{"id":"https://openalex.org/W3209431827","doi":"https://doi.org/10.1093/bioinformatics/btab752","title":"Density-based binning of gene clusters to infer function or evolutionary history using GeneGrouper","display_name":"Density-based binning of gene clusters to infer function or evolutionary history using GeneGrouper","publication_year":2021,"publication_date":"2021-10-29","ids":{"openalex":"https://openalex.org/W3209431827","doi":"https://doi.org/10.1093/bioinformatics/btab752","mag":"3209431827","pmid":"https://pubmed.ncbi.nlm.nih.gov/34734968"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btab752","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab752","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049826494","display_name":"Alexander McFarland","orcid":"https://orcid.org/0000-0002-1803-3623"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander G McFarland","raw_affiliation_strings":["Department of Civil and Environmental Engineering, Northwestern University , Evanston, IL 60208, USA"],"raw_orcid":"https://orcid.org/0000-0002-1803-3623","affiliations":[{"raw_affiliation_string":"Department of Civil and Environmental Engineering, Northwestern University , Evanston, IL 60208, USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082803142","display_name":"Nolan W. Kennedy","orcid":"https://orcid.org/0000-0002-2944-5439"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nolan W Kennedy","raw_affiliation_strings":["Department of Chemical and Biological Engineering, Northwestern University , Evanston, IL 60208, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemical and Biological Engineering, Northwestern University , Evanston, IL 60208, USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016315607","display_name":"Carolyn E. Mills","orcid":"https://orcid.org/0000-0001-6058-0762"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carolyn E Mills","raw_affiliation_strings":["Department of Chemical and Biological Engineering, Northwestern University , Evanston, IL 60208, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemical and Biological Engineering, Northwestern University , Evanston, IL 60208, USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075689223","display_name":"Danielle Tullman\u2010Ercek","orcid":"https://orcid.org/0000-0001-6734-480X"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Danielle Tullman-Ercek","raw_affiliation_strings":["Department of Chemical and Biological Engineering, Northwestern University , Evanston, IL 60208, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemical and Biological Engineering, Northwestern University , Evanston, IL 60208, USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008844345","display_name":"Curtis Huttenhower","orcid":"https://orcid.org/0000-0002-1110-0096"},"institutions":[{"id":"https://openalex.org/I107606265","display_name":"Broad Institute","ror":"https://ror.org/05a0ya142","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I107606265"]},{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Curtis Huttenhower","raw_affiliation_strings":["Department of Immunology and Infectious Diseases, Harvard T. H. Chan School of Public Health, Boston, MA 02115, USA","Departments of Biostatistics and Immunology and Infectious Diseases, Harvard T.H. Chan School of Public Health , Boston, MA 02115, USA","Harvard Chan Microbiome in Public Health Center, Harvard T. H. Chan School of Public Health, Boston, MA 02115, USA","Infectious Disease and Microbiome Program, Broad Institute of MIT and Harvard , Cambridge, MA 02142, USA"],"raw_orcid":"https://orcid.org/0000-0002-1110-0096","affiliations":[{"raw_affiliation_string":"Department of Immunology and Infectious Diseases, Harvard T. H. Chan School of Public Health, Boston, MA 02115, USA","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"Departments of Biostatistics and Immunology and Infectious Diseases, Harvard T.H. Chan School of Public Health , Boston, MA 02115, USA","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"Harvard Chan Microbiome in Public Health Center, Harvard T. H. Chan School of Public Health, Boston, MA 02115, USA","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"Infectious Disease and Microbiome Program, Broad Institute of MIT and Harvard , Cambridge, MA 02142, USA","institution_ids":["https://openalex.org/I107606265"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047718140","display_name":"Erica M. Hartmann","orcid":"https://orcid.org/0000-0002-0966-2014"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Erica M Hartmann","raw_affiliation_strings":["Department of Civil and Environmental Engineering, Northwestern University , Evanston, IL 60208, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Civil and Environmental Engineering, Northwestern University , Evanston, IL 60208, USA","institution_ids":["https://openalex.org/I111979921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5047718140"],"corresponding_institution_ids":["https://openalex.org/I111979921"],"apc_list":{"value":3478,"currency":"USD","value_usd":3478},"apc_paid":null,"fwci":0.4476,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.59352848,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":"38","issue":"3","first_page":"612","last_page":"620"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.6825000047683716,"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":0.6825000047683716,"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":0.03680000081658363,"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/T11048","display_name":"Bacteriophages and microbial interactions","score":0.036400001496076584,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pseudogene","display_name":"Pseudogene","score":0.8199693560600281},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.6845466494560242},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.6809449195861816},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.6742362976074219},{"id":"https://openalex.org/keywords/gene-cluster","display_name":"Gene cluster","score":0.662263810634613},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5828715562820435},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.5303581357002258},{"id":"https://openalex.org/keywords/gene-prediction","display_name":"Gene prediction","score":0.43064019083976746},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.42997509241104126},{"id":"https://openalex.org/keywords/orthologous-gene","display_name":"Orthologous Gene","score":0.4227927327156067},{"id":"https://openalex.org/keywords/homology","display_name":"Homology (biology)","score":0.4146236181259155},{"id":"https://openalex.org/keywords/evolutionary-biology","display_name":"Evolutionary biology","score":0.32090669870376587},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.1332024335861206}],"concepts":[{"id":"https://openalex.org/C34957205","wikidata":"https://www.wikidata.org/wiki/Q277338","display_name":"Pseudogene","level":4,"score":0.8199693560600281},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.6845466494560242},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.6809449195861816},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.6742362976074219},{"id":"https://openalex.org/C36857842","wikidata":"https://www.wikidata.org/wiki/Q1501261","display_name":"Gene cluster","level":3,"score":0.662263810634613},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5828715562820435},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.5303581357002258},{"id":"https://openalex.org/C105565629","wikidata":"https://www.wikidata.org/wiki/Q1248292","display_name":"Gene prediction","level":4,"score":0.43064019083976746},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.42997509241104126},{"id":"https://openalex.org/C2909108991","wikidata":"https://www.wikidata.org/wiki/Q414601","display_name":"Orthologous Gene","level":4,"score":0.4227927327156067},{"id":"https://openalex.org/C165525559","wikidata":"https://www.wikidata.org/wiki/Q224180","display_name":"Homology (biology)","level":3,"score":0.4146236181259155},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.32090669870376587},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.1332024335861206},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D005810","descriptor_name":"Multigene Family","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005810","descriptor_name":"Multigene Family","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005810","descriptor_name":"Multigene Family","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":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D064349","descriptor_name":"Genome, Microbial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D064349","descriptor_name":"Genome, Microbial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D064349","descriptor_name":"Genome, Microbial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btab752","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab752","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:34734968","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34734968","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":"Bioinformatics (Oxford, England)","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4042385825","display_name":null,"funder_award_id":"W911NF-19-1-0298","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"}],"funders":[{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W1605984840","https://openalex.org/W1832517154","https://openalex.org/W1858605697","https://openalex.org/W1908889304","https://openalex.org/W1963749370","https://openalex.org/W1999979510","https://openalex.org/W2004745913","https://openalex.org/W2008856488","https://openalex.org/W2012673943","https://openalex.org/W2014598704","https://openalex.org/W2031611770","https://openalex.org/W2041257508","https://openalex.org/W2042947619","https://openalex.org/W2085487226","https://openalex.org/W2090408264","https://openalex.org/W2099540110","https://openalex.org/W2114850508","https://openalex.org/W2124166542","https://openalex.org/W2126957790","https://openalex.org/W2131971159","https://openalex.org/W2134587758","https://openalex.org/W2136592243","https://openalex.org/W2142678478","https://openalex.org/W2142932602","https://openalex.org/W2144626747","https://openalex.org/W2160378127","https://openalex.org/W2171908015","https://openalex.org/W2173732482","https://openalex.org/W2179444328","https://openalex.org/W2187341651","https://openalex.org/W2276368784","https://openalex.org/W2345727655","https://openalex.org/W2476759866","https://openalex.org/W2509423360","https://openalex.org/W2513727910","https://openalex.org/W2527473185","https://openalex.org/W2740690937","https://openalex.org/W2752784701","https://openalex.org/W2760987883","https://openalex.org/W2767051074","https://openalex.org/W2805445510","https://openalex.org/W2883251903","https://openalex.org/W2885227193","https://openalex.org/W2894873183","https://openalex.org/W2896596996","https://openalex.org/W2903680162","https://openalex.org/W2910615673","https://openalex.org/W2914641239","https://openalex.org/W2947482526","https://openalex.org/W2950954328","https://openalex.org/W2953008890","https://openalex.org/W2979549191","https://openalex.org/W2982100056","https://openalex.org/W2988396470","https://openalex.org/W2999968268","https://openalex.org/W3000649071","https://openalex.org/W3028280407","https://openalex.org/W3080955776","https://openalex.org/W3107633475","https://openalex.org/W3126054037","https://openalex.org/W3149016991","https://openalex.org/W6639085847","https://openalex.org/W6753383325"],"related_works":["https://openalex.org/W2027224416","https://openalex.org/W2066900946","https://openalex.org/W2018908055","https://openalex.org/W2116072809","https://openalex.org/W2056770622","https://openalex.org/W2145772607","https://openalex.org/W1997434888","https://openalex.org/W2006998778","https://openalex.org/W2054214931","https://openalex.org/W1590455801"],"abstract_inverted_index":{"MOTIVATION:":[0],"Identifying":[1],"variant":[2],"forms":[3],"of":[4,7,49,67,83,121,153,178,191],"gene":[5,25,73,85,106,128,136,159,197,201],"clusters":[6,26,74,107,160,198,202],"interest":[8],"in":[9,39,116,161,175,204],"phylogenetically":[10],"proximate":[11],"and":[12,22,59,88,114,130,151,155,199,206,214],"distant":[13,195],"taxa":[14],"can":[15,38,78],"help":[16],"to":[17,104],"infer":[18],"their":[19,84],"evolutionary":[20],"histories":[21],"functions.":[23],"Conserved":[24],"may":[27],"differ":[28],"by":[29,46,193],"only":[30],"a":[31,80,95,100,145,167],"few":[32],"genes,":[33],"but":[34,69],"these":[35],"small":[36],"differences":[37],"turn":[40],"induce":[41],"substantial":[42],"phenotypes,":[43],"such":[44],"as":[45,56],"the":[47,119,122,149,179,189],"formation":[48],"pseudogenes":[50],"or":[51],"insertions":[52],"interrupting":[53],"regulation.":[54],"Particularly":[55],"microbial":[57],"genomes":[58,140],"metagenomic":[60],"assemblies":[61],"become":[62],"increasingly":[63],"abundant,":[64],"unsupervised":[65],"grouping":[66],"similar,":[68],"not":[70],"necessarily":[71],"identical,":[72],"into":[75,108],"consistent":[76],"bins":[77],"provide":[79],"population-level":[81],"understanding":[82],"content":[86],"variation":[87],"functional":[89],"homology.":[90],"RESULTS:":[91],"We":[92,186],"developed":[93],"GeneGrouper,":[94],"command-line":[96],"tool":[97],"that":[98],"uses":[99],"density-based":[101],"clustering":[102,194],"method":[103],"group":[105],"bins.":[109],"GeneGrouper":[110,165,192,212],"demonstrated":[111,188],"high":[112],"recall":[113],"precision":[115],"benchmarks":[117],"for":[118],"detection":[120],"23-gene":[123],"Salmonella":[124],"enterica":[125],"LT2":[126,157],"Pdu":[127,158],"cluster":[129,137],"four-gene":[131],"Pseudomonas":[132],"aeruginosa":[133],"PAO1":[134],"Mex":[135],"among":[138],"435":[139],"spanning":[141],"mixed":[142],"taxa.":[143],"In":[144],"subsequent":[146],"application":[147],"investigating":[148],"diversity":[150],"impact":[152],"gene-complete":[154],"-incomplete":[156],"1130":[162],"S.enterica":[163],"genomes,":[164],"identified":[166],"novel,":[168],"frequently":[169],"occurring":[170],"pduN":[171,180],"pseudogene.":[172],"When":[173],"investigated":[174],"vivo,":[176],"introduction":[177],"pseudogene":[181],"negatively":[182],"impacted":[183],"microcompartment":[184],"formation.":[185],"next":[187],"versatility":[190],"homologous":[196],"variable":[200],"found":[203],"integrative":[205],"conjugative":[207],"elements.":[208],"AVAILABILITY":[209],"AND":[210],"IMPLEMENTATION:":[211],"software":[213],"code":[215],"are":[216,225],"publicly":[217],"available":[218,226],"at":[219,227],"https://pypi.org/project/GeneGrouper/.":[220],"SUPPLEMENTARY":[221],"INFORMATION:":[222],"Supplementary":[223],"data":[224],"Bioinformatics":[228],"online.":[229]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}