{"id":"https://openalex.org/W2995795539","doi":"https://doi.org/10.1093/molbev/msz284","title":"Estimating Pangenomes with Roary","display_name":"Estimating Pangenomes with Roary","publication_year":2019,"publication_date":"2019-12-03","ids":{"openalex":"https://openalex.org/W2995795539","doi":"https://doi.org/10.1093/molbev/msz284","mag":"2995795539","pmid":"https://pubmed.ncbi.nlm.nih.gov/31848603","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/7038658"},"language":"en","primary_location":{"id":"doi:10.1093/molbev/msz284","doi":"https://doi.org/10.1093/molbev/msz284","is_oa":true,"landing_page_url":"https://doi.org/10.1093/molbev/msz284","pdf_url":"https://academic.oup.com/mbe/article-pdf/37/3/933/32618436/msz284.pdf","source":{"id":"https://openalex.org/S57552105","display_name":"Molecular Biology and Evolution","issn_l":"0737-4038","issn":["0737-4038","1537-1719"],"is_oa":false,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-a","jufo-3","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1"],"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Molecular Biology and Evolution","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://academic.oup.com/mbe/article-pdf/37/3/933/32618436/msz284.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091205522","display_name":"Farrah Sitto","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I177721651","display_name":"Oakland University","ror":"https://ror.org/01ythxj32","country_code":"US","type":"education","lineage":["https://openalex.org/I177721651"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Farrah Sitto","raw_affiliation_strings":["Department of Biological Sciences, Oakland University, Rochester, MI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biological Sciences, Oakland University, Rochester, MI","institution_ids":["https://openalex.org/I177721651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085701739","display_name":"Fabia Ursula Battistuzzi","orcid":"https://orcid.org/0000-0003-1852-2934","observed_orcids":["https://orcid.org/0000-0003-1852-2934"]},"institutions":[{"id":"https://openalex.org/I177721651","display_name":"Oakland University","ror":"https://ror.org/01ythxj32","country_code":"US","type":"education","lineage":["https://openalex.org/I177721651"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Fabia U Battistuzzi","raw_affiliation_strings":["Center for Data Science and Big Data Analytics, Oakland University, Rochester, MI","Department of Biological Sciences, Oakland University, Rochester, MI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Data Science and Big Data Analytics, Oakland University, Rochester, MI","institution_ids":["https://openalex.org/I177721651"]},{"raw_affiliation_string":"Department of Biological Sciences, Oakland University, Rochester, MI","institution_ids":["https://openalex.org/I177721651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5085701739"],"corresponding_institution_ids":["https://openalex.org/I177721651"],"apc_list":{"value":3418,"currency":"USD","value_usd":3418},"apc_paid":{"value":3418,"currency":"USD","value_usd":3418},"fwci":1.9018,"has_fulltext":true,"cited_by_count":87,"citation_normalized_percentile":{"value":0.8672458,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":"37","issue":"3","first_page":"933","last_page":"939"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9994999766349792,"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":0.9994999766349792,"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/T10434","display_name":"Chromosomal and Genetic Variations","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.0,"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/pan-genome","display_name":"pan-genome","score":0.8730000257492065},{"id":"https://openalex.org/keywords/roary","display_name":"Roary","score":0.9779999852180481},{"id":"https://openalex.org/keywords/core-genes","display_name":"core genes","score":0.7070000171661377},{"id":"https://openalex.org/keywords/accessory-genes","display_name":"accessory genes","score":0.9980000257492065},{"id":"https://openalex.org/keywords/gene-presence-absence","display_name":"gene presence/absence","score":0.9020000100135803},{"id":"https://openalex.org/keywords/gene-repertoire","display_name":"gene repertoire","score":0.7239999771118164},{"id":"https://openalex.org/keywords/comparative-genomics","display_name":"comparative genomics","score":0.6420000195503235},{"id":"https://openalex.org/keywords/bacterial-genomes","display_name":"bacterial genomes","score":0.4569999873638153}],"concepts":[{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.9220637083053589},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.7448122501373291},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.7284610867500305},{"id":"https://openalex.org/C2778473898","wikidata":"https://www.wikidata.org/wiki/Q2145110","display_name":"Repertoire","level":2,"score":0.6850898265838623},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.49647265672683716},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.47750991582870483},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.4063647389411926},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[{"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":false},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D010641","descriptor_name":"Phenotype","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":false},{"descriptor_ui":"D013045","descriptor_name":"Species Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/molbev/msz284","doi":"https://doi.org/10.1093/molbev/msz284","is_oa":true,"landing_page_url":"https://doi.org/10.1093/molbev/msz284","pdf_url":"https://academic.oup.com/mbe/article-pdf/37/3/933/32618436/msz284.pdf","source":{"id":"https://openalex.org/S57552105","display_name":"Molecular Biology and Evolution","issn_l":"0737-4038","issn":["0737-4038","1537-1719"],"is_oa":false,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-a","jufo-3","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1"],"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Molecular Biology and Evolution","raw_type":"journal-article"},{"id":"pmh:oai:pubmedcentral.nih.gov:7038658","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7038658","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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Mol Biol Evol","raw_type":"Text"},{"id":"pmid:31848603","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31848603","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":"Molecular biology and evolution","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1093/molbev/msz284","doi":"https://doi.org/10.1093/molbev/msz284","is_oa":true,"landing_page_url":"https://doi.org/10.1093/molbev/msz284","pdf_url":"https://academic.oup.com/mbe/article-pdf/37/3/933/32618436/msz284.pdf","source":{"id":"https://openalex.org/S57552105","display_name":"Molecular Biology and Evolution","issn_l":"0737-4038","issn":["0737-4038","1537-1719"],"is_oa":false,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-a","jufo-3","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1"],"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Molecular Biology and Evolution","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2466576084","display_name":"SCIENCE GOALS: WHEN RECONSTRUCTING EVOLUTIONARY HISTORIES OF LIFE ON EARTH PRIMARY SOURCES OF INFORMATION ARE GEOLOGIC DATA  APPLICABLE MOSTLY TO PHANEROZOIC LIFE FORMS  AND MOLECULAR DATA FOR PRE-CAMBRIAN LIFE. TIMELINES INFERRED FROM THESE TWO SOURCES ARE GENERALLY IN AGREEMENT BUT MAJOR CHALLENGES FOR KEY EVOLUTIONARY STEPS REMAIN. THIS IS ESPECIALLY TRUE FOR TIMELINES OF EARLY MICROBIAL LIFE THAT  DUE TO THE ALMOST COMPLETE LACK OF GEOLOGIC RECORD  ARE HEAVILY DEPENDENT ON MOLECULAR-BASED APPROACHES THAT OFTEN PRODUCE CONTRASTING EVOLUTIONARY HISTORIES. TO IMPROVE THE CONFIDENCE IN THE ESTIMATED TIMELINES IT IS THEREFORE IMPERATIVE TO (I) RECONCILE CONTRASTING TIMELINES FROM MOLECULAR DATA WITH EACH OTHER AND ALSO WITH THE GEOLOGIC TIMELINE AND (II) DESIGN AN OBJECTIVE PROCEDURE TO IDENTIFY BIASES IN ESTIMATIONS EVEN IN CASES WHEN ALTERNATIVE INDEPENDENT EVIDENCE IS LACKING. OBJECTIVES: IN RESPONSE TO THESE NEEDS  HERE WE PROPOSE TO ESTABLISH AN OBJECTIVE AND COMPUTATIONALLY EASY PROCEDURE TO EVALUATE THE ACCURACY OF PUBLISHED AND FUTURE TIMETREES THAT WILL LEAD TO MORE ACCURATE AND CONCORDANT TIMELINES. OUR METHOD INVESTIGATES THE PARAMETERS ASSOCIATED WITH CALIBRATION POINTS AND EVOLUTIONARY RATE VARIATION AMONG LINEAGES  PARAMETERS THAT ARE KNOWN TO AFFECT THE ACCURACY OF RELAXED MOLECULAR CLOCKS. WE PROPOSE TO USE A RELATIVE FRAMEWORK ESTABLISHED FROM PRIOR-FREE MODELS (FOURTH GENERATION MOLECULAR CLOCKS) TO DETECT BIASES IN THESE PARAMETERS  WHICH CAN THEN BE REMOVED TO INCREASE ACCURACY OF INDIVIDUAL ESTIMATES. WE SHOW PRELIMINARY DATA FROM THE APPLICATION OF THE PROPOSED APPROACH IN SIMULATED SCENARIOS AND AN EMPIRICAL DATASET RELATED TO A HIGHLY CONTROVERSIAL EVOLUTIONARY EVENT  THE TIMELINE OF THE ORIGIN AND DIVERSIFICATION OF ANIMALS. THE RESULTS SUPPORT THE VALIDITY OF THE PROPOSED APPROACH THAT WE PLAN TO APPLY TO HUNDREDS OF PUBLISHED TIMETREES WITH KNOWN DISAGREEMENTS  IN AN EFFORT TO PRODUCE AN ACCURATE TIMELINE OF THE EVOLUTION OF LIFE. THE ESTABLISHED PROCEDURE WILL BE PARTICULARLY USEFUL IN INVESTIGATIONS OF EARLY MICROBIAL LIFE FOR WHICH MOLECULAR DATA IS VIRTUALLY THE ONLY RECORD OF THEIR EVOLUTIONARY HISTORY. METHODS: BASED ON THE OVERALL GOAL OF THIS PROPOSAL  WE HAVE IDENTIFIED TWO AIMS. IN AIM #1 WE WILL FOCUS ON THE EVALUATION OF CALIBRATION BOUNDARIES AND THEIR EFFECTS ON DIVERGENCE TIMES. THIS IS AN APPLIED AIM THAT WILL FIRST EVALUATE TIMETREES FROM THE LITERATURE TO IDENTIFY THE MOST COMMON WEAKNESSES AND RE-ESTIMATE NEW TIMETREES WITH IMPROVED PARAMETERS AND TAXONOMIC SAMPLING. THE OUTCOMES OF THIS AIM WILL BE THE FIRST LARGE-SCALE ASSESSMENT OF PUBLISHED TIMETREES AND THE ESTIMATION OF NEW  MORE ACCURATE  DIVERGENCE TIMES FOR A WIDE RANGE OF TAXONOMIC GROUPS FOCUSING ON EARLY MICROBIAL SPECIES. AIM #2 WILL PROVIDE THEORETICAL AND COMPUTATIONAL SUPPORT FOR THE APPLIED ANALYSIS OF THE PREVIOUS AIM BY INVESTIGATING DISTRIBUTIONS OF RATE VARIATION AMONG LINEAGES FOR DIFFERENT SIMULATED DATASETS. THESE DISTRIBUTIONS WILL SERVE AS REFERENCE TO DETERMINE PATTERNS OF RATE VARIATION IN EMPIRICAL DATA AND WILL PROVIDE INFORMATION TO OPTIMIZE OUR METHODOLOGY. THE NEW TESTING PROCEDURE DEVELOPED IN AIMS #1 AND #2 WILL THEN BE IMPLEMENTED IN A NEW SOFTWARE THAT WILL ALLOW EXPERTS AND NON-EXPERTS TO EVALUATE THE DEPENDENCY OF THEIR ESTIMATED DIVERGENCE TIMES ON THE CHOSEN PARAMETERS. SIGNIFICANCE: WE EXPECT THIS PROJECT TO BE HIGHLY SIGNIFICANT BECAUSE  BY IMPROVING MOLECULAR DATING METHODS  IT WILL PROVIDE THE MEANS TO ESTIMATE A TIMELINE OF THE EVOLUTION OF LIFE THAT WILL BRING INTO CLOSER AGREEMENT BIOLOGICAL  GEOLOGICAL  AND PALEONTOLOGICAL VIEWS OF THE CONDITIONS ON EARLY EARTH. RECONSTRUCTING A CHRONOLOGY OF LIFE ON EARTH HAS BEEN A LONGSTANDING GOAL IN ASTROBIOLOGY AS IT EMPOWERS RESEARCHERS TO DRAW INFERENCES ON THE CO-EVOLUTION OF LIFE AND HABITABLE CONDITIONS OF A PLANET.","funder_award_id":"NNX16AJ30G","funder_id":"https://openalex.org/F4320306101","funder_display_name":"National Aeronautics and Space Administration"},{"id":"https://openalex.org/G8900628686","display_name":"Understanding the evolution of pathogenicity with a genome complexity approach","funder_award_id":"R15GM121981","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320306101","display_name":"National Aeronautics and Space Administration","ror":"https://ror.org/027ka1x80"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2995795539.pdf","grobid_xml":"https://content.openalex.org/works/W2995795539.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1822648038","https://openalex.org/W1850890413","https://openalex.org/W2019188545","https://openalex.org/W2091328482","https://openalex.org/W2091543364","https://openalex.org/W2093610003","https://openalex.org/W2117207428","https://openalex.org/W2122673596","https://openalex.org/W2150550043","https://openalex.org/W2155090350","https://openalex.org/W2509995029","https://openalex.org/W2554414896","https://openalex.org/W2586159524","https://openalex.org/W2602439962","https://openalex.org/W2759456806","https://openalex.org/W2782987161","https://openalex.org/W2792874482","https://openalex.org/W2910230493","https://openalex.org/W2949102320","https://openalex.org/W2951254987"],"related_works":["https://openalex.org/W6889833190","https://openalex.org/W2122673596","https://openalex.org/W4411636213","https://openalex.org/W3021348214","https://openalex.org/W6901970328","https://openalex.org/W4399582088","https://openalex.org/W4375864669","https://openalex.org/W4390287042","https://openalex.org/W7001213335","https://openalex.org/W7133526448"],"abstract_inverted_index":{"A":[0],"description":[1],"of":[2,6,30,33,47,63,69,89],"the":[3,20,31,64,87],"genetic":[4],"makeup":[5],"a":[7,11,34,37,91,97],"species":[8,35],"based":[9],"on":[10,121],"single":[12],"genome":[13,126],"is":[14,36,96],"often":[15],"insufficient":[16],"because":[17],"it":[18,43],"ignores":[19],"variability":[21],"in":[22,60,113,124,134],"gene":[23,122],"repertoire":[24],"among":[25],"multiple":[26],"strains.":[27],"The":[28],"estimation":[29],"pangenome":[32,93],"solution":[38],"to":[39,76],"this":[40],"issue":[41],"as":[42],"provides":[44,101],"an":[45,103],"overview":[46,104],"genes":[48,56,70,109],"that":[49,57,100],"are":[50,58,131],"shared":[51],"by":[52],"all":[53],"strains":[54],"and":[55,82,107,136],"present":[59],"only":[61],"some":[62],"genomes.":[65],"These":[66],"different":[67],"sets":[68],"can":[71],"then":[72],"be":[73],"analyzed":[74],"functionally":[75],"explore":[77],"correlations":[78],"with":[79],"unique":[80],"phenotypes":[81],"adaptations.":[83],"This":[84],"protocol":[85],"presents":[86],"usage":[88],"Roary,":[90],"Linux-native":[92],"application.":[94],"Roary":[95],"straightforward":[98],"software":[99],"1)":[102],"about":[105],"core":[106],"accessory":[108],"for":[110,127],"those":[111],"interested":[112],"general":[114],"trends":[115],"and,":[116],"also,":[117],"2)":[118],"detailed":[119],"information":[120],"presence/absence":[123],"each":[125],"in-depth":[128],"analyses.":[129],"Results":[130],"provided":[132],"both":[133],"text":[135],"graphic":[137],"format.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":2}],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2019-12-26T00:00:00"}