{"id":"https://openalex.org/W2799276990","doi":"https://doi.org/10.23919/icitst.2017.8356451","title":"Spark framework for transcriptomic trimming algorithm reduces cost of reading multiple input files","display_name":"Spark framework for transcriptomic trimming algorithm reduces cost of reading multiple input files","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2799276990","doi":"https://doi.org/10.23919/icitst.2017.8356451","mag":"2799276990"},"language":"en","primary_location":{"id":"doi:10.23919/icitst.2017.8356451","is_oa":false,"landing_page_url":"https://doi.org/10.23919/icitst.2017.8356451","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 12th International Conference for Internet Technology and Secured Transactions (ICITST)","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/A5063920858","display_name":"Walter Blair","orcid":null},"institutions":[{"id":"https://openalex.org/I204593131","display_name":"College of Charleston","ror":"https://ror.org/00390t168","country_code":"US","type":"education","lineage":["https://openalex.org/I204593131"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Walter Blair","raw_affiliation_strings":["Department of Computer Science, College of Charleston, Charleston, SC"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, College of Charleston, Charleston, SC","institution_ids":["https://openalex.org/I204593131"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037716101","display_name":"Aspen Olmsted","orcid":"https://orcid.org/0000-0003-2652-0154"},"institutions":[{"id":"https://openalex.org/I204593131","display_name":"College of Charleston","ror":"https://ror.org/00390t168","country_code":"US","type":"education","lineage":["https://openalex.org/I204593131"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aspen Olmsted","raw_affiliation_strings":["Department of Computer Science, College of Charleston, Charleston, SC"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, College of Charleston, Charleston, SC","institution_ids":["https://openalex.org/I204593131"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113765572","display_name":"Paul E. Anderson","orcid":null},"institutions":[{"id":"https://openalex.org/I204593131","display_name":"College of Charleston","ror":"https://ror.org/00390t168","country_code":"US","type":"education","lineage":["https://openalex.org/I204593131"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul Anderson","raw_affiliation_strings":["Department of Computer Science, College of Charleston, Charleston, SC"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, College of Charleston, Charleston, SC","institution_ids":["https://openalex.org/I204593131"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5063920858"],"corresponding_institution_ids":["https://openalex.org/I204593131"],"apc_list":null,"apc_paid":null,"fwci":0.1063,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.50525068,"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":"469","last_page":"471"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9954000115394592,"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":0.9954000115394592,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9918000102043152,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9912999868392944,"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/trimming","display_name":"Trimming","score":0.8589035272598267},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8403960466384888},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.81487637758255},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.7424178719520569},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6243107318878174},{"id":"https://openalex.org/keywords/scala","display_name":"Scala","score":0.5823442339897156},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.52284175157547},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4603545069694519},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.41720402240753174},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3242959976196289},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.21829959750175476},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.17216724157333374}],"concepts":[{"id":"https://openalex.org/C56951928","wikidata":"https://www.wikidata.org/wiki/Q3539213","display_name":"Trimming","level":2,"score":0.8589035272598267},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8403960466384888},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.81487637758255},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.7424178719520569},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6243107318878174},{"id":"https://openalex.org/C109701466","wikidata":"https://www.wikidata.org/wiki/Q460584","display_name":"Scala","level":3,"score":0.5823442339897156},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.52284175157547},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4603545069694519},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.41720402240753174},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3242959976196289},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.21829959750175476},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.17216724157333374},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/icitst.2017.8356451","is_oa":false,"landing_page_url":"https://doi.org/10.23919/icitst.2017.8356451","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 12th International Conference for Internet Technology and Secured Transactions (ICITST)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1989017925","https://openalex.org/W2025943989","https://openalex.org/W2082447166","https://openalex.org/W2131271579","https://openalex.org/W2147869723","https://openalex.org/W2292431705","https://openalex.org/W2408045830","https://openalex.org/W2462981832","https://openalex.org/W2530314904","https://openalex.org/W2575651982","https://openalex.org/W6713636576"],"related_works":["https://openalex.org/W2467235537","https://openalex.org/W4243755427","https://openalex.org/W1493074871","https://openalex.org/W2763674625","https://openalex.org/W4252019479","https://openalex.org/W2337519567","https://openalex.org/W2548921709","https://openalex.org/W4252076541","https://openalex.org/W2620395718","https://openalex.org/W2950624501"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"investigate":[4,146],"the":[5,65,75,80,85,96,112,124,147,152],"feasibility":[6],"and":[7,28,34,38,56,88,109],"performance":[8,138,148],"improvement":[9],"of":[10,31,74,95,126,150],"adapting":[11],"a":[12,22,48],"common":[13,98],"standalone":[14],"bioinformatics":[15,66],"trimming":[16,101],"tool":[17],"for":[18,51],"in-memory":[19],"processing":[20,42],"on":[21],"distributed":[23,113,153],"Spark":[24,135],"framework.":[25],"The":[26],"rapid":[27],"continuous":[29],"rise":[30],"genomics":[32],"technologies":[33],"applications":[35],"demands":[36],"fast":[37],"efficient":[39],"genomic":[40],"data":[41],"pipelines.":[43],"ADAM":[44,81,157],"has":[45],"emerged":[46],"as":[47,72,77],"successful":[49],"framework":[50,82,114],"handling":[52],"large":[53],"scientific":[54],"datasets,":[55],"efforts":[57],"are":[58],"ongoing":[59],"to":[60,103,118,156,167],"expand":[61],"its":[62],"functionality":[63],"in":[64,134,158],"pipeline.":[67],"We":[68,91,129],"hypothesize":[69],"that":[70,111,131],"executing":[71,132],"much":[73],"pipeline":[76],"possible":[78],"within":[79],"will":[83,136,145],"improve":[84,137],"pipeline's":[86],"time":[87],"disk":[89],"requirements.":[90],"compare":[92],"Trimmomatic,":[93],"one":[94],"most":[97],"raw":[99],"read":[100],"algorithms,":[102],"our":[104,116],"own":[105],"simple":[106],"Scala":[107],"trimmer":[108,117],"show":[110],"allows":[115],"suffer":[119],"less":[120],"overhead":[121],"from":[122],"increasing":[123],"number":[125],"input":[127],"files.":[128],"conclude":[130],"Trimmomatic":[133],"with":[139],"multiple":[140],"file":[141,166],"inputs.":[142],"Future":[143],"work":[144],"benefit":[149],"passing":[151],"dataset":[154],"directly":[155],"memory":[159],"rather":[160],"than":[161],"writing":[162],"out":[163],"an":[164],"intermediate":[165],"disk.":[168]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
