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":1,"locations":[{"id":"doi:10.1109/bhi.2018.8333418","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bhi.2018.8333418","pdf_url":null,"source":null,"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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1971962952","https://openalex.org/W1976821017","https://openalex.org/W2012016911","https://openalex.org/W2063220786","https://openalex.org/W2093931624","https://openalex.org/W2095680943","https://openalex.org/W2108234281","https://openalex.org/W2119180969","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/W2613297071","https://openalex.org/W2913854892","https://openalex.org/W2949811559","https://openalex.org/W4394666350","https://openalex.org/W6687031098"],"related_works":["https://openalex.org/W2572716084","https://openalex.org/W2082671441","https://openalex.org/W2605169415","https://openalex.org/W180351855","https://openalex.org/W2538312128","https://openalex.org/W2904574017","https://openalex.org/W3113817755","https://openalex.org/W2971589461","https://openalex.org/W2794178276","https://openalex.org/W2529735807"],"abstract_inverted_index":{"Modern":[0],"sequencing":[1,56],"machines":[2],"produce":[3],"order":[4,121],"of":[5,8,36,42,55,60,76,97],"a":[6,18,27],"terabyte":[7],"data":[9,143],"per":[10],"day,":[11],"which":[12,32],"need":[13],"subsequently":[14],"to":[15,50,79,122,146],"go":[16],"through":[17,117],"complex":[19],"processing":[20,100],"pipeline.":[21],"The":[22,134],"conventional":[23],"workflow":[24],"begins":[25],"with":[26],"few":[28],"independent,":[29],"shared-memory":[30],"tools,":[31],"communicate":[33],"by":[34],"means":[35],"intermediate":[37],"files.":[38],"Given":[39],"its":[40,86,90],"lack":[41],"robustness":[43],"and":[44,88,104,108,110,127,144],"scalability,":[45],"this":[46,70],"approach":[47],"is":[48,137],"ill-suited":[49],"exploiting":[51],"the":[52,58,67,74,81,94,98,130],"full":[53],"potential":[54],"in":[57,101,120,129],"context":[59],"healthcare,":[61],"where":[62],"large-scale,":[63],"population-wide":[64],"applications":[65],"are":[66],"norm.":[68],"In":[69],"work":[71],"we":[72,111],"propose":[73],"adoption":[75],"stream":[77],"computing":[78],"simplify":[80],"genomic":[82,99],"resequencing":[83],"pipeline,":[84],"boosting":[85],"performance":[87],"improving":[89],"fault-tolerance.":[91],"We":[92],"decompose":[93],"first":[95],"steps":[96],"two":[102],"distinct":[103],"specialized":[105],"modules":[106],"(preprocessing":[107],"alignment)":[109],"loosely":[112],"compose":[113],"them":[114],"via":[115],"communication":[116],"Kafka":[118],"streams,":[119],"allow":[123],"for":[124],"easy":[125],"composability":[126],"integration":[128],"already-existing":[131],"YARN-based":[132],"pipelines.":[133],"proposed":[135],"solution":[136],"then":[138],"experimentally":[139],"validated":[140],"on":[141],"real":[142],"shown":[145],"scale":[147],"almost":[148],"linearly.":[149]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
