{"id":"https://openalex.org/W2612420148","doi":"https://doi.org/10.1145/3070607.3070615","title":"Bi-Dimensional Binning for Big Genomic Datasets","display_name":"Bi-Dimensional Binning for Big Genomic Datasets","publication_year":2017,"publication_date":"2017-05-08","ids":{"openalex":"https://openalex.org/W2612420148","doi":"https://doi.org/10.1145/3070607.3070615","mag":"2612420148"},"language":"en","primary_location":{"id":"doi:10.1145/3070607.3070615","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3070607.3070615","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th ACM SIGMOD Workshop on Algorithms and Systems for MapReduce and Beyond","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/11311/1050053","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052193529","display_name":"Simone Cattani","orcid":null},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Simone Cattani","raw_affiliation_strings":["Politecnico di Milano, Milan, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048332811","display_name":"Stefano Ceri","orcid":"https://orcid.org/0000-0003-0671-2415"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Stefano Ceri","raw_affiliation_strings":["Politecnico di Milano, Milan, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016603624","display_name":"Abdulrahman Kaitoua","orcid":"https://orcid.org/0000-0002-0244-9691"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Abdulrahman Kaitoua","raw_affiliation_strings":["Politecnico di Milano, Milan, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074094001","display_name":"Pietro Pinoli","orcid":"https://orcid.org/0000-0001-9786-2851"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Pietro Pinoli","raw_affiliation_strings":["Politecnico di Milano, Milan, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I93860229"],"apc_list":null,"apc_paid":null,"fwci":0.4153,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.61292334,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"31","issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9987999796867371,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9987999796867371,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9955000281333923,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.991599977016449,"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/spark","display_name":"SPARK (programming language)","score":0.8838011026382446},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.8244624733924866},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7946673631668091},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.6005858182907104},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5275604128837585},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4036552309989929},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.11098882555961609}],"concepts":[{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.8838011026382446},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8244624733924866},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7946673631668091},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.6005858182907104},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5275604128837585},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4036552309989929},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.11098882555961609},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3070607.3070615","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3070607.3070615","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th ACM SIGMOD Workshop on Algorithms and Systems for MapReduce and Beyond","raw_type":"proceedings-article"},{"id":"pmh:oai:re.public.polimi.it:11311/1050053","is_oa":true,"landing_page_url":"http://hdl.handle.net/11311/1050053","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:re.public.polimi.it:11311/1050053","is_oa":true,"landing_page_url":"http://hdl.handle.net/11311/1050053","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2142680014","https://openalex.org/W2397862861","https://openalex.org/W2407906562","https://openalex.org/W2444247778","https://openalex.org/W2507333165","https://openalex.org/W2590972148","https://openalex.org/W3197904229"],"related_works":["https://openalex.org/W2766461310","https://openalex.org/W4247566972","https://openalex.org/W4388692845","https://openalex.org/W3202731209","https://openalex.org/W3211874991","https://openalex.org/W2844620057","https://openalex.org/W2610007503","https://openalex.org/W4308507533","https://openalex.org/W2407107767","https://openalex.org/W2901787049"],"abstract_inverted_index":{"Binning":[0],"the":[1,21,47,69],"genome":[2],"is":[3,82],"used":[4,64],"in":[5],"order":[6],"to":[7,88],"parallelize":[8],"big":[9],"data":[10],"operations":[11],"upon":[12],"regions.":[13,37],"In":[14,38],"this":[15],"extended":[16,87],"abstract,":[17],"we":[18,40],"comparatively":[19],"evaluate":[20],"performance":[22],"and":[23,27,57,67,73,84,91],"scalability":[24],"of":[25,33,35,54,79],"Spark":[26],"SciDB":[28,66,72],"implementations":[29],"over":[30],"datasets":[31],"consisting":[32],"billions":[34],"genomic":[36],"particular,":[39],"introduce":[41],"an":[42],"original":[43],"method":[44],"for":[45],"binning":[46,63,81],"genome,":[48],"i.e.":[49],"partitioning":[50],"it":[51,60],"into":[52],"sections":[53],"small":[55],"sizes,":[56],"show":[58],"that":[59],"outperforms":[61],"conventional":[62],"by":[65],"closes":[68],"gap":[70],"between":[71],"a":[74],"Spark-based":[75],"implementation.":[76],"The":[77],"concept":[78],"bi-dimensional":[80],"new":[83],"can":[85],"be":[86],"other":[89],"systems":[90],"technologies.":[92]},"counts_by_year":[{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
