{"id":"https://openalex.org/W2747052100","doi":"https://doi.org/10.1145/3107411.3107491","title":"Distributed Memory Partitioning of High-Throughput Sequencing Datasets for Enabling Parallel Genomics Analyses","display_name":"Distributed Memory Partitioning of High-Throughput Sequencing Datasets for Enabling Parallel Genomics Analyses","publication_year":2017,"publication_date":"2017-08-20","ids":{"openalex":"https://openalex.org/W2747052100","doi":"https://doi.org/10.1145/3107411.3107491","mag":"2747052100"},"language":"en","primary_location":{"id":"doi:10.1145/3107411.3107491","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3107411.3107491","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th ACM International Conference on Bioinformatics, Computational Biology,and Health Informatics","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/A5051155185","display_name":"Nagakishore Jammula","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nagakishore Jammula","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070968071","display_name":"Sriram P. Chockalingam","orcid":"https://orcid.org/0000-0003-1358-7691"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sriram P. Chockalingam","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074347913","display_name":"Srinivas Aluru","orcid":"https://orcid.org/0000-0003-4279-469X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Srinivas Aluru","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5051155185"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.319,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.58125705,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"417","last_page":"424"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9997000098228455,"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":0.9997000098228455,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9991000294685364,"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/T10885","display_name":"Gene expression and cancer classification","score":0.9869999885559082,"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/de-bruijn-graph","display_name":"De Bruijn graph","score":0.8652893900871277},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8190883994102478},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5931999087333679},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.5593492984771729},{"id":"https://openalex.org/keywords/graph-partition","display_name":"Graph partition","score":0.5591543912887573},{"id":"https://openalex.org/keywords/metagenomics","display_name":"Metagenomics","score":0.5474026203155518},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5339974164962769},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.48843660950660706},{"id":"https://openalex.org/keywords/de-bruijn-sequence","display_name":"De Bruijn sequence","score":0.452729195356369},{"id":"https://openalex.org/keywords/genomics","display_name":"Genomics","score":0.4335525929927826},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4136314392089844},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.41085439920425415},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2708025574684143},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.1815079152584076},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13629069924354553},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.11395400762557983},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.08050131797790527}],"concepts":[{"id":"https://openalex.org/C20218877","wikidata":"https://www.wikidata.org/wiki/Q3066095","display_name":"De Bruijn graph","level":3,"score":0.8652893900871277},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8190883994102478},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5931999087333679},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.5593492984771729},{"id":"https://openalex.org/C48903430","wikidata":"https://www.wikidata.org/wiki/Q491370","display_name":"Graph partition","level":3,"score":0.5591543912887573},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.5474026203155518},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5339974164962769},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.48843660950660706},{"id":"https://openalex.org/C170320093","wikidata":"https://www.wikidata.org/wiki/Q1953457","display_name":"De Bruijn sequence","level":2,"score":0.452729195356369},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.4335525929927826},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4136314392089844},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.41085439920425415},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2708025574684143},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.1815079152584076},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13629069924354553},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.11395400762557983},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.08050131797790527},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3107411.3107491","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3107411.3107491","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th ACM International Conference on Bioinformatics, Computational Biology,and Health Informatics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2567864256","display_name":null,"funder_award_id":"CCF-1360593","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1577822803","https://openalex.org/W1850079471","https://openalex.org/W1910515323","https://openalex.org/W1982633903","https://openalex.org/W2102532874","https://openalex.org/W2103441770","https://openalex.org/W2104677379","https://openalex.org/W2118953734","https://openalex.org/W2121984048","https://openalex.org/W2125804745","https://openalex.org/W2163830511","https://openalex.org/W2171963266","https://openalex.org/W2302703011","https://openalex.org/W2396849069","https://openalex.org/W2557391416","https://openalex.org/W2963783227"],"related_works":["https://openalex.org/W2562683361","https://openalex.org/W3087469195","https://openalex.org/W2354744388","https://openalex.org/W3125399386","https://openalex.org/W2949121831","https://openalex.org/W3215786367","https://openalex.org/W1908987670","https://openalex.org/W2756186577","https://openalex.org/W2735897904","https://openalex.org/W2107854630"],"abstract_inverted_index":{"State-of-the-art":[0],"high-throughput":[1],"sequencing":[2],"instruments":[3],"decipher":[4],"in":[5,34,72,96],"excess":[6],"of":[7,30,47,82,104,107,136,140],"a":[8,27,64,105,130],"billion":[9],"short":[10],"genomic":[11],"fragments":[12],"per":[13],"run.":[14],"The":[15],"output":[16],"sequences":[17],"are":[18,53],"referred":[19],"to":[20,43,74,117],"as":[21,37,113],"'reads'.":[22],"These":[23],"read":[24,49,70,85],"datasets":[25,71],"facilitate":[26,75],"wide":[28],"variety":[29],"analyses":[31,52],"with":[32],"applications":[33,100],"areas":[35],"such":[36,51,112],"genomics,":[38],"metagenomics,":[39],"and":[40,56,89,142],"transcriptomics.":[41],"Owing":[42],"the":[44,48,80,84,91,108,120,134,137],"large":[45],"size":[46],"datasets,":[50,86],"often":[54],"compute":[55],"memory":[57],"intensive.":[58],"In":[59,126],"this":[60],"paper,":[61],"we":[62,87,128],"present":[63],"parallel":[65,77],"algorithm":[66,146],"for":[67,132],"partitioning":[68,83],"large-scale":[69],"order":[73],"distributed-memory":[76],"analyses.":[78],"During":[79],"process":[81],"construct":[88],"partition":[90],"associated":[92],"de":[93,109,114,122],"Bruijn":[94,110,123],"graph":[95,124],"parallel.":[97],"This":[98],"allows":[99],"that":[101,144],"make":[102],"use":[103],"variant":[106],"graph,":[111],"novo":[115],"assembly,":[116],"directly":[118],"leverage":[119],"generated":[121,138],"partitions.":[125,150],"addition,":[127],"propose":[129],"mechanism":[131],"evaluating":[133],"quality":[135,149],"partitions":[139],"reads":[141],"demonstrate":[143],"our":[145],"produces":[147],"high":[148],"Our":[151],"implementation":[152],"is":[153],"available":[154],"at":[155],"github.com/ParBLiSS/read_partitioning.":[156]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}