{"id":"https://openalex.org/W1993978523","doi":"https://doi.org/10.1186/1471-2105-9-s9-s2","title":"Validation of an NSP-based (negative selection pattern) gene family identification strategy","display_name":"Validation of an NSP-based (negative selection pattern) gene family identification strategy","publication_year":2008,"publication_date":"2008-08-12","ids":{"openalex":"https://openalex.org/W1993978523","doi":"https://doi.org/10.1186/1471-2105-9-s9-s2","mag":"1993978523","pmid":"https://pubmed.ncbi.nlm.nih.gov/18793465"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-9-s9-s2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-9-s9-s2","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-9-S9-S2","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/10.1186/1471-2105-9-S9-S2","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041290640","display_name":"Ronald Frank","orcid":"https://orcid.org/0000-0003-2683-6511"},"institutions":[{"id":"https://openalex.org/I20382870","display_name":"Missouri University of Science and Technology","ror":"https://ror.org/00scwqd12","country_code":"US","type":"education","lineage":["https://openalex.org/I20382870"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ronald L Frank","raw_affiliation_strings":["Biological Sciences Department, Missouri S&T, Rolla, MO 65409, USA. rfrank@mst.edu","Biological Sciences Department, Missouri S&T, Rolla, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biological Sciences Department, Missouri S&T, Rolla, MO 65409, USA. rfrank@mst.edu","institution_ids":["https://openalex.org/I20382870"]},{"raw_affiliation_string":"Biological Sciences Department, Missouri S&T, Rolla, USA","institution_ids":["https://openalex.org/I20382870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009112568","display_name":"Cyriac Kandoth","orcid":"https://orcid.org/0000-0002-1345-3573"},"institutions":[{"id":"https://openalex.org/I20382870","display_name":"Missouri University of Science and Technology","ror":"https://ror.org/00scwqd12","country_code":"US","type":"education","lineage":["https://openalex.org/I20382870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cyriac Kandoth","raw_affiliation_strings":["Computer Science Department, Missouri S&T, Rolla, MO, 65409, USA","Computer Science Department, Missouri S&T, Rolla, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Missouri S&T, Rolla, MO, 65409, USA","institution_ids":["https://openalex.org/I20382870"]},{"raw_affiliation_string":"Computer Science Department, Missouri S&T, Rolla, USA","institution_ids":["https://openalex.org/I20382870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006592299","display_name":"Fikret Er\u00e7al","orcid":null},"institutions":[{"id":"https://openalex.org/I20382870","display_name":"Missouri University of Science and Technology","ror":"https://ror.org/00scwqd12","country_code":"US","type":"education","lineage":["https://openalex.org/I20382870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fikret Ercal","raw_affiliation_strings":["Computer Science Department, Missouri S&T, Rolla, MO, 65409, USA","Computer Science Department, Missouri S&T, Rolla, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Missouri S&T, Rolla, MO, 65409, USA","institution_ids":["https://openalex.org/I20382870"]},{"raw_affiliation_string":"Computer Science Department, Missouri S&T, Rolla, USA","institution_ids":["https://openalex.org/I20382870"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5041290640"],"corresponding_institution_ids":["https://openalex.org/I20382870"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":0.5199,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.63974407,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"9","issue":"S9","first_page":"S2","last_page":"S2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.23589999973773956,"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":0.23589999973773956,"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/T11468","display_name":"Genetic Mapping and Diversity in Plants and Animals","score":0.20229999721050262,"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/T10012","display_name":"Genetic diversity and population structure","score":0.056299999356269836,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/dna-microarray","display_name":"DNA microarray","score":0.6560596227645874},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6396833062171936},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.6188800930976868},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6105570793151855},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.545712947845459},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.5348206162452698},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.4954921007156372},{"id":"https://openalex.org/keywords/gene-selection","display_name":"Gene selection","score":0.41124364733695984},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.35161781311035156},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.3293062150478363},{"id":"https://openalex.org/keywords/microarray-analysis-techniques","display_name":"Microarray analysis techniques","score":0.2815699577331543},{"id":"https://openalex.org/keywords/gene-expression","display_name":"Gene expression","score":0.18206876516342163},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14549079537391663}],"concepts":[{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.6560596227645874},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6396833062171936},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6188800930976868},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6105570793151855},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.545712947845459},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.5348206162452698},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.4954921007156372},{"id":"https://openalex.org/C2984324147","wikidata":"https://www.wikidata.org/wiki/Q3080021","display_name":"Gene selection","level":5,"score":0.41124364733695984},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.35161781311035156},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.3293062150478363},{"id":"https://openalex.org/C8415881","wikidata":"https://www.wikidata.org/wiki/Q6839217","display_name":"Microarray analysis techniques","level":4,"score":0.2815699577331543},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.18206876516342163},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14549079537391663},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D002874","descriptor_name":"Chromosome Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D002874","descriptor_name":"Chromosome Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D002874","descriptor_name":"Chromosome Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D005810","descriptor_name":"Multigene Family","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D005810","descriptor_name":"Multigene Family","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D005810","descriptor_name":"Multigene Family","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012641","descriptor_name":"Selection, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012641","descriptor_name":"Selection, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012641","descriptor_name":"Selection, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017360","descriptor_name":"Arabidopsis","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D017360","descriptor_name":"Arabidopsis","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D017360","descriptor_name":"Arabidopsis","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D018745","descriptor_name":"Genome, Plant","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D018745","descriptor_name":"Genome, Plant","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D018745","descriptor_name":"Genome, Plant","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D020224","descriptor_name":"Expressed Sequence Tags","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020224","descriptor_name":"Expressed Sequence Tags","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020224","descriptor_name":"Expressed Sequence Tags","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D029681","descriptor_name":"Arabidopsis Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D029681","descriptor_name":"Arabidopsis Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D029681","descriptor_name":"Arabidopsis Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1186/1471-2105-9-s9-s2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-9-s9-s2","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-9-S9-S2","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:18793465","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/18793465","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:98445c33278c4b6e81b12f3640915d33","is_oa":true,"landing_page_url":"https://doaj.org/article/98445c33278c4b6e81b12f3640915d33","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 9, Iss Suppl 9, p S2 (2008)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:2537573","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2537573","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:10.1186/1471-2105-9-s9-s2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-9-s9-s2","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-9-S9-S2","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/W1993978523.pdf","grobid_xml":"https://content.openalex.org/works/W1993978523.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W946643615","https://openalex.org/W1135241613","https://openalex.org/W1185101214","https://openalex.org/W1598933278","https://openalex.org/W1603607306","https://openalex.org/W1784978584","https://openalex.org/W1832626394","https://openalex.org/W1907806866","https://openalex.org/W1972007609","https://openalex.org/W1980779265","https://openalex.org/W2003792005","https://openalex.org/W2046183549","https://openalex.org/W2049389010","https://openalex.org/W2053534324","https://openalex.org/W2063291945","https://openalex.org/W2063489864","https://openalex.org/W2066471094","https://openalex.org/W2072603644","https://openalex.org/W2081702874","https://openalex.org/W2094448442","https://openalex.org/W2104189907","https://openalex.org/W2106861238","https://openalex.org/W2109348952","https://openalex.org/W2122821321","https://openalex.org/W2124786890","https://openalex.org/W2140604686","https://openalex.org/W2142512145","https://openalex.org/W2143693649","https://openalex.org/W2152075687","https://openalex.org/W2155421142","https://openalex.org/W2166085889","https://openalex.org/W2166265186","https://openalex.org/W2305923397"],"related_works":["https://openalex.org/W4205762803","https://openalex.org/W2535856026","https://openalex.org/W2898732673","https://openalex.org/W2410053581","https://openalex.org/W2383658677","https://openalex.org/W3123203398","https://openalex.org/W2265065644","https://openalex.org/W4313016600","https://openalex.org/W1533508595","https://openalex.org/W2155345760"],"abstract_inverted_index":{"BACKGROUND:":[0],"Gene":[1],"family":[2,37,47,96,130,165],"identification":[3,38],"from":[4,74,137],"ESTs":[5,136],"can":[6,179],"be":[7,70,180],"a":[8,34],"valuable":[9],"resource":[10],"for":[11,22],"analysis":[12],"of":[13,106,114,126,157],"genome":[14,26],"evolution":[15],"but":[16],"presents":[17],"unique":[18],"challenges":[19],"in":[20,62,85,98,161,167,187],"organisms":[21],"which":[23],"the":[24,81,100,107,115,127,138,148,155,158],"entire":[25],"is":[27],"not":[28],"yet":[29,196],"sequenced.":[30],"We":[31,153],"have":[32],"developed":[33],"novel":[35],"gene":[36,60,83,101,109,121,129,149,164,185],"method":[39,93],"based":[40],"on":[41,57],"negative":[42],"selection":[43],"patterns":[44],"(NSP)":[45],"between":[46],"members":[48,97,105,112,125,166],"to":[49,64,80,182],"screen":[50],"EST-generated":[51],"contigs.":[52],"This":[53],"strategy":[54,160,178],"was":[55],"tested":[56],"five":[58],"known":[59],"families":[61,102,186],"Arabidopsis":[63,168],"see":[65],"if":[66],"individual":[67],"paralogs":[68],"could":[69],"identified":[71,95],"with":[72],"accuracy":[73],"EST":[75,171],"data":[76,145,172],"alone":[77],"when":[78,141],"compared":[79],"actual":[82],"sequences":[84],"this":[86,177],"fully":[87],"sequenced":[88],"genome.":[89],"RESULTS:":[90],"The":[91],"NSP":[92,159],"uniquely":[94],"all":[99,135],"tested.":[103],"Two":[104],"FtsH":[108],"family,":[110],"three":[111],"each":[113],"PAL,":[116],"RF1,":[117],"and":[118,123,173],"ribosomal":[119],"L6":[120],"families,":[122],"four":[124],"CAD":[128],"were":[131],"correctly":[132],"identified.":[133],"Additionally":[134],"representative":[139],"contigs":[140],"checked":[142],"against":[143],"MapViewer":[144],"successfully":[146],"identify":[147,183],"locus":[150],"predicted.":[151],"CONCLUSION:":[152],"demonstrate":[154],"effectiveness":[156],"identifying":[162],"specific":[163],"using":[169],"only":[170],"we":[174],"describe":[175],"how":[176],"used":[181],"many":[184],"agronomically":[188],"important":[189],"crop":[190],"species":[191],"where":[192],"they":[193],"are":[194],"as":[195],"undiscovered.":[197]},"counts_by_year":[{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
