{"id":"https://openalex.org/W7117532740","doi":"https://doi.org/10.1186/s12859-025-06355-2","title":"PG-SCUnK: measuring pangenome graph representativeness using single-copy and universal K-mers","display_name":"PG-SCUnK: measuring pangenome graph representativeness using single-copy and universal K-mers","publication_year":2025,"publication_date":"2025-12-30","ids":{"openalex":"https://openalex.org/W7117532740","doi":"https://doi.org/10.1186/s12859-025-06355-2","pmid":"https://pubmed.ncbi.nlm.nih.gov/41469934"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-025-06355-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-025-06355-2","pdf_url":null,"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://doi.org/10.1186/s12859-025-06355-2","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009787104","display_name":"Tristan Cumer","orcid":"https://orcid.org/0000-0002-0276-7462"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Tristan Cumer","raw_affiliation_strings":["Animal Genomics, ETH Zurich, Zurich, Switzerland. t.cumer.sci@gmail.com"],"raw_orcid":"https://orcid.org/0000-0002-0276-7462","affiliations":[{"raw_affiliation_string":"Animal Genomics, ETH Zurich, Zurich, Switzerland. t.cumer.sci@gmail.com","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121566720","display_name":"Sotiria Milia","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Sotiria Milia","raw_affiliation_strings":["Animal Genomics, ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0009-0006-9409-1987","affiliations":[{"raw_affiliation_string":"Animal Genomics, ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051751201","display_name":"Alexander S. Leonard","orcid":"https://orcid.org/0000-0001-8425-5630"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Alexander S. Leonard","raw_affiliation_strings":["Animal Genomics, ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0001-8425-5630","affiliations":[{"raw_affiliation_string":"Animal Genomics, ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000493727","display_name":"Hubert Pausch","orcid":"https://orcid.org/0000-0002-0501-6760"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Hubert Pausch","raw_affiliation_strings":["Animal Genomics, ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-0501-6760","affiliations":[{"raw_affiliation_string":"Animal Genomics, ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5009787104"],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.73779952,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":"1","first_page":"29","last_page":"29"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.2703000009059906,"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"}},"topics":[{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.2703000009059906,"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":0.11420000344514847,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.10199999809265137,"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/representativeness-heuristic","display_name":"Representativeness heuristic","score":0.7513999938964844},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6202999949455261},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5659999847412109},{"id":"https://openalex.org/keywords/dna-microarray","display_name":"DNA microarray","score":0.29789999127388}],"concepts":[{"id":"https://openalex.org/C37381756","wikidata":"https://www.wikidata.org/wiki/Q20203288","display_name":"Representativeness heuristic","level":2,"score":0.7513999938964844},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6202999949455261},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5659999847412109},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4690000116825104},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3756999969482422},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3116999864578247},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.29789999127388},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.29120001196861267},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.2896000146865845},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.27950000762939453},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2768000066280365}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","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":"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":"D014644","descriptor_name":"Genetic Variation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014644","descriptor_name":"Genetic Variation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":5,"locations":[{"id":"doi:10.1186/s12859-025-06355-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-025-06355-2","pdf_url":null,"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:41469934","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41469934","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:doaj.org/article:7a9304a892b742eba0b08e5ef2e11f4f","is_oa":true,"landing_page_url":"https://doaj.org/article/7a9304a892b742eba0b08e5ef2e11f4f","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 27, Iss 1, Pp 1-9 (2025)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:11667511","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12859900","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,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:12859900","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12859900/","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/s12859-025-06355-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-025-06355-2","pdf_url":null,"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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2104549677","https://openalex.org/W2155628349","https://openalex.org/W2523941254","https://openalex.org/W2583363792","https://openalex.org/W2788099780","https://openalex.org/W2888300707","https://openalex.org/W2964989753","https://openalex.org/W3007365321","https://openalex.org/W3030556878","https://openalex.org/W3086246013","https://openalex.org/W4200597270","https://openalex.org/W4280583823","https://openalex.org/W4362660695","https://openalex.org/W4376118380","https://openalex.org/W4376133202","https://openalex.org/W4391514350","https://openalex.org/W4394961089","https://openalex.org/W4395000446","https://openalex.org/W4404045659","https://openalex.org/W4404945100","https://openalex.org/W4411370797"],"related_works":[],"abstract_inverted_index":{"BACKGROUND:":[0],"Pangenome":[1],"graphs":[2,16],"integrate":[3],"multiple":[4],"assemblies":[5,44,85],"to":[6,32,61,119,134],"represent":[7],"non-redundant":[8],"genetic":[9],"diversity.":[10],"However,":[11],"current":[12],"evaluations":[13],"of":[14,26,106,131],"pangenome":[15,52,67,121,138],"rely":[17],"primarily":[18],"on":[19],"technical":[20],"parameters":[21,133],"(e.g.,":[22],"total":[23],"length,":[24],"number":[25],"nodes/edges,":[27],"growth":[28],"curves),":[29],"which":[30,112],"fail":[31],"assess":[33,63],"how":[34,46,64,76],"effectively":[35],"the":[36,42,83,92,97,104,120,129],"graph":[37,53,68,93],"represents":[38,69],"homologous":[39],"stretches":[40],"across":[41],"integrated":[43,71],"and":[45,79,88,109],"well":[47,65],"short":[48,115],"reads":[49],"align":[50],"against":[51],"references.":[54],"RESULTS:":[55],"We":[56],"introduce":[57],"a":[58,66],"novel":[59],"method":[60,74],"quantitatively":[62],"its":[70],"assemblies.":[72],"Our":[73],"quantifies":[75],"many":[77],"single-copy":[78],"universal":[80],"k-mers":[81],"from":[82],"source":[84],"are":[86],"uniquely":[87],"completely":[89],"represented":[90],"within":[91],"nodes.":[94],"Implemented":[95],"in":[96],"open-source":[98],"tool":[99],"PG-SCUnK,":[100],"this":[101],"approach":[102],"identifies":[103],"fractions":[105],"unique,":[107],"duplicated,":[108],"split":[110],"k-mers,":[111],"correlate":[113],"with":[114],"read":[116],"mapping":[117],"rates":[118],"graph.":[122],"CONCLUSIONS:":[123],"Insights":[124],"provided":[125],"by":[126],"PG-SCUnK":[127],"facilitate":[128],"selection":[130],"appropriate":[132],"build":[135],"optimal":[136],"reference":[137],"graphs.":[139]},"counts_by_year":[],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-12-30T00:00:00"}
