{"id":"https://openalex.org/W2213505663","doi":"https://doi.org/10.1109/bigdata.2015.7363853","title":"Spaler: Spark and GraphX based de novo genome assembler","display_name":"Spaler: Spark and GraphX based de novo genome assembler","publication_year":2015,"publication_date":"2015-10-01","ids":{"openalex":"https://openalex.org/W2213505663","doi":"https://doi.org/10.1109/bigdata.2015.7363853","mag":"2213505663"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2015.7363853","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7363853","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Big Data (Big Data)","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/A5000436299","display_name":"Anas Abu-Doleh","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Anas Abu-Doleh","raw_affiliation_strings":["Dept. of Electrical and Computer Engineering, Ohio State University"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026046737","display_name":"\u00dcmit V. \u00c7ataly\u00fcrek","orcid":"https://orcid.org/0000-0002-5625-3758"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Umit V. Catalyurek","raw_affiliation_strings":["Dept. of Biomedical Informatics, Ohio State University"],"affiliations":[{"raw_affiliation_string":"Dept. of Biomedical Informatics, Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5000436299"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":2.0421,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.87112253,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1013","last_page":"1018"},"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":0.9854999780654907,"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/T10434","display_name":"Chromosomal and Genetic Variations","score":0.9839000105857849,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"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":0.7758301496505737},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7524683475494385},{"id":"https://openalex.org/keywords/sequence-assembly","display_name":"Sequence assembly","score":0.6846343278884888},{"id":"https://openalex.org/keywords/swap","display_name":"Swap (finance)","score":0.6629701256752014},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.6398070454597473},{"id":"https://openalex.org/keywords/de-bruijn-sequence","display_name":"De Bruijn sequence","score":0.6019704341888428},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.5846794843673706},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4390062093734741},{"id":"https://openalex.org/keywords/k-mer","display_name":"k-mer","score":0.41550901532173157},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.40133213996887207},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3866894841194153},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2713072896003723},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.20836421847343445},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.15096920728683472},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1498168706893921},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.1067294180393219}],"concepts":[{"id":"https://openalex.org/C20218877","wikidata":"https://www.wikidata.org/wiki/Q3066095","display_name":"De Bruijn graph","level":3,"score":0.7758301496505737},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7524683475494385},{"id":"https://openalex.org/C18949551","wikidata":"https://www.wikidata.org/wiki/Q740578","display_name":"Sequence assembly","level":5,"score":0.6846343278884888},{"id":"https://openalex.org/C99821215","wikidata":"https://www.wikidata.org/wiki/Q1136583","display_name":"Swap (finance)","level":2,"score":0.6629701256752014},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.6398070454597473},{"id":"https://openalex.org/C170320093","wikidata":"https://www.wikidata.org/wiki/Q1953457","display_name":"De Bruijn sequence","level":2,"score":0.6019704341888428},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5846794843673706},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4390062093734741},{"id":"https://openalex.org/C2279292","wikidata":"https://www.wikidata.org/wiki/Q6322851","display_name":"k-mer","level":4,"score":0.41550901532173157},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.40133213996887207},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3866894841194153},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2713072896003723},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.20836421847343445},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.15096920728683472},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1498168706893921},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.1067294180393219},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2015.7363853","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7363853","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5199999809265137}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309815","display_name":"Qatar Foundation","ror":"https://ror.org/01cawbq05"},{"id":"https://openalex.org/F4320332753","display_name":"Qatar National Research Fund","ror":"https://ror.org/01svaqq28"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1966822396","https://openalex.org/W2033292629","https://openalex.org/W2041391522","https://openalex.org/W2055503200","https://openalex.org/W2060380866","https://openalex.org/W2095267560","https://openalex.org/W2104846587","https://openalex.org/W2107772251","https://openalex.org/W2122910323","https://openalex.org/W2127651281","https://openalex.org/W2127768708","https://openalex.org/W2136651963","https://openalex.org/W2152073175","https://openalex.org/W2154375983","https://openalex.org/W2171475724"],"related_works":["https://openalex.org/W2120956621","https://openalex.org/W2915362964","https://openalex.org/W2991626973","https://openalex.org/W3215786367","https://openalex.org/W3205360317","https://openalex.org/W4318940746","https://openalex.org/W2562683361","https://openalex.org/W3200242814","https://openalex.org/W4387083702","https://openalex.org/W2133531097"],"abstract_inverted_index":{"The":[0,98],"recent":[1],"advancements":[2],"in":[3,92,114],"high-throughput":[4],"genome":[5,51],"sequencing":[6],"technologies":[7],"have":[8],"accelerated":[9],"the":[10,20,25,40,44,82],"efficient":[11],"discovery":[12],"of":[13,24,42,84,116],"novel":[14,33],"genomes.":[15,34],"De":[16],"novo":[17,50],"assembly":[18,53],"is":[19,72],"first":[21],"and":[22,69,77,96,108],"one":[23],"most":[26],"computationally":[27],"intensive":[28],"step":[29],"to":[30,86],"analyze":[31],"such":[32],"In":[35],"this":[36],"work,":[37],"we":[38],"addressed":[39],"problem":[41],"parallelizing":[43],"de":[45,49],"Bruijn":[46],"graph":[47],"based":[48,73,90],"sequence":[52],"on":[54,74],"distributed":[55,88],"memory":[56,89],"systems.":[57],"We":[58,80],"proposed":[59],"a":[60],"new":[61],"tool,":[62],"Spaler,":[63],"which":[64],"assembles":[65],"short":[66],"reads":[67],"efficiently":[68],"accurately.":[70],"Spaler":[71,85,102],"Spark":[75],"framework":[76],"GraphX":[78],"API.":[79],"compared":[81],"performance":[83],"other":[87],"assemblers,":[91],"particular,":[93],"ABySS,":[94],"Ray":[95],"SWAP-Assembler.":[97],"results":[99,113],"show":[100],"that":[101],"scales":[103],"better":[104,112],"than":[105],"existing":[106],"tools":[107],"produces":[109],"comparable":[110],"or":[111],"terms":[115],"solution":[117],"quality.":[118]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}