{"id":"https://openalex.org/W2122210493","doi":"https://doi.org/10.1093/bioinformatics/btr595","title":"RAPSearch2: a fast and memory-efficient protein similarity search tool for next-generation sequencing data","display_name":"RAPSearch2: a fast and memory-efficient protein similarity search tool for next-generation sequencing data","publication_year":2011,"publication_date":"2011-10-28","ids":{"openalex":"https://openalex.org/W2122210493","doi":"https://doi.org/10.1093/bioinformatics/btr595","mag":"2122210493","pmid":"https://pubmed.ncbi.nlm.nih.gov/22039206"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btr595","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btr595","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/28/1/125/50568248/bioinformatics_28_1_125.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/28/1/125/50568248/bioinformatics_28_1_125.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048904646","display_name":"Yongan Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yongan Zhao","raw_affiliation_strings":["1 School of Informatics and Computing and 2Center for Genomics and Bioinformatics, Indiana University, Bloomington, IN 47404, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 School of Informatics and Computing and 2Center for Genomics and Bioinformatics, Indiana University, Bloomington, IN 47404, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078007096","display_name":"Haixu Tang","orcid":"https://orcid.org/0000-0001-8963-8155"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haixu Tang","raw_affiliation_strings":["1 School of Informatics and Computing and 2Center for Genomics and Bioinformatics, Indiana University, Bloomington, IN 47404, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 School of Informatics and Computing and 2Center for Genomics and Bioinformatics, Indiana University, Bloomington, IN 47404, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082620694","display_name":"Yuzhen Ye","orcid":"https://orcid.org/0000-0003-3707-3185"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuzhen Ye","raw_affiliation_strings":["1 School of Informatics and Computing and 2Center for Genomics and Bioinformatics, Indiana University, Bloomington, IN 47404, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 School of Informatics and Computing and 2Center for Genomics and Bioinformatics, Indiana University, Bloomington, IN 47404, USA","institution_ids":["https://openalex.org/I4210119109"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":6.3871,"has_fulltext":true,"cited_by_count":443,"citation_normalized_percentile":{"value":0.97527776,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"28","issue":"1","first_page":"125","last_page":"126"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.3260999917984009,"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":0.3260999917984009,"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/T11642","display_name":"Genomics and Rare Diseases","score":0.13079999387264252,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.12559999525547028,"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/computer-science","display_name":"Computer science","score":0.8370786905288696},{"id":"https://openalex.org/keywords/suffix-array","display_name":"Suffix array","score":0.7499995231628418},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6690249443054199},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.6335150003433228},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.5309585928916931},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.47801673412323},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.4489080011844635},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.444241464138031},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.4430626332759857},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4270709455013275},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35372114181518555},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.3280360698699951},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.27281033992767334},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.16775882244110107},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12569043040275574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8370786905288696},{"id":"https://openalex.org/C2779259728","wikidata":"https://www.wikidata.org/wiki/Q281472","display_name":"Suffix array","level":3,"score":0.7499995231628418},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6690249443054199},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.6335150003433228},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.5309585928916931},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.47801673412323},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.4489080011844635},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.444241464138031},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.4430626332759857},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4270709455013275},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35372114181518555},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.3280360698699951},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.27281033992767334},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16775882244110107},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12569043040275574}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057386","descriptor_name":"Search Engine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057386","descriptor_name":"Search Engine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057386","descriptor_name":"Search Engine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btr595","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btr595","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/28/1/125/50568248/bioinformatics_28_1_125.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:22039206","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/22039206","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:3244761","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3244761","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btr595","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btr595","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/28/1/125/50568248/bioinformatics_28_1_125.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2122210493.pdf","grobid_xml":"https://content.openalex.org/works/W2122210493.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W2040805829","https://openalex.org/W2055043387","https://openalex.org/W2115026474","https://openalex.org/W2116895571","https://openalex.org/W2121211805","https://openalex.org/W2131342905","https://openalex.org/W2136145671","https://openalex.org/W2149573313","https://openalex.org/W2153990926","https://openalex.org/W2158714788","https://openalex.org/W4293196852","https://openalex.org/W6842402754"],"related_works":["https://openalex.org/W2952211608","https://openalex.org/W4292322738","https://openalex.org/W2546940932","https://openalex.org/W1717915937","https://openalex.org/W3113848129","https://openalex.org/W2905797027","https://openalex.org/W2159613260","https://openalex.org/W2003608043","https://openalex.org/W1988679864","https://openalex.org/W4286817058"],"abstract_inverted_index":{"SUMMARY:":[0],"With":[1],"the":[2,91,116,128,167,176,186],"wide":[3],"application":[4],"of":[5,51,76,90,108],"next-generation":[6],"sequencing":[7],"(NGS)":[8],"techniques,":[9],"fast":[10],"tools":[11],"for":[12,53,136,173],"protein":[13,55],"similarity":[14,103,117],"search":[15,104],"that":[16,38,94],"scale":[17],"well":[18],"to":[19,44,68,73,100,142,153],"large":[20,24],"query":[21],"datasets":[22],"and":[23,127],"databases":[25],"are":[26],"highly":[27],"desirable.":[28],"In":[29],"a":[30,40,64,77,86,96,102],"previous":[31],"work,":[32],"we":[33,83],"developed":[34],"RAPSearch,":[35,61],"an":[36,109],"algorithm":[37,93],"achieved":[39],"~20-90-fold":[41],"speedup":[42],"relative":[43],"BLAST":[45],"while":[46],"still":[47],"achieving":[48],"similar":[49],"levels":[50],"sensitivity":[52],"short":[54],"fragments":[56],"derived":[57],"from":[58],"NGS":[59],"data.":[60],"however,":[62],"requires":[63,140],"substantial":[65],"memory":[66,144,155],"footprint":[67],"identify":[69],"alignment":[70],"seeds,":[71],"due":[72],"its":[74],"use":[75],"suffix":[78],"array":[79],"data":[80,111],"structure.":[81],"Here":[82],"present":[84],"RAPSearch2,":[85,126],"new":[87],"memory-efficient":[88],"implementation":[89],"RAPSearch":[92],"uses":[95],"collision-free":[97],"hash":[98],"table":[99],"index":[101],"database.":[105],"The":[106],"utilization":[107],"optimized":[110],"structure":[112],"further":[113],"speeds":[114],"up":[115,141,152],"search-another":[118],"2-3":[119],"times.":[120],"We":[121],"also":[122],"implemented":[123],"multi-threading":[124],"in":[125,147,158,165],"multi-thread":[129],"modes":[130],"achieve":[131],"significant":[132],"acceleration":[133],"(e.g.":[134],"3.5X":[135],"4-thread":[137,159],"mode).":[138],"RAPSearch2":[139,177,187],"2G":[143],"when":[145,156],"running":[146,157],"single":[148],"thread":[149],"mode,":[150],"or":[151],"3.5G":[154],"mode.":[160],"AVAILABILITY":[161],"AND":[162],"IMPLEMENTATION:":[163],"Implemented":[164],"C++,":[166],"source":[168],"code":[169],"is":[170],"freely":[171],"available":[172],"download":[174],"at":[175,185],"website:":[178],"http://omics.informatics.indiana.edu/mg/RAPSearch2/.":[179],"CONTACT:":[180],"yye@indiana.edu":[181],"SUPPLEMENTARY":[182],"INFORMATION:":[183],"Available":[184],"website.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":21},{"year":2022,"cited_by_count":29},{"year":2021,"cited_by_count":41},{"year":2020,"cited_by_count":21},{"year":2019,"cited_by_count":33},{"year":2018,"cited_by_count":44},{"year":2017,"cited_by_count":66},{"year":2016,"cited_by_count":58},{"year":2015,"cited_by_count":46},{"year":2014,"cited_by_count":29},{"year":2013,"cited_by_count":14},{"year":2012,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
