{"id":"https://openalex.org/W1964320560","doi":"https://doi.org/10.1186/1471-2105-10-112","title":"Island method for estimating the statistical significance of profile-profile alignment scores","display_name":"Island method for estimating the statistical significance of profile-profile alignment scores","publication_year":2009,"publication_date":"2009-04-20","ids":{"openalex":"https://openalex.org/W1964320560","doi":"https://doi.org/10.1186/1471-2105-10-112","mag":"1964320560","pmid":"https://pubmed.ncbi.nlm.nih.gov/19379500"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-10-112","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-10-112","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-10-112","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/counter/pdf/10.1186/1471-2105-10-112","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046539917","display_name":"Aleksandar Poleksi\u0107","orcid":"https://orcid.org/0000-0002-6444-0350"},"institutions":[{"id":"https://openalex.org/I119234918","display_name":"University of Northern Iowa","ror":"https://ror.org/02h4qpx12","country_code":"US","type":"education","lineage":["https://openalex.org/I119234918"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Aleksandar Poleksic","raw_affiliation_strings":["Department of Computer Science, University of Northern Iowa, Cedar Falls, IA 50614, USA. poleksic@cs.uni.edu","Department of Computer Science, University of Northern Iowa, Cedar Falls, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Northern Iowa, Cedar Falls, IA 50614, USA. poleksic@cs.uni.edu","institution_ids":["https://openalex.org/I119234918"]},{"raw_affiliation_string":"Department of Computer Science, University of Northern Iowa, Cedar Falls, USA","institution_ids":["https://openalex.org/I119234918"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5046539917"],"corresponding_institution_ids":["https://openalex.org/I119234918"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":0.54,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.65074219,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"10","issue":"1","first_page":"112","last_page":"112"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.7687000036239624,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.7687000036239624,"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/T11162","display_name":"Enzyme Structure and Function","score":0.04610000178217888,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials 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":0.043699998408555984,"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/gumbel-distribution","display_name":"Gumbel distribution","score":0.759514331817627},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6985810995101929},{"id":"https://openalex.org/keywords/shuffling","display_name":"Shuffling","score":0.5880835652351379},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5379173755645752},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.5026922225952148},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.44948655366897583},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.382292777299881},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3787418007850647},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35997474193573},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.34445446729660034},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28103530406951904},{"id":"https://openalex.org/keywords/extreme-value-theory","display_name":"Extreme value theory","score":0.1418936550617218}],"concepts":[{"id":"https://openalex.org/C137610916","wikidata":"https://www.wikidata.org/wiki/Q1096862","display_name":"Gumbel distribution","level":3,"score":0.759514331817627},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6985810995101929},{"id":"https://openalex.org/C167927819","wikidata":"https://www.wikidata.org/wiki/Q1930567","display_name":"Shuffling","level":2,"score":0.5880835652351379},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5379173755645752},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.5026922225952148},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44948655366897583},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.382292777299881},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3787418007850647},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35997474193573},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34445446729660034},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28103530406951904},{"id":"https://openalex.org/C147581598","wikidata":"https://www.wikidata.org/wiki/Q729429","display_name":"Extreme value theory","level":2,"score":0.1418936550617218},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[{"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":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":6,"locations":[{"id":"doi:10.1186/1471-2105-10-112","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-10-112","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-10-112","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:19379500","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/19379500","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:scholarworks.uni.edu:cmp_facpub-1002","is_oa":true,"landing_page_url":"https://scholarworks.uni.edu/cmp_facpub/3","pdf_url":null,"source":{"id":"https://openalex.org/S4377196489","display_name":"UNI ScholarWorks (University of Northern Iowa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119234918","host_organization_name":"University of Northern Iowa","host_organization_lineage":["https://openalex.org/I119234918"],"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":"Faculty Publications","raw_type":"text"},{"id":"pmh:oai:scholarworks.uni.edu:facpub-3261","is_oa":false,"landing_page_url":"https://scholarworks.uni.edu/facpub/2260","pdf_url":null,"source":{"id":"https://openalex.org/S4377196489","display_name":"UNI ScholarWorks (University of Northern Iowa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119234918","host_organization_name":"University of Northern Iowa","host_organization_lineage":["https://openalex.org/I119234918"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Faculty Publications","raw_type":"text"},{"id":"pmh:oai:doaj.org/article:f39c10bcfb514f02b9554472aaf14e3c","is_oa":false,"landing_page_url":"https://doaj.org/article/f39c10bcfb514f02b9554472aaf14e3c","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 10, Iss 1, p 112 (2009)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:2678096","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2678096","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-10-112","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-10-112","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-10-112","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1964320560.pdf","grobid_xml":"https://content.openalex.org/works/W1964320560.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W626058384","https://openalex.org/W1530714294","https://openalex.org/W1659313070","https://openalex.org/W1834266941","https://openalex.org/W1983698816","https://openalex.org/W1996112765","https://openalex.org/W1996357466","https://openalex.org/W2005576892","https://openalex.org/W2012924461","https://openalex.org/W2015292449","https://openalex.org/W2024239868","https://openalex.org/W2026257220","https://openalex.org/W2026586467","https://openalex.org/W2032295681","https://openalex.org/W2033177501","https://openalex.org/W2034123395","https://openalex.org/W2045067706","https://openalex.org/W2051085340","https://openalex.org/W2052599790","https://openalex.org/W2055043387","https://openalex.org/W2062693912","https://openalex.org/W2070220641","https://openalex.org/W2071274932","https://openalex.org/W2085277871","https://openalex.org/W2087064593","https://openalex.org/W2089035513","https://openalex.org/W2094519647","https://openalex.org/W2097972395","https://openalex.org/W2099075703","https://openalex.org/W2102677343","https://openalex.org/W2106108593","https://openalex.org/W2109533003","https://openalex.org/W2118581189","https://openalex.org/W2120122292","https://openalex.org/W2131724426","https://openalex.org/W2145268834","https://openalex.org/W2145476180","https://openalex.org/W2146296021","https://openalex.org/W2147667050","https://openalex.org/W2150483438","https://openalex.org/W2155480346","https://openalex.org/W2158714788","https://openalex.org/W2170025018","https://openalex.org/W2170962128","https://openalex.org/W2171656629","https://openalex.org/W2312194337","https://openalex.org/W2796537448","https://openalex.org/W4229723287","https://openalex.org/W4236154753","https://openalex.org/W4246726420","https://openalex.org/W4253986630","https://openalex.org/W4255875578"],"related_works":["https://openalex.org/W4213239787","https://openalex.org/W2045745654","https://openalex.org/W2114337652","https://openalex.org/W4388857216","https://openalex.org/W4377131110","https://openalex.org/W4294559962","https://openalex.org/W2046590706","https://openalex.org/W4390419005","https://openalex.org/W2949444602","https://openalex.org/W1587991081"],"abstract_inverted_index":{"BACKGROUND:":[0],"In":[1],"the":[2,35,48,57,78,92,119,141,159,168],"last":[3],"decade,":[4],"a":[5,38,153,163],"significant":[6],"improvement":[7],"in":[8,22,175],"detecting":[9],"remote":[10],"similarity":[11],"between":[12],"protein":[13],"sequences":[14],"has":[15,162],"been":[16],"made":[17],"by":[18,64],"utilizing":[19],"alignment":[20,40,53,83,142],"profiles":[21,103],"place":[23],"of":[24,37,41,50,56,81,102,104,112,156],"amino-acid":[25],"strings.":[26],"Unfortunately,":[27],"no":[28],"analytical":[29],"theory":[30],"is":[31,55],"available":[32],"for":[33,99,122,140,172],"estimating":[34,61],"significance":[36],"gapped":[39],"two":[42,157],"profiles.":[43],"Many":[44],"experiments":[45],"suggest":[46],"that":[47,77,109],"distribution":[49,62,80,93],"local":[51],"profile-profile":[52,82,123,133],"scores":[54,84,148],"Gumbel":[58],"form.":[59],"However,":[60],"parameters":[63,94,114],"random":[65],"simulations":[66],"turns":[67],"out":[68],"to":[69,132,135],"be":[70,96,116,130,150],"computationally":[71],"very":[72],"expensive.":[73],"RESULTS:":[74],"We":[75,106],"demonstrate":[76],"background":[79],"heavily":[85],"depends":[86],"on":[87],"profiles'":[88],"composition":[89],"and":[90],"thus":[91],"must":[95],"estimated":[97],"independently,":[98],"each":[100],"pair":[101],"interest.":[105],"also":[107],"show":[108],"accurate":[110],"estimates":[111],"statistical":[113],"can":[115,129,149],"obtained":[117],"using":[118],"\"island":[120],"statistics\"":[121],"alignments.":[124],"CONCLUSION:":[125],"The":[126],"island":[127,147,160],"statistics":[128],"generalized":[131],"alignments":[134],"provide":[136],"an":[137],"efficient":[138],"method":[139,161,171],"score":[143],"normalization.":[144],"Since":[145],"multiple":[146],"extracted":[151],"from":[152],"single":[154],"comparison":[155],"profiles,":[158],"clear":[164],"speed":[165],"advantage":[166],"over":[167],"direct":[169],"shuffling":[170],"comparable":[173],"accuracy":[174],"parameter":[176],"estimates.":[177]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}