{"id":"https://openalex.org/W2210725399","doi":"https://doi.org/10.1016/j.dib.2015.12.015","title":"Data for constructing insect genome content matrices for phylogenetic analysis and functional annotation","display_name":"Data for constructing insect genome content matrices for phylogenetic analysis and functional annotation","publication_year":2015,"publication_date":"2015-12-17","ids":{"openalex":"https://openalex.org/W2210725399","doi":"https://doi.org/10.1016/j.dib.2015.12.015","mag":"2210725399","pmid":"https://pubmed.ncbi.nlm.nih.gov/26862572","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/4707205"},"language":"en","primary_location":{"id":"doi:10.1016/j.dib.2015.12.015","doi":"https://doi.org/10.1016/j.dib.2015.12.015","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.dib.2015.12.015","pdf_url":"https://www.sciencedirect.com/science/article/pii/S2352340915003807/pdf","source":{"id":"https://openalex.org/S2481029507","display_name":"Data in Brief","issn_l":"2352-3409","issn":["2352-3409"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","jufo-1","ki-jl-1","norway-1","oarl","poland-40","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data in Brief","raw_type":"journal-article"},"volume":null,"type":"data-paper","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.sciencedirect.com/science/article/pii/S2352340915003807/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034922709","display_name":"Jeffrey Rosenfeld","orcid":"https://orcid.org/0000-0002-8750-2841","observed_orcids":["https://orcid.org/0000-0002-8750-2841"]},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]},{"id":"https://openalex.org/I1338124936","display_name":"American Museum of Natural History","ror":"https://ror.org/03thb3e06","country_code":"US","type":"archive","lineage":["https://openalex.org/I1338124936"]},{"id":"https://openalex.org/I4390039325","display_name":"Rutgers Cancer Institute","ror":"https://ror.org/0060x3y55","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I102322142","https://openalex.org/I4390039302","https://openalex.org/I4390039325"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey Rosenfeld","raw_affiliation_strings":["Sackler Institute for Comparative Genomics, American Museum of Natural History, New York, NY, USA; Cancer Institute of New Jersey, Rutgers University, New Brunswick, NJ, USA","Cancer Institute of New Jersey, Rutgers University, New Brunswick, NJ, USA","Sackler Institute for Comparative Genomics, American Museum of Natural History, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sackler Institute for Comparative Genomics, American Museum of Natural History, New York, NY, USA; Cancer Institute of New Jersey, Rutgers University, New Brunswick, NJ, USA","institution_ids":["https://openalex.org/I102322142","https://openalex.org/I1338124936","https://openalex.org/I4390039325"]},{"raw_affiliation_string":"Cancer Institute of New Jersey, Rutgers University, New Brunswick, NJ, USA","institution_ids":["https://openalex.org/I102322142","https://openalex.org/I4390039325"]},{"raw_affiliation_string":"Sackler Institute for Comparative Genomics, American Museum of Natural History, New York, NY, USA","institution_ids":["https://openalex.org/I1338124936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073240939","display_name":"Jonathan Foox","orcid":"https://orcid.org/0000-0002-5705-3985","observed_orcids":["https://orcid.org/0000-0002-5705-3985"]},"institutions":[{"id":"https://openalex.org/I1338124936","display_name":"American Museum of Natural History","ror":"https://ror.org/03thb3e06","country_code":"US","type":"archive","lineage":["https://openalex.org/I1338124936"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Foox","raw_affiliation_strings":["Sackler Institute for Comparative Genomics, American Museum of Natural History, New York, NY, USA; Division of Invertebrate Zoology, American Museum of Natural History, New York, NY, USA; Richard Gilder Graduate School, American Museum of Natural History, New York, NY, USA","Division of Invertebrate Zoology, American Museum of Natural History, New York, NY, USA","Richard Gilder Graduate School, American Museum of Natural History, New York, NY, USA","Sackler Institute for Comparative Genomics, American Museum of Natural History, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sackler Institute for Comparative Genomics, American Museum of Natural History, New York, NY, USA; Division of Invertebrate Zoology, American Museum of Natural History, New York, NY, USA; Richard Gilder Graduate School, American Museum of Natural History, New York, NY, USA","institution_ids":["https://openalex.org/I1338124936"]},{"raw_affiliation_string":"Division of Invertebrate Zoology, American Museum of Natural History, New York, NY, USA","institution_ids":["https://openalex.org/I1338124936"]},{"raw_affiliation_string":"Richard Gilder Graduate School, American Museum of Natural History, New York, NY, USA","institution_ids":["https://openalex.org/I1338124936"]},{"raw_affiliation_string":"Sackler Institute for Comparative Genomics, American Museum of Natural History, New York, NY, USA","institution_ids":["https://openalex.org/I1338124936"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011665083","display_name":"Rob DeSalle","orcid":"https://orcid.org/0000-0002-6490-7109","observed_orcids":["https://orcid.org/0000-0002-6490-7109"]},"institutions":[{"id":"https://openalex.org/I1338124936","display_name":"American Museum of Natural History","ror":"https://ror.org/03thb3e06","country_code":"US","type":"archive","lineage":["https://openalex.org/I1338124936"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rob DeSalle","raw_affiliation_strings":["Sackler Institute for Comparative Genomics, American Museum of Natural History, New York, NY, USA; Division of Invertebrate Zoology, American Museum of Natural History, New York, NY, USA; Richard Gilder Graduate School, American Museum of Natural History, New York, NY, USA","Division of Invertebrate Zoology, American Museum of Natural History, New York, NY, USA","Richard Gilder Graduate School, American Museum of Natural History, New York, NY, USA","Sackler Institute for Comparative Genomics, American Museum of Natural History, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sackler Institute for Comparative Genomics, American Museum of Natural History, New York, NY, USA; Division of Invertebrate Zoology, American Museum of Natural History, New York, NY, USA; Richard Gilder Graduate School, American Museum of Natural History, New York, NY, USA","institution_ids":["https://openalex.org/I1338124936"]},{"raw_affiliation_string":"Division of Invertebrate Zoology, American Museum of Natural History, New York, NY, USA","institution_ids":["https://openalex.org/I1338124936"]},{"raw_affiliation_string":"Richard Gilder Graduate School, American Museum of Natural History, New York, NY, USA","institution_ids":["https://openalex.org/I1338124936"]},{"raw_affiliation_string":"Sackler Institute for Comparative Genomics, American Museum of Natural History, New York, NY, USA","institution_ids":["https://openalex.org/I1338124936"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5011665083"],"corresponding_institution_ids":["https://openalex.org/I1338124936"],"apc_list":{"value":1220,"currency":"USD","value_usd":1220},"apc_paid":{"value":1220,"currency":"USD","value_usd":1220},"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"6","issue":null,"first_page":"279","last_page":"281"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9940999746322632,"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":0.9940999746322632,"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/T12606","display_name":"Diptera species taxonomy and behavior","score":0.0007999999797903001,"subfield":{"id":"https://openalex.org/subfields/1105","display_name":"Ecology, Evolution, Behavior and Systematics"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10702","display_name":"Insect and Arachnid Ecology and Behavior","score":0.0005000000237487257,"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/insect-phylogeny","display_name":"insect phylogeny","score":0.8650000095367432},{"id":"https://openalex.org/keywords/single-linkage-clustering","display_name":"single linkage clustering","score":0.7870000004768372},{"id":"https://openalex.org/keywords/core-genes","display_name":"core genes","score":0.7459999918937683},{"id":"https://openalex.org/keywords/gene-gain-and-loss","display_name":"gene gain and loss","score":0.746999979019165},{"id":"https://openalex.org/keywords/apomorphies","display_name":"apomorphies","score":0.7570000290870667},{"id":"https://openalex.org/keywords/functional-annotation","display_name":"functional annotation","score":0.6899999976158142},{"id":"https://openalex.org/keywords/consistency-index","display_name":"consistency index","score":0.6200000047683716},{"id":"https://openalex.org/keywords/insect-genomes","display_name":"insect genomes","score":0.4729999899864197}],"concepts":[{"id":"https://openalex.org/C193252679","wikidata":"https://www.wikidata.org/wiki/Q242125","display_name":"Phylogenetic tree","level":3,"score":0.8369222283363342},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.7323774695396423},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.6031977534294128},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.48256129026412964},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.43349310755729675},{"id":"https://openalex.org/C90132467","wikidata":"https://www.wikidata.org/wiki/Q171184","display_name":"Phylogenetics","level":3,"score":0.43141692876815796},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4222242832183838},{"id":"https://openalex.org/C42251679","wikidata":"https://www.wikidata.org/wiki/Q933491","display_name":"GC-content","level":4,"score":0.4146381914615631},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.3636590242385864},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.35394686460494995},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.23899272084236145},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.07599040865898132}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1016/j.dib.2015.12.015","doi":"https://doi.org/10.1016/j.dib.2015.12.015","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.dib.2015.12.015","pdf_url":"https://www.sciencedirect.com/science/article/pii/S2352340915003807/pdf","source":{"id":"https://openalex.org/S2481029507","display_name":"Data in Brief","issn_l":"2352-3409","issn":["2352-3409"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","jufo-1","ki-jl-1","norway-1","oarl","poland-40","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data in Brief","raw_type":"journal-article"},{"id":"pmh:oai:europepmc.org:3708951","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4707205","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,"listed_in":[],"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:4707205","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4707205","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,"listed_in":[],"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Brief","raw_type":"Text"},{"id":"pmid:26862572","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/26862572","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,"listed_in":[],"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":"Data in brief","raw_type":"Journal Article"},{"id":"pmh:oai:doaj.org/article:5870257efdde41f6aaf8e6860ca39b42","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/5870257efdde41f6aaf8e6860ca39b42","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,"listed_in":[],"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":"Data in Brief, Vol 6, Iss , Pp 279-281 (2016)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1016/j.dib.2015.12.015","doi":"https://doi.org/10.1016/j.dib.2015.12.015","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.dib.2015.12.015","pdf_url":"https://www.sciencedirect.com/science/article/pii/S2352340915003807/pdf","source":{"id":"https://openalex.org/S2481029507","display_name":"Data in Brief","issn_l":"2352-3409","issn":["2352-3409"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","jufo-1","ki-jl-1","norway-1","oarl","poland-40","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data in Brief","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2210725399.pdf","grobid_xml":"https://content.openalex.org/works/W2210725399.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W2061912939","https://openalex.org/W2124954099","https://openalex.org/W2148957995"],"related_works":["https://openalex.org/W2148957995","https://openalex.org/W2550042340","https://openalex.org/W2114324651","https://openalex.org/W2544330939","https://openalex.org/W6892067889","https://openalex.org/W6887853434","https://openalex.org/W2907533318","https://openalex.org/W2006895104","https://openalex.org/W1997174525","https://openalex.org/W2267615460"],"abstract_inverted_index":{"Twenty":[0],"one":[1],"fully":[2],"sequenced":[3],"and":[4,19,40,97,106,132,134,139],"well":[5],"annotated":[6],"insect":[7,23,104],"genomes":[8,55],"were":[9],"used":[10,36,56,72],"to":[11,57],"construct":[12,58],"genome":[13,60],"content":[14,61],"matrices":[15,71],"for":[16,129,141],"phylogenetic":[17,62,74,86],"analysis":[18],"functional":[20],"annotation":[21],"of":[22,29,53,113,119,137],"genomes.":[24],"To":[25],"examine":[26],"the":[27,54,59,69,81,93,126],"role":[28],"e-value":[30,38],"cutoff":[31],"in":[32,73,102,125],"ortholog":[33],"determination":[34],"we":[35],"scaled":[37],"cutoffs":[39],"a":[41,51,65,77,108,111],"single":[42],"linkage":[43],"clustering":[44],"approach..":[45],"The":[46],"present":[47],"communication":[48],"includes":[49],"(1)":[50],"list":[52],"matrices,":[63],"(2)":[64],"nexus":[66,78],"file":[67,79,91],"with":[68,80],"data":[70,127],"analysis,":[75,87],"(3)":[76],"Newick":[82],"trees":[83],"generated":[84],"by":[85],"(4)":[88],"an":[89],"excel":[90],"listing":[92],"Core":[94],"(CORE)":[95],"genes":[96,100,121],"Unique":[98],"(UNI)":[99],"found":[101],"five":[103],"groups,":[105],"(5)":[107],"figure":[109],"showing":[110],"plot":[112],"consistency":[114,143],"index":[115,144],"(CI)":[116,145],"versus":[117],"percent":[118],"unannotated":[120],"that":[122],"are":[123],"apomorphies":[124],"set":[128],"gene":[130],"losses":[131,140],"gains":[133,138],"bar":[135],"plots":[136],"four":[142],"cutoffs.":[146]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2016-06-24T00:00:00"}