{"id":"https://openalex.org/W1978625128","doi":"https://doi.org/10.1145/2484762.2484809","title":"High performance computing workflow for protein functional annotation","display_name":"High performance computing workflow for protein functional annotation","publication_year":2013,"publication_date":"2013-07-22","ids":{"openalex":"https://openalex.org/W1978625128","doi":"https://doi.org/10.1145/2484762.2484809","mag":"1978625128"},"language":"en","primary_location":{"id":"doi:10.1145/2484762.2484809","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2484762.2484809","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Conference on Extreme Science and Engineering Discovery Environment: Gateway to Discovery","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/A5068385320","display_name":"Larissa Stanberry","orcid":"https://orcid.org/0000-0002-2388-0640"},"institutions":[{"id":"https://openalex.org/I4210136254","display_name":"Children\u2019s Health Research Institute","ror":"https://ror.org/038pa9k74","country_code":"CA","type":"funder","lineage":["https://openalex.org/I2800925808","https://openalex.org/I4210136254","https://openalex.org/I4406742388"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Larissa Stanberry","raw_affiliation_strings":["Seattle Children's Research Institute (SCRI), DELSA, Global"],"affiliations":[{"raw_affiliation_string":"Seattle Children's Research Institute (SCRI), DELSA, Global","institution_ids":["https://openalex.org/I4210136254"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100390952","display_name":"Yuan Liu","orcid":"https://orcid.org/0000-0003-4247-3562"},"institutions":[{"id":"https://openalex.org/I4210159558","display_name":"Joint Institute for Computational Sciences","ror":"https://ror.org/05277x335","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294","https://openalex.org/I4210159558","https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuan Liu","raw_affiliation_strings":["JICS UT - ORNL"],"affiliations":[{"raw_affiliation_string":"JICS UT - ORNL","institution_ids":["https://openalex.org/I4210159558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008551250","display_name":"Bhanu Rekepalli","orcid":null},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhanu Rekepalli","raw_affiliation_strings":["University of Tennessee \u00e2\u0102\u015e, DELSA, Global"],"affiliations":[{"raw_affiliation_string":"University of Tennessee \u00e2\u0102\u015e, DELSA, Global","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004994637","display_name":"Paul Giblock","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159558","display_name":"Joint Institute for Computational Sciences","ror":"https://ror.org/05277x335","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294","https://openalex.org/I4210159558","https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul Giblock","raw_affiliation_strings":["JICS UT - ORNL"],"affiliations":[{"raw_affiliation_string":"JICS UT - ORNL","institution_ids":["https://openalex.org/I4210159558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108222756","display_name":"Roger Higdon","orcid":null},"institutions":[{"id":"https://openalex.org/I4210151837","display_name":"High Throughput Biology (United States)","ror":"https://ror.org/05h1bjp83","country_code":"US","type":"company","lineage":["https://openalex.org/I4210151837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roger Higdon","raw_affiliation_strings":["Bioinformatics &amp; High-Throughput Analysis Laboratory and High-throughput Analysis Core, SCRI DELSA Global"],"affiliations":[{"raw_affiliation_string":"Bioinformatics &amp; High-Throughput Analysis Laboratory and High-throughput Analysis Core, SCRI DELSA Global","institution_ids":["https://openalex.org/I4210151837"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056533315","display_name":"William Broomall","orcid":null},"institutions":[{"id":"https://openalex.org/I4210151837","display_name":"High Throughput Biology (United States)","ror":"https://ror.org/05h1bjp83","country_code":"US","type":"company","lineage":["https://openalex.org/I4210151837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Broomall","raw_affiliation_strings":["High-Throughput Analysis Core, SCRI; DELSA Global","DELSA Global"],"affiliations":[{"raw_affiliation_string":"High-Throughput Analysis Core, SCRI; DELSA Global","institution_ids":["https://openalex.org/I4210151837"]},{"raw_affiliation_string":"DELSA Global","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5068385320"],"corresponding_institution_ids":["https://openalex.org/I4210136254"],"apc_list":null,"apc_paid":null,"fwci":0.1462,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54556084,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9998000264167786,"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":0.9998000264167786,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9962000250816345,"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":0.9814000129699707,"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/workflow","display_name":"Workflow","score":0.9084140062332153},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.74456787109375},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7351605892181396},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6847206354141235},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.5579859614372253},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4693972170352936},{"id":"https://openalex.org/keywords/bacterial-genome-size","display_name":"Bacterial genome size","score":0.44177672266960144},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.4400861859321594},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.22737199068069458},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2208556830883026},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2051558792591095},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.12979644536972046},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.12163254618644714},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.0946243405342102}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.9084140062332153},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.74456787109375},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7351605892181396},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6847206354141235},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5579859614372253},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4693972170352936},{"id":"https://openalex.org/C3742359","wikidata":"https://www.wikidata.org/wiki/Q4839988","display_name":"Bacterial genome size","level":4,"score":0.44177672266960144},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.4400861859321594},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.22737199068069458},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2208556830883026},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2051558792591095},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.12979644536972046},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.12163254618644714},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0946243405342102}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2484762.2484809","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2484762.2484809","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Conference on Extreme Science and Engineering Discovery Environment: Gateway to Discovery","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W145805655","https://openalex.org/W1587558271","https://openalex.org/W1857624741","https://openalex.org/W1976049389","https://openalex.org/W1990453950","https://openalex.org/W1997268601","https://openalex.org/W1997512351","https://openalex.org/W2003647795","https://openalex.org/W2005112508","https://openalex.org/W2014328430","https://openalex.org/W2024799741","https://openalex.org/W2030006812","https://openalex.org/W2035575075","https://openalex.org/W2055043387","https://openalex.org/W2057705283","https://openalex.org/W2059133370","https://openalex.org/W2065783627","https://openalex.org/W2081294880","https://openalex.org/W2097485877","https://openalex.org/W2112286591","https://openalex.org/W2121481633","https://openalex.org/W2124166542","https://openalex.org/W2129154270","https://openalex.org/W2130312510","https://openalex.org/W2132926880","https://openalex.org/W2137488129","https://openalex.org/W2146827656","https://openalex.org/W2148130205","https://openalex.org/W2154364831","https://openalex.org/W2155518645","https://openalex.org/W2155606054","https://openalex.org/W2156125289","https://openalex.org/W2158714788","https://openalex.org/W2172031170","https://openalex.org/W2173541864","https://openalex.org/W2582743722","https://openalex.org/W2951726307","https://openalex.org/W3126065083","https://openalex.org/W3174107850","https://openalex.org/W4207066629","https://openalex.org/W6677221801","https://openalex.org/W6737467347"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2358755282","https://openalex.org/W2625833328","https://openalex.org/W1533177136","https://openalex.org/W1989895641","https://openalex.org/W2467039083"],"abstract_inverted_index":{"Functional":[0],"annotation":[1,81],"of":[2,8,38,45,50,65,106,109,178],"newly":[3,170],"sequenced":[4,27,171],"genomes":[5,29],"is":[6],"one":[7,168],"the":[9,19,63,113,122,163,175,179,181],"major":[10],"challenges":[11],"in":[12],"modern":[13,16],"biology.":[14],"With":[15,174],"sequencing":[17],"technologies,":[18],"PSU":[20],"(Protein":[21],"Sequence":[22],"Universe)":[23],"expands":[24],"exponentially.":[25],"Newly":[26],"bacterial":[28,103,172],"alone":[30],"contain":[31],"over":[32],"7.5":[33],"million":[34,169],"proteins.":[35,173],"The":[36,48,139],"rate":[37],"data":[39,52,130],"generation":[40],"has":[41],"far":[42],"surpassed":[43],"that":[44],"protein":[46,51,80],"annotation.":[47],"volume":[49],"makes":[53],"manual":[54],"curation":[55],"infeasible":[56],"whereas":[57],"a":[58,94],"high":[59],"compute":[60],"cost":[61],"limits":[62],"utility":[64],"existing":[66,83],"automated":[67,75],"approaches.":[68],"In":[69],"this":[70],"study,":[71],"we":[72,165],"built":[73],"an":[74],"workflow":[76,140,183],"to":[77,99,131,187],"enable":[78,185],"large-scale":[79],"into":[82,102],"orthologous":[84],"groups":[85],"using":[86],"HPC":[87],"(High":[88],"Performance":[89],"Computing)":[90],"architectures.":[91],"We":[92],"developed":[93,152],"low":[95],"complexity":[96],"classification":[97,147],"algorithm":[98,123],"assign":[100],"proteins":[101],"COGs":[104],"(Clusters":[105],"Orthologous":[107],"Groups":[108],"proteins).":[110],"Based":[111],"on":[112,126,153],"PSI-BLAST":[114],"(Position-Specific":[115],"Iterative":[116],"Basic":[117],"Local":[118],"Alignment":[119],"Search":[120],"Tool),":[121],"was":[124,151],"validated":[125],"simulated":[127],"and":[128,137,148,157],"archaeal":[129],"ensure":[132],"at":[133],"least":[134],"80%":[135],"specificity":[136],"sensitivity.":[138],"with":[141],"highly":[142],"scalable":[143],"parallel":[144],"applications":[145],"for":[146],"sequence":[149],"alignment":[150],"XSEDE":[154],"(Extreme":[155],"Science":[156],"Engineering":[158],"Discovery":[159],"Environment)":[160],"supercomputers.":[161],"Using":[162],"workflow,":[164],"have":[166],"classified":[167],"rapid":[176],"expansion":[177],"PSU,":[180],"proposed":[182],"will":[184],"scientists":[186],"annotate":[188],"big":[189],"genome":[190],"data.":[191]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
