{"id":"https://openalex.org/W3132950154","doi":"https://doi.org/10.1186/s12859-021-03981-4","title":"cognac: rapid generation of concatenated gene alignments for phylogenetic inference from large, bacterial whole genome sequencing datasets","display_name":"cognac: rapid generation of concatenated gene alignments for phylogenetic inference from large, bacterial whole genome sequencing datasets","publication_year":2021,"publication_date":"2021-02-15","ids":{"openalex":"https://openalex.org/W3132950154","doi":"https://doi.org/10.1186/s12859-021-03981-4","mag":"3132950154","pmid":"https://pubmed.ncbi.nlm.nih.gov/33588753"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-021-03981-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-021-03981-4","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-021-03981-4","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/s12859-021-03981-4","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091315007","display_name":"Ryan Crawford","orcid":"https://orcid.org/0000-0002-6173-6092"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryan D. Crawford","raw_affiliation_strings":["Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI, 48109, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI, 48109, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086283835","display_name":"Evan S. Snitkin","orcid":"https://orcid.org/0000-0001-8409-278X"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Evan S. Snitkin","raw_affiliation_strings":["Department of Microbiology and Immunology, University of Michigan, Ann Arbor, MI, 48109, USA. esnitkin@umich.edu","Department of Microbiology and Immunology, University of Michigan, Ann Arbor, MI, 48109, USA"],"raw_orcid":"https://orcid.org/0000-0001-8409-278X","affiliations":[{"raw_affiliation_string":"Department of Microbiology and Immunology, University of Michigan, Ann Arbor, MI, 48109, USA. esnitkin@umich.edu","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"Department of Microbiology and Immunology, University of Michigan, Ann Arbor, MI, 48109, USA","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5086283835"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":0.9771,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.73879598,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"22","issue":"1","first_page":"70","last_page":"70"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9854000210762024,"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":0.9854000210762024,"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/T13664","display_name":"Genome Rearrangement Algorithms","score":0.007799999788403511,"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/T10066","display_name":"Gut microbiota and health","score":0.0008999999845400453,"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/phylogenetic-tree","display_name":"Phylogenetic tree","score":0.7824783325195312},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.6410089731216431},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.560787558555603},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.5566838979721069},{"id":"https://openalex.org/keywords/dna-microarray","display_name":"DNA microarray","score":0.5183478593826294},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.5174829959869385},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4656798243522644},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.44513002038002014},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.4176778197288513},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.24291661381721497},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.09624618291854858},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.06169477105140686}],"concepts":[{"id":"https://openalex.org/C193252679","wikidata":"https://www.wikidata.org/wiki/Q242125","display_name":"Phylogenetic tree","level":3,"score":0.7824783325195312},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.6410089731216431},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.560787558555603},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.5566838979721069},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.5183478593826294},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.5174829959869385},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4656798243522644},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.44513002038002014},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.4176778197288513},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.24291661381721497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.09624618291854858},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.06169477105140686},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.0}],"mesh":[{"descriptor_ui":"D000073336","descriptor_name":"Whole Genome Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000073336","descriptor_name":"Whole Genome Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000073336","descriptor_name":"Whole Genome Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":true},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":true},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":true},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D005191","descriptor_name":"Family Characteristics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005191","descriptor_name":"Family Characteristics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005191","descriptor_name":"Family Characteristics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","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":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":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1186/s12859-021-03981-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-021-03981-4","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-021-03981-4","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:33588753","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33588753","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:deepblue.lib.umich.edu:2027.42/173436","is_oa":false,"landing_page_url":"https://hdl.handle.net/2027.42/173436","pdf_url":null,"source":{"id":"https://openalex.org/S4306400393","display_name":"Deep Blue (University of Michigan)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I27837315","host_organization_name":"University of Michigan","host_organization_lineage":["https://openalex.org/I27837315"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"},{"id":"pmh:oai:doaj.org/article:d015fd73dff04d3dabe8e331920223f2","is_oa":true,"landing_page_url":"https://doaj.org/article/d015fd73dff04d3dabe8e331920223f2","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 22, Iss 1, Pp 1-10 (2021)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:7885345","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7885345","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/s12859-021-03981-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-021-03981-4","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-021-03981-4","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":[{"id":"https://openalex.org/G3563940613","display_name":null,"funder_award_id":"T32GM070449","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G580482727","display_name":null,"funder_award_id":"T32 GM070449","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6724415921","display_name":null,"funder_award_id":"1R01AI148259 01","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"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/W3132950154.pdf","grobid_xml":"https://content.openalex.org/works/W3132950154.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W226607508","https://openalex.org/W1965584649","https://openalex.org/W1975548496","https://openalex.org/W1984836595","https://openalex.org/W2002638840","https://openalex.org/W2004548026","https://openalex.org/W2037654474","https://openalex.org/W2053767920","https://openalex.org/W2071465766","https://openalex.org/W2076960650","https://openalex.org/W2078969200","https://openalex.org/W2082473664","https://openalex.org/W2096093282","https://openalex.org/W2112364185","https://openalex.org/W2116913446","https://openalex.org/W2119022294","https://openalex.org/W2122673596","https://openalex.org/W2136096754","https://openalex.org/W2137076742","https://openalex.org/W2142503351","https://openalex.org/W2143485490","https://openalex.org/W2145514756","https://openalex.org/W2151409320","https://openalex.org/W2159325249","https://openalex.org/W2160378127","https://openalex.org/W2165699474","https://openalex.org/W2170747616","https://openalex.org/W2230694237","https://openalex.org/W2751583588","https://openalex.org/W2949236085","https://openalex.org/W2950150251","https://openalex.org/W2977580499","https://openalex.org/W2990925943","https://openalex.org/W3005014603","https://openalex.org/W3037274972","https://openalex.org/W4207066629","https://openalex.org/W4252288082"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W2087343574","https://openalex.org/W2121910908"],"abstract_inverted_index":{"BACKGROUND:":[0],"The":[1],"quantity":[2,20],"of":[3,21,88,93],"genomic":[4,73],"data":[5,23,61],"is":[6,51],"expanding":[7],"at":[8],"an":[9,102,121,137],"increasing":[10],"rate.":[11],"Tools":[12],"for":[13,43,70,84,124,129,146],"phylogenetic":[14,44,56,130],"analysis":[15],"which":[16,107],"scale":[17],"to":[18,37,53,148],"the":[19,98],"available":[22],"are":[24],"required.":[25],"To":[26,75],"address":[27],"this":[28],"need,":[29],"we":[30,79],"present":[31],"cognac,":[32],"a":[33,60,91],"user-friendly":[34],"software":[35],"package":[36,139],"rapidly":[38,54],"generate":[39,66],"concatenated":[40,67,126],"gene":[41,68,82,127],"alignments":[42,69,83,128],"analysis.":[45,131],"RESULTS:":[46],"We":[47,116,132],"illustrate":[48],"that":[49,118],"cognac":[50,119,135],"able":[52],"identify":[55],"marker":[57],"genes":[58],"using":[59],"driven":[62],"approach":[63],"and":[64],"efficiently":[65],"very":[71],"large":[72],"datasets.":[74],"benchmark":[76],"our":[77],"tool,":[78],"generated":[80],"core":[81],"eight":[85],"unique":[86],"genera":[87],"bacteria,":[89],"including":[90],"dataset":[92],"over":[94],"11,000":[95],"genomes":[96],"from":[97],"genus":[99],"Escherichia":[100],"producing":[101],"alignment":[103],"with":[104,143],"1353":[105],"genes,":[106],"was":[108],"constructed":[109],"in":[110],"less":[111],"than":[112],"17":[113],"h.":[114],"CONCLUSIONS:":[115],"demonstrate":[117],"presents":[120],"efficient":[122],"method":[123],"generating":[125],"have":[133],"released":[134],"as":[136],"R":[138],"(":[140],"https://github.com/rdcrawford/cognac":[141],")":[142],"customizable":[144],"parameters":[145],"adaptation":[147],"diverse":[149],"applications.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-10T00:00:00"}