{"id":"https://openalex.org/W2887121898","doi":"https://doi.org/10.1186/s12859-018-2290-3","title":"TOPAZ: asymmetric suffix array neighbourhood search for massive protein databases","display_name":"TOPAZ: asymmetric suffix array neighbourhood search for massive protein databases","publication_year":2018,"publication_date":"2018-07-31","ids":{"openalex":"https://openalex.org/W2887121898","doi":"https://doi.org/10.1186/s12859-018-2290-3","mag":"2887121898","pmid":"https://pubmed.ncbi.nlm.nih.gov/30064374"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-018-2290-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-018-2290-3","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-018-2290-3","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-018-2290-3","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007118986","display_name":"Alan Medlar","orcid":"https://orcid.org/0000-0002-5139-9483"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]},{"id":"https://openalex.org/I2800229700","display_name":"Helsinki Institute of Physics","ror":"https://ror.org/01x2x1522","country_code":"FI","type":"facility","lineage":["https://openalex.org/I133731052","https://openalex.org/I2800229700","https://openalex.org/I63548447","https://openalex.org/I94722563","https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Alan Medlar","raw_affiliation_strings":["Institute of Biotechnology, University of Helsinki, Helsinki, 00014, Finland. alan.j.medlar@helsinki.fi","Institute of Biotechnology, University of Helsinki, Helsinki, 00014, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Biotechnology, University of Helsinki, Helsinki, 00014, Finland. alan.j.medlar@helsinki.fi","institution_ids":["https://openalex.org/I2800229700"]},{"raw_affiliation_string":"Institute of Biotechnology, University of Helsinki, Helsinki, 00014, Finland","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064498279","display_name":"Liisa Holm","orcid":"https://orcid.org/0000-0002-7807-2966"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Liisa Holm","raw_affiliation_strings":["Institute of Biotechnology, University of Helsinki, Helsinki, 00014, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Biotechnology, University of Helsinki, Helsinki, 00014, Finland","institution_ids":["https://openalex.org/I133731052"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5007118986"],"corresponding_institution_ids":["https://openalex.org/I133731052","https://openalex.org/I2800229700"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":0.1648,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.48580744,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"19","issue":"1","first_page":"278","last_page":"278"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.5997999906539917,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.5997999906539917,"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":0.11739999800920486,"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/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.05220000073313713,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6769426465034485},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5793420672416687},{"id":"https://openalex.org/keywords/uniprot","display_name":"UniProt","score":0.5371556878089905},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.4576323330402374},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.42451146245002747},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38135838508605957},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3204852044582367},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.31659185886383057},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2316218912601471},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.22984856367111206},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1079263985157013},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.09883356094360352}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6769426465034485},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5793420672416687},{"id":"https://openalex.org/C202264299","wikidata":"https://www.wikidata.org/wiki/Q905695","display_name":"UniProt","level":3,"score":0.5371556878089905},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.4576323330402374},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.42451146245002747},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38135838508605957},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3204852044582367},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.31659185886383057},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2316218912601471},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.22984856367111206},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1079263985157013},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.09883356094360352},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004755","descriptor_name":"Enterobacteriaceae","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D004755","descriptor_name":"Enterobacteriaceae","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D004755","descriptor_name":"Enterobacteriaceae","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","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}],"locations_count":6,"locations":[{"id":"doi:10.1186/s12859-018-2290-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-018-2290-3","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-018-2290-3","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:30064374","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30064374","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:753ce6bffdd34cb29a978f619185cc65","is_oa":true,"landing_page_url":"https://doaj.org/article/753ce6bffdd34cb29a978f619185cc65","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 19, Iss 1, Pp 1-9 (2018)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:5026300","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6069885","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},{"id":"pmh:oai:helda.helsinki.fi:10138/237629","is_oa":true,"landing_page_url":"http://hdl.handle.net/10138/237629","pdf_url":null,"source":{"id":"https://openalex.org/S4210213322","display_name":"Ty\u00f6v\u00e4entutkimus Vuosikirja","issn_l":"0784-1272","issn":["0784-1272","1459-7780"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"http://purl.org/eprint/type/JournalArticle"},{"id":"pmh:oai:helda.helsinki.fi:10138/237865","is_oa":true,"landing_page_url":"http://hdl.handle.net/10138/237865","pdf_url":null,"source":{"id":"https://openalex.org/S4210213322","display_name":"Ty\u00f6v\u00e4entutkimus Vuosikirja","issn_l":"0784-1272","issn":["0784-1272","1459-7780"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1186/s12859-018-2290-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-018-2290-3","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-018-2290-3","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/11"}],"awards":[{"id":"https://openalex.org/G1074501907","display_name":null,"funder_award_id":"292589","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"}],"funders":[{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2887121898.pdf","grobid_xml":"https://content.openalex.org/works/W2887121898.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1513332069","https://openalex.org/W2018564950","https://openalex.org/W2045204781","https://openalex.org/W2047520798","https://openalex.org/W2066852475","https://openalex.org/W2096041635","https://openalex.org/W2097892623","https://openalex.org/W2106292145","https://openalex.org/W2117012676","https://openalex.org/W2128591967","https://openalex.org/W2140057519","https://openalex.org/W2141200343","https://openalex.org/W2142678478","https://openalex.org/W2158322625","https://openalex.org/W2158874082","https://openalex.org/W2161418621","https://openalex.org/W2161488606","https://openalex.org/W2162758337","https://openalex.org/W2184115732","https://openalex.org/W2799828084","https://openalex.org/W2803807675","https://openalex.org/W3145128584","https://openalex.org/W4246219036"],"related_works":["https://openalex.org/W2317245370","https://openalex.org/W3138386522","https://openalex.org/W2499279132","https://openalex.org/W4249323025","https://openalex.org/W198851386","https://openalex.org/W2030310580","https://openalex.org/W947442053","https://openalex.org/W1980160788","https://openalex.org/W2148915962","https://openalex.org/W2283866686"],"abstract_inverted_index":{"BACKGROUND:":[0],"Protein":[1],"homology":[2,36,180],"search":[3,37,73,181],"is":[4,134],"an":[5,53,108],"important,":[6],"yet":[7],"time-consuming,":[8],"step":[9],"in":[10,141],"everything":[11],"from":[12],"protein":[13,30],"annotation":[14],"to":[15,25,34,49,76,84,156,167,174,184],"metagenomics.":[16],"Its":[17],"application,":[18],"however,":[19],"has":[20],"become":[21],"increasingly":[22],"challenging,":[23],"due":[24],"the":[26,39,69,90,123,128,137,157,178,196],"exponential":[27],"growth":[28],"of":[29,68,92,127,136,143,171,195],"databases.":[31],"In":[32,148],"order":[33],"perform":[35],"at":[38,89],"required":[40],"scale,":[41],"many":[42],"methods":[43,140,182,202],"have":[44,183],"been":[45],"proposed":[46],"as":[47,193],"alternatives":[48],"BLAST":[50],"that":[51],"make":[52,185],"explicit":[54],"trade-off":[55,179],"between":[56,186],"sensitivity":[57,88,124,145,170,187],"and":[58,80,107,125,146,188,199],"speed.":[59],"One":[60],"such":[61],"method,":[62],"SANSparallel,":[63],"uses":[64],"a":[65,97,169],"parallel":[66],"implementation":[67],"suffix":[70,110],"array":[71,111],"neighbourhood":[72],"(SANS)":[74],"technique":[75],"achieve":[77,168],"high":[78],"speed":[79,126],"provides":[81],"several":[82],"modes":[83],"allow":[85],"for":[86,153],"greater":[87],"expense":[91],"performance.":[93],"RESULTS:":[94],"We":[95],"present":[96],"new":[98],"approach":[99],"called":[100,114],"asymmetric":[101],"SANS":[102,129],"together":[103],"with":[104],"scored":[105],"seeds":[106],"alternative":[109],"ordering":[112],"scheme":[113],"optimal":[115],"substitution":[116],"ordering.":[117],"These":[118],"techniques":[119],"dramatically":[120],"improve":[121],"both":[122],"approach.":[130],"Our":[131],"implementation,":[132],"TOPAZ,":[133],"one":[135,194],"top":[138],"performing":[139],"terms":[142],"speed,":[144,189],"scalability.":[147],"our":[149],"benchmark,":[150],"searching":[151],"UniProtKB":[152],"homologous":[154],"proteins":[155],"Dickeya":[158],"solani":[159],"proteome,":[160],"TOPAZ":[161,190],"took":[162],"less":[163],"than":[164],"3":[165],"minutes":[166],"0.84":[172],"compared":[173],"BLAST.":[175],"CONCLUSIONS:":[176],"Despite":[177],"stands":[191],"out":[192],"most":[197],"sensitive":[198],"highest":[200],"performance":[201],"currently":[203],"available.":[204]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
