{"id":"https://openalex.org/W7224780857","doi":"https://doi.org/10.64898/2026.10.29.762972","title":"Assembly of minimally fragmented metagenomic pangenome graphs","display_name":"Assembly of minimally fragmented metagenomic pangenome graphs","publication_year":2026,"publication_date":"2026-10-30","ids":{"openalex":"https://openalex.org/W7224780857","doi":"https://doi.org/10.64898/2026.10.29.762972"},"language":"en","primary_location":{"id":"doi:10.64898/2026.10.29.762972","doi":"https://doi.org/10.64898/2026.10.29.762972","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.29.762972","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/30/2026.10.29.762972.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/30/2026.10.29.762972.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036132643","display_name":"Dylan Duchen","orcid":"https://orcid.org/0000-0001-5629-2012","observed_orcids":["https://orcid.org/0000-0001-5629-2012"]},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dylan Duchen","raw_affiliation_strings":["Department of Biomedical Informatics and Data Science, Yale University School of Medicine, New Haven, CT, USA","Department of Pathology, Yale University School of Medicine, New Haven, CT, USA"],"raw_orcid":"https://orcid.org/0000-0001-5629-2012","affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics and Data Science, Yale University School of Medicine, New Haven, CT, USA","institution_ids":["https://openalex.org/I32971472"]},{"raw_affiliation_string":"Department of Pathology, Yale University School of Medicine, New Haven, CT, USA","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053736697","display_name":"Florencia Martino","orcid":"https://orcid.org/0009-0006-1381-6326","observed_orcids":["https://orcid.org/0009-0006-1381-6326"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2799853436","display_name":"Johns Hopkins Medicine","ror":"https://ror.org/037zgn354","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Florencia Martino","raw_affiliation_strings":["Department of Medicine, Division of Infectious Diseases, Johns Hopkins School of Medicine, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Medicine, Division of Infectious Diseases, Johns Hopkins School of Medicine, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2799853436"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007138133","display_name":"Kakhangchung Panmei","orcid":"https://orcid.org/0009-0005-5695-6241","observed_orcids":["https://orcid.org/0009-0005-5695-6241"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2799853436","display_name":"Johns Hopkins Medicine","ror":"https://ror.org/037zgn354","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kakhangchung Panmei","raw_affiliation_strings":["Department of Medicine, Division of Infectious Diseases, Johns Hopkins School of Medicine, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Medicine, Division of Infectious Diseases, Johns Hopkins School of Medicine, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2799853436"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040960443","display_name":"Abraham Joseph Kandathil","orcid":"https://orcid.org/0000-0002-9038-134X","observed_orcids":["https://orcid.org/0000-0002-9038-134X"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2799853436","display_name":"Johns Hopkins Medicine","ror":"https://ror.org/037zgn354","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abraham J. Kandathil","raw_affiliation_strings":["Department of Medicine, Division of Infectious Diseases, Johns Hopkins School of Medicine, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Medicine, Division of Infectious Diseases, Johns Hopkins School of Medicine, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2799853436"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008957169","display_name":"Steven J. Clipman","orcid":"https://orcid.org/0000-0002-2366-8420","observed_orcids":["https://orcid.org/0000-0002-2366-8420"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2799853436","display_name":"Johns Hopkins Medicine","ror":"https://ror.org/037zgn354","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steven J. Clipman","raw_affiliation_strings":["Department of Medicine, Division of Infectious Diseases, Johns Hopkins School of Medicine, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Medicine, Division of Infectious Diseases, Johns Hopkins School of Medicine, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2799853436"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5036132643"],"corresponding_institution_ids":["https://openalex.org/I32971472"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"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":0.9984999895095825,"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":0.9984999895095825,"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/T11048","display_name":"Bacteriophages and microbial interactions","score":0.00039999998989515007,"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"}},{"id":"https://openalex.org/T12946","display_name":"Fractal and DNA sequence analysis","score":0.00019999999494757503,"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/maximum-spanning-tree","display_name":"maximum spanning tree","score":0.7110000252723694},{"id":"https://openalex.org/keywords/average-nucleotide-identity","display_name":"average nucleotide identity","score":0.9819999933242798},{"id":"https://openalex.org/keywords/anelloviridae","display_name":"Anelloviridae","score":0.9120000004768372},{"id":"https://openalex.org/keywords/viral-genome-diversity","display_name":"viral genome diversity","score":0.5270000100135803}],"concepts":[{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.6632000207901001},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.6535000205039978},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.5582000017166138},{"id":"https://openalex.org/C193252679","wikidata":"https://www.wikidata.org/wiki/Q242125","display_name":"Phylogenetic tree","level":3,"score":0.4595000147819519},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.44350001215934753},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.44339999556541443},{"id":"https://openalex.org/C2776473694","wikidata":"https://www.wikidata.org/wiki/Q4950555","display_name":"Bovine genome","level":4,"score":0.4000000059604645},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.38040000200271606},{"id":"https://openalex.org/C5349765","wikidata":"https://www.wikidata.org/wiki/Q5282866","display_name":"Distance matrices in phylogeny","level":2,"score":0.34279999136924744},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.3418000042438507},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.3391000032424927},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.31290000677108765},{"id":"https://openalex.org/C68873052","wikidata":"https://www.wikidata.org/wiki/Q349856","display_name":"Genetic variation","level":3,"score":0.3100999891757965},{"id":"https://openalex.org/C151020129","wikidata":"https://www.wikidata.org/wiki/Q7625067","display_name":"Structural variation","level":4,"score":0.30869999527931213},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.29030001163482666},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.2833999991416931},{"id":"https://openalex.org/C31266012","wikidata":"https://www.wikidata.org/wiki/Q6554340","display_name":"Linkage (software)","level":3,"score":0.28040000796318054},{"id":"https://openalex.org/C105176652","wikidata":"https://www.wikidata.org/wiki/Q1147112","display_name":"Comparative genomics","level":5,"score":0.2757999897003174},{"id":"https://openalex.org/C24432333","wikidata":"https://www.wikidata.org/wiki/Q2068526","display_name":"Whole genome sequencing","level":4,"score":0.27559998631477356},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C20218877","wikidata":"https://www.wikidata.org/wiki/Q3066095","display_name":"De Bruijn graph","level":3,"score":0.2614000141620636},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.25600001215934753},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.10.29.762972","doi":"https://doi.org/10.64898/2026.10.29.762972","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.29.762972","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/30/2026.10.29.762972.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.10.29.762972","doi":"https://doi.org/10.64898/2026.10.29.762972","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.29.762972","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/30/2026.10.29.762972.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G9000131954","display_name":"Biomedical Informatics and Data Science Training at Yale","funder_award_id":"T15LM007056","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"}],"funders":[{"id":"https://openalex.org/F4320337347","display_name":"National Institute on Drug Abuse","ror":"https://ror.org/00fq5cm18"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224780857.pdf","grobid_xml":"https://content.openalex.org/works/W7224780857.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4416774120","https://openalex.org/W4379508567","https://openalex.org/W4416856051","https://openalex.org/W2951704474","https://openalex.org/W7134973052","https://openalex.org/W4403609447","https://openalex.org/W4385727346","https://openalex.org/W3012393121","https://openalex.org/W7155070202","https://openalex.org/W3092652421"],"abstract_inverted_index":{"Abstract":[0],"Pangenome":[1],"variation":[2,84,109,159,181],"graphs":[3,110,182],"are":[4,120,184],"a":[5,100,128,157],"powerful":[6],"tool":[7],"for":[8,71,191],"representing":[9],"genetic":[10,37,197],"diversity":[11],"within":[12,43],"and":[13,18,36,95,195],"across":[14,63,170,199],"populations.":[15],"For":[16],"comparative":[17],"evolutionary":[19],"genomic":[20],"analyses":[21,198],"leveraging":[22],"these":[23,50],"graph-based":[24],"structures,":[25],"it":[26],"is":[27,68,125],"important":[28],"that":[29,183],"graph":[30,85,124,160,162],"topology":[31,163],"reflects":[32,164],"the":[33,40,44,118,123,165,171],"underlying":[34],"phylogenetic":[35],"similarities":[38,168],"of":[39,60,141],"genomes":[41,61,81,119],"embedded":[42,62],"graph.":[45],"However,":[46],"in":[47,116],"metagenomic":[48,106,178],"settings":[49],"approaches":[51],"often":[52],"produce":[53],"highly":[54,200],"fragmented":[55,105,177],"multi-component":[56],"graphs,":[57],"hindering":[58],"comparisons":[59],"different":[64],"components.":[65],"This":[66],"challenge":[67],"particularly":[69],"pronounced":[70],"hypervariable":[72],"viral":[73],"families":[74],"like":[75],"Anelloviridae":[76,143,153],",":[77],"whose":[78,161],"short":[79],"circular":[80],"frustrate":[82],"existing":[83,188],"construction":[86],"methods.":[87],"We":[88],"present":[89],"PANIMaSTA":[90,174],"(Progressive":[91],"Average":[92],"Nucleotide":[93],"Identity":[94],"Maximum":[96],"Spanning":[97],"Tree-Based":[98],"Assembly),":[99],"workflow":[101],"to":[102,149],"construct":[103,156],"minimally":[104,176],"pangenome":[107,179],"sequence":[108,158,180],"through":[111],"progressive":[112],"assembly.":[113],"The":[114],"order":[115],"which":[117],"incorporated":[121],"into":[122],"informed":[126],"by":[127],"maximum":[129],"spanning":[130],"tree":[131],"(MST)":[132],"inferred":[133],"from":[134],"an":[135],"all-to-all":[136],"genome":[137,167],"similarity":[138],"matrix":[139],"comprised":[140],"pairwise":[142],"average":[144],"nucleotide":[145],"identities":[146],"(ANI).":[147],"Applied":[148],"over":[150],"5,200":[151],"diverse":[152,201],"genomes,":[154],"we":[155],"global":[166],"observed":[169],"ANI":[172],"matrix.":[173],"constructs":[175],"not":[185],"achievable":[186],"with":[187],"methods":[189],"suitable":[190],"similarity-aware":[192],"sequence-to-graph":[193],"mapping":[194],"downstream":[196],"genomes.":[202]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-10-31T00:00:00"}
