{"id":"https://openalex.org/W2037509366","doi":"https://doi.org/10.1109/icpp.2010.41","title":"A Scalable Parallel Algorithm for Large-Scale Protein Sequence Homology Detection","display_name":"A Scalable Parallel Algorithm for Large-Scale Protein Sequence Homology Detection","publication_year":2010,"publication_date":"2010-09-01","ids":{"openalex":"https://openalex.org/W2037509366","doi":"https://doi.org/10.1109/icpp.2010.41","mag":"2037509366"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpp.2010.41","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5110069965","display_name":"Changjun Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I72951846","display_name":"Washington State University","ror":"https://ror.org/05dk0ce17","country_code":"US","type":"funder","lineage":["https://openalex.org/I72951846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Changjun Wu","raw_affiliation_strings":["Sch. of Electr. Eng. & Comput. Sci.,, Washington State Univ., Pullman, WA, USA"],"affiliations":[{"raw_affiliation_string":"Sch. of Electr. Eng. & Comput. Sci.,, Washington State Univ., Pullman, WA, USA","institution_ids":["https://openalex.org/I72951846"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103010775","display_name":"Ananth Kalyanaraman","orcid":"https://orcid.org/0000-0003-3495-2264"},"institutions":[{"id":"https://openalex.org/I72951846","display_name":"Washington State University","ror":"https://ror.org/05dk0ce17","country_code":"US","type":"funder","lineage":["https://openalex.org/I72951846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ananth Kalyanaraman","raw_affiliation_strings":["Sch. of Electr. Eng. & Comput. Sci.,, Washington State Univ., Pullman, WA, USA"],"affiliations":[{"raw_affiliation_string":"Sch. of Electr. Eng. & Comput. Sci.,, Washington State Univ., Pullman, WA, USA","institution_ids":["https://openalex.org/I72951846"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058577320","display_name":"William R. Cannon","orcid":"https://orcid.org/0000-0003-3789-7889"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"funder","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William R. Cannon","raw_affiliation_strings":["Pacific Northwest National Laboratories Richland WA USA"],"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratories Richland WA USA","institution_ids":["https://openalex.org/I142606810"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.556,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":3,"citation_normalized_percentile":{"value":0.598268,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":75,"max":77},"biblio":{"volume":null,"issue":null,"first_page":"333","last_page":"342"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9962,"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":0.9962,"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":0.9931,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9931,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.46822307},{"id":"https://openalex.org/keywords/homology","display_name":"Homology","score":0.4570984}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7209943},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6039104},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.6037169},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.57645375},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5116961},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.46822307},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4601233},{"id":"https://openalex.org/C165525559","wikidata":"https://www.wikidata.org/wiki/Q224180","display_name":"Homology (biology)","level":3,"score":0.4570984},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.42961097},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.41633263},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33015645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16131648},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1552451},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.11878681},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpp.2010.41","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":20,"referenced_works":["https://openalex.org/W1791999417","https://openalex.org/W2029954707","https://openalex.org/W2055043387","https://openalex.org/W2074231493","https://openalex.org/W2087064593","https://openalex.org/W2096984027","https://openalex.org/W2109681892","https://openalex.org/W2121297744","https://openalex.org/W2124166542","https://openalex.org/W2127230663","https://openalex.org/W2141885858","https://openalex.org/W2143210482","https://openalex.org/W2147783737","https://openalex.org/W2161189461","https://openalex.org/W21816278","https://openalex.org/W2533248932","https://openalex.org/W2584945553","https://openalex.org/W4210400672","https://openalex.org/W4236236547","https://openalex.org/W4243336146"],"related_works":["https://openalex.org/W3214280620","https://openalex.org/W3191490922","https://openalex.org/W2794038527","https://openalex.org/W2765823764","https://openalex.org/W2523801036","https://openalex.org/W2384867379","https://openalex.org/W2329539859","https://openalex.org/W2227905990","https://openalex.org/W2151092287","https://openalex.org/W2000785801"],"abstract_inverted_index":{"Protein":[0],"sequence":[1,93],"homology":[2,31,41],"detection":[3],"is":[4,36,54,88,99,111,123],"a":[5,13,43,83,102,155],"fundamental":[6],"problem":[7,75],"in":[8,16,119,134],"computational":[9],"molecular":[10],"biology,":[11],"with":[12],"pervasive":[14],"application":[15],"nearly":[17],"all":[18,146],"analyses":[19],"that":[20,72,87,131,140],"aim":[21],"to":[22,60,78,151,161],"structurally":[23],"and":[24,80,115,177],"functionally":[25],"characterize":[26],"protein":[27,34,92],"molecules.":[28],"While":[29],"detecting":[30,39],"between":[32],"two":[33],"sequences":[35],"computationally":[37],"inexpensive,":[38],"pairwise":[40],"at":[42],"large-scale":[44,91],"becomes":[45],"prohibitive,":[46],"requiring":[47],"millions":[48],"of":[49,170,174],"CPU":[50],"hours.":[51],"Yet,":[52],"there":[53],"currently":[55],"no":[56],"efficient":[57],"method":[58,142],"available":[59],"parallelize":[61],"this":[62,65,74],"kernel.":[63],"In":[64,159],"paper,":[66],"we":[67,165],"present":[68,166],"the":[69,108,116,121,128,135,171,175],"key":[70],"characteristics":[71],"make":[73],"particularly":[76],"hard":[77],"parallelize,":[79],"then":[81],"propose":[82],"new":[84],"parallel":[85],"algorithm":[86],"suited":[89],"for":[90],"data.":[94],"Our":[95],"method,":[96],"called":[97],"pGraph,":[98],"designed":[100],"using":[101],"hierarchical":[103],"multiple-master":[104],"multiple-worker":[105],"model,":[106],"where":[107],"processor":[109],"space":[110],"partitioned":[112],"into":[113],"subgroups":[114],"hierarchy":[117],"helps":[118],"ensuring":[120],"workload":[122],"load":[124],"balanced":[125],"fashion":[126],"despite":[127],"inherent":[129],"irregularity":[130],"may":[132],"originate":[133],"input.":[136],"Experimental":[137],"evaluation":[138],"demonstrates":[139],"our":[141],"scales":[143],"linearly":[144],"on":[145,154],"input":[147],"sizes":[148],"tested":[149],"(up":[150],"640K":[152],"sequences)":[153],"1,024":[156],"node":[157],"supercomputer.":[158],"addition":[160],"demonstrating":[162],"strong":[163],"scaling,":[164],"an":[167],"extensive":[168],"study":[169],"various":[172],"components":[173],"system":[176],"related":[178],"parametric":[179],"studies.":[180]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2037509366","counts_by_year":[{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2025-03-15T19:28:00.314149","created_date":"2016-06-24"}