{"id":"https://openalex.org/W2770032907","doi":"https://doi.org/10.1109/escience.2017.59","title":"Accelerating Genome Sequence Alignment on Hadoop on Lustre Environment","display_name":"Accelerating Genome Sequence Alignment on Hadoop on Lustre Environment","publication_year":2017,"publication_date":"2017-10-01","ids":{"openalex":"https://openalex.org/W2770032907","doi":"https://doi.org/10.1109/escience.2017.59","mag":"2770032907"},"language":"en","primary_location":{"id":"doi:10.1109/escience.2017.59","is_oa":false,"landing_page_url":"https://doi.org/10.1109/escience.2017.59","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 13th International Conference on e-Science (e-Science)","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/A5021539206","display_name":"Eun-Kyu Byun","orcid":null},"institutions":[{"id":"https://openalex.org/I878022262","display_name":"Korea Institute of Science & Technology Information","ror":"https://ror.org/01k4yrm29","country_code":"KR","type":"facility","lineage":["https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098","https://openalex.org/I878022262"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Eun-Kyu Byun","raw_affiliation_strings":["Korea Institute of Science and Technology Information, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Korea Institute of Science and Technology Information, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I878022262"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069177443","display_name":"Junehawk Lee","orcid":"https://orcid.org/0000-0001-8908-0884"},"institutions":[{"id":"https://openalex.org/I878022262","display_name":"Korea Institute of Science & Technology Information","ror":"https://ror.org/01k4yrm29","country_code":"KR","type":"facility","lineage":["https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098","https://openalex.org/I878022262"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Junehawk Lee","raw_affiliation_strings":["Korea Institute of Science and Technology Information, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Korea Institute of Science and Technology Information, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I878022262"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008207995","display_name":"Seok Jong Yu","orcid":"https://orcid.org/0000-0002-2272-9869"},"institutions":[{"id":"https://openalex.org/I878022262","display_name":"Korea Institute of Science & Technology Information","ror":"https://ror.org/01k4yrm29","country_code":"KR","type":"facility","lineage":["https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098","https://openalex.org/I878022262"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seok Jong Yu","raw_affiliation_strings":["Korea Institute of Science and Technology Information, Daejeon, KR"],"affiliations":[{"raw_affiliation_string":"Korea Institute of Science and Technology Information, Daejeon, KR","institution_ids":["https://openalex.org/I878022262"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058946946","display_name":"Jae-Hyuck Kwak","orcid":"https://orcid.org/0000-0003-0058-8417"},"institutions":[{"id":"https://openalex.org/I878022262","display_name":"Korea Institute of Science & Technology Information","ror":"https://ror.org/01k4yrm29","country_code":"KR","type":"facility","lineage":["https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098","https://openalex.org/I878022262"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jae-Hyuck Kwak","raw_affiliation_strings":["Korea Institute of Science and Technology Information, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Korea Institute of Science and Technology Information, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I878022262"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113819719","display_name":"Soonwook Hwang","orcid":null},"institutions":[{"id":"https://openalex.org/I878022262","display_name":"Korea Institute of Science & Technology Information","ror":"https://ror.org/01k4yrm29","country_code":"KR","type":"facility","lineage":["https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098","https://openalex.org/I878022262"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Soonwook Hwang","raw_affiliation_strings":["Korea Institute of Science and Technology Information, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Korea Institute of Science and Technology Information, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I878022262"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5021539206"],"corresponding_institution_ids":["https://openalex.org/I878022262"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.13572586,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":95},"biblio":{"volume":"31","issue":null,"first_page":"436","last_page":"437"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.995199978351593,"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":0.9896000027656555,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.77394700050354},{"id":"https://openalex.org/keywords/lustre","display_name":"Lustre (file system)","score":0.7630717754364014},{"id":"https://openalex.org/keywords/map-reduce","display_name":"Map reduce","score":0.5883683562278748},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.540073812007904},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5365960597991943},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.49863314628601074},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.48250842094421387},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4624505341053009},{"id":"https://openalex.org/keywords/alignment-free-sequence-analysis","display_name":"Alignment-free sequence analysis","score":0.4269675612449646},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4232836663722992},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.40855973958969116},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.31996288895606995},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2946726679801941},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.20299655199050903},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1306033432483673},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.10004639625549316},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.08698385953903198},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.07742273807525635}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.77394700050354},{"id":"https://openalex.org/C180699724","wikidata":"https://www.wikidata.org/wiki/Q1877782","display_name":"Lustre (file system)","level":3,"score":0.7630717754364014},{"id":"https://openalex.org/C3019257732","wikidata":"https://www.wikidata.org/wiki/Q567759","display_name":"Map reduce","level":3,"score":0.5883683562278748},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.540073812007904},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5365960597991943},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.49863314628601074},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.48250842094421387},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4624505341053009},{"id":"https://openalex.org/C180384323","wikidata":"https://www.wikidata.org/wiki/Q16335137","display_name":"Alignment-free sequence analysis","level":5,"score":0.4269675612449646},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4232836663722992},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.40855973958969116},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.31996288895606995},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2946726679801941},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.20299655199050903},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1306033432483673},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.10004639625549316},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.08698385953903198},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.07742273807525635},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/escience.2017.59","is_oa":false,"landing_page_url":"https://doi.org/10.1109/escience.2017.59","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 13th International Conference on e-Science (e-Science)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Responsible consumption and production","id":"https://metadata.un.org/sdg/12","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1904861952","https://openalex.org/W2017928178","https://openalex.org/W2103441770","https://openalex.org/W2121762798","https://openalex.org/W2141978878","https://openalex.org/W2396849069","https://openalex.org/W4247053599"],"related_works":["https://openalex.org/W2051969447","https://openalex.org/W2141411672","https://openalex.org/W2133116680","https://openalex.org/W2111937814","https://openalex.org/W2029514038","https://openalex.org/W1486249959","https://openalex.org/W2141530749","https://openalex.org/W88386512","https://openalex.org/W1977143711","https://openalex.org/W2091678889"],"abstract_inverted_index":{"Genome":[0],"sequence":[1,33,54],"alignment":[2,34,55],"is":[3,83],"one":[4,16],"of":[5,9,17,26],"the":[6,18],"basic":[7],"procedure":[8],"genome":[10,32],"sequencing":[11],"analysis":[12],"pipeline":[13],"and":[14,72],"also":[15],"most":[19],"time-consuming":[20],"parts.":[21],"Including":[22],"BigBWA,":[23,63],"a":[24,52,91],"number":[25],"tools":[27],"were":[28],"proposed":[29],"to":[30],"accelerate":[31],"by":[35,70],"parallelizing":[36],"computation":[37],"with":[38],"Hadoop":[39,58,95],"technologies.":[40],"However,":[41],"HDFS":[42,71],"incurs":[43],"considerable":[44],"I/O":[45,75],"overhead.":[46],"In":[47],"this":[48],"research,":[49],"we":[50,64],"propose":[51],"new":[53],"tool":[56],"adopting":[57],"on":[59,62],"Lustre.":[60],"Based":[61],"removed":[65],"data":[66],"transfer":[67],"overhead":[68],"caused":[69],"parallelized":[73],"whole":[74],"steps.":[76],"Experimental":[77],"result":[78],"shows":[79],"that":[80],"our":[81],"solution":[82],"five":[84],"times":[85],"faster":[86],"than":[87],"original":[88],"BigBWA":[89],"in":[90],"ten-node":[92],"Lustre":[93],"based":[94],"cluster.":[96]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
