{"id":"https://openalex.org/W2747148449","doi":"https://doi.org/10.1145/3107411.3108222","title":"Overlap Graph Reduction for Genome Assembly using Apache Spark","display_name":"Overlap Graph Reduction for Genome Assembly using Apache Spark","publication_year":2017,"publication_date":"2017-08-20","ids":{"openalex":"https://openalex.org/W2747148449","doi":"https://doi.org/10.1145/3107411.3108222","mag":"2747148449"},"language":"en","primary_location":{"id":"doi:10.1145/3107411.3108222","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3107411.3108222","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/A5103953329","display_name":"Alexander J. Paul","orcid":null},"institutions":[{"id":"https://openalex.org/I47838141","display_name":"Saint Louis University","ror":"https://ror.org/01p7jjy08","country_code":"US","type":"education","lineage":["https://openalex.org/I47838141"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Alexander J. Paul","raw_affiliation_strings":["Saint Louis University, St. Louis, MO, USA"],"affiliations":[{"raw_affiliation_string":"Saint Louis University, St. Louis, MO, USA","institution_ids":["https://openalex.org/I47838141"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025681662","display_name":"Dylan Lawrence","orcid":"https://orcid.org/0000-0001-6919-8308"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dylan Lawrence","raw_affiliation_strings":["Washington University in St. Louis, St. Louis, MO, USA"],"affiliations":[{"raw_affiliation_string":"Washington University in St. Louis, St. Louis, MO, USA","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047054370","display_name":"Tae-Hyuk Ahn","orcid":"https://orcid.org/0000-0002-7281-9459"},"institutions":[{"id":"https://openalex.org/I47838141","display_name":"Saint Louis University","ror":"https://ror.org/01p7jjy08","country_code":"US","type":"education","lineage":["https://openalex.org/I47838141"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tae-Hyuk Ahn","raw_affiliation_strings":["Saint Louis University, St. Louis, MO, USA"],"affiliations":[{"raw_affiliation_string":"Saint Louis University, St. Louis, MO, USA","institution_ids":["https://openalex.org/I47838141"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103953329"],"corresponding_institution_ids":["https://openalex.org/I47838141"],"apc_list":null,"apc_paid":null,"fwci":0.1063,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.4831948,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"613","last_page":"613"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9958999752998352,"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":0.9958999752998352,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9901999831199646,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9690999984741211,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/sequence-assembly","display_name":"Sequence assembly","score":0.682837724685669},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6660877466201782},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.5852065086364746},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5441634654998779},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.5434340834617615},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.4727129638195038},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.46000224351882935},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.38406917452812195},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3699783980846405},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3291320204734802},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.29494526982307434},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14032068848609924},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.13973385095596313},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.1355779469013214},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.13525626063346863},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12548741698265076}],"concepts":[{"id":"https://openalex.org/C18949551","wikidata":"https://www.wikidata.org/wiki/Q740578","display_name":"Sequence assembly","level":5,"score":0.682837724685669},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6660877466201782},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.5852065086364746},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5441634654998779},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5434340834617615},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.4727129638195038},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.46000224351882935},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.38406917452812195},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3699783980846405},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3291320204734802},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.29494526982307434},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14032068848609924},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13973385095596313},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.1355779469013214},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.13525626063346863},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12548741698265076},{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.0},{"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/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3107411.3108222","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3107411.3108222","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/G23608893","display_name":null,"funder_award_id":"CRII-1566292","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"},{"id":"https://openalex.org/F4320312021","display_name":"Saint Louis University","ror":"https://ror.org/01p7jjy08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W1997246534","https://openalex.org/W2140437680","https://openalex.org/W2189465200"],"related_works":["https://openalex.org/W4244478748","https://openalex.org/W1975949872","https://openalex.org/W3159871278","https://openalex.org/W2230552005","https://openalex.org/W4223488648","https://openalex.org/W2905242764","https://openalex.org/W2134969820","https://openalex.org/W2251605416","https://openalex.org/W2560439919","https://openalex.org/W4389340727"],"abstract_inverted_index":{"The":[0],"advent":[1],"of":[2,21,34],"third-generation":[3],"long-range":[4],"DNA":[5],"sequencing":[6],"and":[7],"mapping":[8],"techniques":[9],"has":[10],"permitted":[11],"nearly":[12],"perfect":[13],"or":[14],"very":[15],"high":[16],"quality":[17],"de":[18,27],"novo":[19,28],"assemblies":[20],"genomes.":[22],"However,":[23],"most":[24],"overlap":[25],"graph":[26,47],"assemblers":[29],"still":[30],"require":[31],"large":[32,40],"amounts":[33],"computer":[35],"memory":[36],"to":[37],"resolve":[38],"the":[39],"genome":[41,51],"graphs.":[42],"Here,":[43],"we":[44],"apply":[45],"string":[46],"reduction":[48],"algorithms":[49],"for":[50],"assembly":[52],"using":[53],"Apache":[54],"Spark":[55],"on":[56],"a":[57],"distributed":[58],"cloud":[59],"computing":[60],"platform.":[61]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
