{"id":"https://openalex.org/W4387079708","doi":"https://doi.org/10.1093/bioinformatics/btad595","title":"compleasm: a faster and more accurate reimplementation of BUSCO","display_name":"compleasm: a faster and more accurate reimplementation of BUSCO","publication_year":2023,"publication_date":"2023-09-27","ids":{"openalex":"https://openalex.org/W4387079708","doi":"https://doi.org/10.1093/bioinformatics/btad595","pmid":"https://pubmed.ncbi.nlm.nih.gov/37758247"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btad595","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad595","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad595/51779686/btad595.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"oa_status":"gold","oa_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad595/51779686/btad595.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054096088","display_name":"Neng Huang","orcid":"https://orcid.org/0000-0001-7187-0749"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]},{"id":"https://openalex.org/I4210117453","display_name":"Dana-Farber Cancer Institute","ror":"https://ror.org/02jzgtq86","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210117453"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neng Huang","raw_affiliation_strings":["Department of Biomedical Informatics, Harvard Medical School , Boston, MA 02115, United States","Department of Data Sciences, Dana-Farber Cancer Institute , Boston, MA 02215, United States"],"raw_orcid":"https://orcid.org/0000-0001-7187-0749","affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Harvard Medical School , Boston, MA 02115, United States","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"Department of Data Sciences, Dana-Farber Cancer Institute , Boston, MA 02215, United States","institution_ids":["https://openalex.org/I4210117453"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100338825","display_name":"Heng Li","orcid":"https://orcid.org/0000-0003-4874-2874"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]},{"id":"https://openalex.org/I4210117453","display_name":"Dana-Farber Cancer Institute","ror":"https://ror.org/02jzgtq86","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210117453"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Heng Li","raw_affiliation_strings":["Department of Biomedical Informatics, Harvard Medical School , Boston, MA 02115, United States","Department of Data Sciences, Dana-Farber Cancer Institute , Boston, MA 02215, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Harvard Medical School , Boston, MA 02115, United States","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"Department of Data Sciences, Dana-Farber Cancer Institute , Boston, MA 02215, United States","institution_ids":["https://openalex.org/I4210117453"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100338825"],"corresponding_institution_ids":["https://openalex.org/I136199984","https://openalex.org/I4210117453"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":33.3938,"has_fulltext":true,"cited_by_count":367,"citation_normalized_percentile":{"value":0.99896497,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"39","issue":"10","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.7110999822616577,"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":0.7110999822616577,"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":0.2468000054359436,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.010400000028312206,"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/completeness","display_name":"Completeness (order theory)","score":0.7657983303070068},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.7342258095741272},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6944599151611328},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5636547803878784},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.488750696182251},{"id":"https://openalex.org/keywords/human-genome","display_name":"Human genome","score":0.4820155203342438},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.47429707646369934},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.4251166582107544},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.42492881417274475},{"id":"https://openalex.org/keywords/gene-annotation","display_name":"Gene Annotation","score":0.42116373777389526},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.39315065741539},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1381487250328064},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.05701768398284912}],"concepts":[{"id":"https://openalex.org/C17231256","wikidata":"https://www.wikidata.org/wiki/Q5156540","display_name":"Completeness (order theory)","level":2,"score":0.7657983303070068},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.7342258095741272},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6944599151611328},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5636547803878784},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.488750696182251},{"id":"https://openalex.org/C197077220","wikidata":"https://www.wikidata.org/wiki/Q720988","display_name":"Human genome","level":4,"score":0.4820155203342438},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.47429707646369934},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.4251166582107544},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.42492881417274475},{"id":"https://openalex.org/C2908923196","wikidata":"https://www.wikidata.org/wiki/Q5205742","display_name":"Gene Annotation","level":4,"score":0.42116373777389526},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.39315065741539},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1381487250328064},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.05701768398284912},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btad595","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad595","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad595/51779686/btad595.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:37758247","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37758247","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":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10558035","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10558035","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10558035/pdf/btad595.pdf","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":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btad595","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad595","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad595/51779686/btad595.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3516633646","display_name":null,"funder_award_id":"R01 HG010040","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G4594819197","display_name":null,"funder_award_id":"237653","funder_id":"https://openalex.org/F4320315474","funder_display_name":"Chan Zuckerberg Initiative"}],"funders":[{"id":"https://openalex.org/F4320315474","display_name":"Chan Zuckerberg Initiative","ror":"https://ror.org/02qenvm24"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387079708.pdf"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W2102652793","https://openalex.org/W2107772251","https://openalex.org/W2155628349","https://openalex.org/W2788228074","https://openalex.org/W2968499116","https://openalex.org/W3007075333","https://openalex.org/W3014607123","https://openalex.org/W3047598142","https://openalex.org/W3104062656","https://openalex.org/W3128198169","https://openalex.org/W3186309583","https://openalex.org/W4220668127","https://openalex.org/W4220999759","https://openalex.org/W4316926647"],"related_works":["https://openalex.org/W2059565715","https://openalex.org/W2901823680","https://openalex.org/W1969895229","https://openalex.org/W2009940763","https://openalex.org/W4386637333","https://openalex.org/W2946410450","https://openalex.org/W4361192415","https://openalex.org/W2126804125","https://openalex.org/W2108497208","https://openalex.org/W2162782320"],"abstract_inverted_index":{"MOTIVATION:":[0],"Evaluating":[1],"the":[2,9,42,49,95,102,107,140],"gene":[3,23],"completeness":[4,43,96,128,142],"is":[5,35,66,74,114,135],"critical":[6],"to":[7,20,76,79],"measuring":[8],"quality":[10],"of":[11,44,51,54,62,83,97,129,143],"a":[12,36,52,59,80,125],"genome":[13,45,71,98],"assembly.":[14],"An":[15],"incomplete":[16],"assembly":[17,46],"can":[18],"lead":[19],"errors":[21],"in":[22,136],"predictions,":[24],"annotation,":[25],"and":[26,106,123],"other":[27],"downstream":[28],"analyses.":[29],"Benchmarking":[30],"Universal":[31],"Single-Copy":[32],"Orthologs":[33],"(BUSCO)":[34],"widely":[37],"used":[38],"tool":[39,92],"for":[40,69,93,120,145],"assessing":[41,94],"by":[47],"testing":[48],"presence":[50],"set":[53],"single-copy":[55],"orthologs":[56],"conserved":[57,108],"across":[58],"wide":[60],"range":[61],"taxa.":[63],"However,":[64],"BUSCO":[65,78,119],"slow":[67],"particularly":[68],"large":[70,81],"assemblies.":[72,84,99],"It":[73,113],"cumbersome":[75],"apply":[77],"number":[82],"RESULTS:":[85],"Here,":[86],"we":[87],"present":[88],"compleasm,":[89],"an":[90],"efficient":[91],"Compleasm":[100],"utilizes":[101],"miniprot":[103],"protein-to-genome":[104],"aligner":[105],"orthologous":[109],"genes":[110],"from":[111],"BUSCO.":[112],"14":[115],"times":[116],"faster":[117],"than":[118,131],"human":[121],"assemblies":[122],"reports":[124],"more":[126],"accurate":[127],"99.6%":[130],"BUSCO's":[132],"95.7%,":[133],"which":[134],"close":[137],"agreement":[138],"with":[139],"annotation":[141],"99.5%":[144],"T2T-CHM13.":[146],"AVAILABILITY":[147],"AND":[148],"IMPLEMENTATION:":[149],"https://github.com/huangnengCSU/compleasm.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":96},{"year":2025,"cited_by_count":162},{"year":2024,"cited_by_count":100},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":2}],"updated_date":"2026-08-13T07:04:57.449891","created_date":"2025-10-10T00:00:00"}