{"id":"https://openalex.org/W7147084740","doi":"https://doi.org/10.1093/bioinformatics/btag155","title":"FALCON2: compression-based metagenomic classification of ancient viruses","display_name":"FALCON2: compression-based metagenomic classification of ancient viruses","publication_year":2026,"publication_date":"2026-03-24","ids":{"openalex":"https://openalex.org/W7147084740","doi":"https://doi.org/10.1093/bioinformatics/btag155","pmid":"https://pubmed.ncbi.nlm.nih.gov/41913056"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btag155","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag155","pdf_url":null,"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://doi.org/10.1093/bioinformatics/btag155","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109830909","display_name":"Luis Marques","orcid":"https://orcid.org/0000-0002-7581-1882"},"institutions":[{"id":"https://openalex.org/I60858718","display_name":"University of Aveiro","ror":"https://ror.org/00nt41z93","country_code":"PT","type":"education","lineage":["https://openalex.org/I60858718"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"Lu\u00eds L Marques","raw_affiliation_strings":["DETI \u2013 Department of Electronics, Telecommunications and Informatics, University of Aveiro , Campus Universit\u00e1rio de Santiago , Aveiro, 3810-193,","IEETA \u2013 Institute of Electronics and Informatics Engineering of Aveiro, University of Aveiro , Campus Universit\u00e1rio de Santiago , Aveiro, 3810-193,","LASI \u2013 Intelligent Systems Associate Laboratory, University of Aveiro , Campus Universit\u00e1rio de Santiago , Aveiro, 3810-193,"],"raw_orcid":"https://orcid.org/0009-0007-6013-5061","affiliations":[{"raw_affiliation_string":"DETI \u2013 Department of Electronics, Telecommunications and Informatics, University of Aveiro , Campus Universit\u00e1rio de Santiago , Aveiro, 3810-193,","institution_ids":["https://openalex.org/I60858718"]},{"raw_affiliation_string":"IEETA \u2013 Institute of Electronics and Informatics Engineering of Aveiro, University of Aveiro , Campus Universit\u00e1rio de Santiago , Aveiro, 3810-193,","institution_ids":["https://openalex.org/I60858718"]},{"raw_affiliation_string":"LASI \u2013 Intelligent Systems Associate Laboratory, University of Aveiro , Campus Universit\u00e1rio de Santiago , Aveiro, 3810-193,","institution_ids":["https://openalex.org/I60858718"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075489861","display_name":"Armando J. Pinho","orcid":"https://orcid.org/0000-0002-9164-0016"},"institutions":[{"id":"https://openalex.org/I60858718","display_name":"University of Aveiro","ror":"https://ror.org/00nt41z93","country_code":"PT","type":"education","lineage":["https://openalex.org/I60858718"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Armando J Pinho","raw_affiliation_strings":["DETI \u2013 Department of Electronics, Telecommunications and Informatics, University of Aveiro , Campus Universit\u00e1rio de Santiago , Aveiro, 3810-193,","IEETA \u2013 Institute of Electronics and Informatics Engineering of Aveiro, University of Aveiro , Campus Universit\u00e1rio de Santiago , Aveiro, 3810-193,","LASI \u2013 Intelligent Systems Associate Laboratory, University of Aveiro , Campus Universit\u00e1rio de Santiago , Aveiro, 3810-193,"],"raw_orcid":"https://orcid.org/0000-0002-9164-0016","affiliations":[{"raw_affiliation_string":"DETI \u2013 Department of Electronics, Telecommunications and Informatics, University of Aveiro , Campus Universit\u00e1rio de Santiago , Aveiro, 3810-193,","institution_ids":["https://openalex.org/I60858718"]},{"raw_affiliation_string":"IEETA \u2013 Institute of Electronics and Informatics Engineering of Aveiro, University of Aveiro , Campus Universit\u00e1rio de Santiago , Aveiro, 3810-193,","institution_ids":["https://openalex.org/I60858718"]},{"raw_affiliation_string":"LASI \u2013 Intelligent Systems Associate Laboratory, University of Aveiro , Campus Universit\u00e1rio de Santiago , Aveiro, 3810-193,","institution_ids":["https://openalex.org/I60858718"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051693451","display_name":"Diogo Pratas","orcid":"https://orcid.org/0000-0003-1176-552X"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]},{"id":"https://openalex.org/I60858718","display_name":"University of Aveiro","ror":"https://ror.org/00nt41z93","country_code":"PT","type":"education","lineage":["https://openalex.org/I60858718"]}],"countries":["FI","PT"],"is_corresponding":true,"raw_author_name":"Diogo Pratas","raw_affiliation_strings":["DETI \u2013 Department of Electronics, Telecommunications and Informatics, University of Aveiro , Campus Universit\u00e1rio de Santiago , Aveiro, 3810-193,","DoV \u2013 Department of Virology, University of Helsinki , Haartmaninkatu 3 , Helsinki, 00014,","IEETA \u2013 Institute of Electronics and Informatics Engineering of Aveiro, University of Aveiro , Campus Universit\u00e1rio de Santiago , Aveiro, 3810-193,","LASI \u2013 Intelligent Systems Associate Laboratory, University of Aveiro , Campus Universit\u00e1rio de Santiago , Aveiro, 3810-193,"],"raw_orcid":"https://orcid.org/0000-0003-1176-552X","affiliations":[{"raw_affiliation_string":"DETI \u2013 Department of Electronics, Telecommunications and Informatics, University of Aveiro , Campus Universit\u00e1rio de Santiago , Aveiro, 3810-193,","institution_ids":["https://openalex.org/I60858718"]},{"raw_affiliation_string":"DoV \u2013 Department of Virology, University of Helsinki , Haartmaninkatu 3 , Helsinki, 00014,","institution_ids":["https://openalex.org/I133731052"]},{"raw_affiliation_string":"IEETA \u2013 Institute of Electronics and Informatics Engineering of Aveiro, University of Aveiro , Campus Universit\u00e1rio de Santiago , Aveiro, 3810-193,","institution_ids":["https://openalex.org/I60858718"]},{"raw_affiliation_string":"LASI \u2013 Intelligent Systems Associate Laboratory, University of Aveiro , Campus Universit\u00e1rio de Santiago , Aveiro, 3810-193,","institution_ids":["https://openalex.org/I60858718"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5051693451","https://openalex.org/A5109830909"],"corresponding_institution_ids":["https://openalex.org/I133731052","https://openalex.org/I60858718"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.46289311,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"42","issue":"5","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11048","display_name":"Bacteriophages and microbial interactions","score":0.8197000026702881,"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"}},"topics":[{"id":"https://openalex.org/T11048","display_name":"Bacteriophages and microbial interactions","score":0.8197000026702881,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.043800000101327896,"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/T11495","display_name":"Animal Virus Infections Studies","score":0.03180000185966492,"subfield":{"id":"https://openalex.org/subfields/1103","display_name":"Animal Science and Zoology"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/metagenomics","display_name":"Metagenomics","score":0.83160001039505},{"id":"https://openalex.org/keywords/virus-classification","display_name":"Virus classification","score":0.3149999976158142},{"id":"https://openalex.org/keywords/genomics","display_name":"Genomics","score":0.27480000257492065},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.26409998536109924},{"id":"https://openalex.org/keywords/biological-classification","display_name":"Biological classification","score":0.2556000053882599}],"concepts":[{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.83160001039505},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.5426999926567078},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4896000027656555},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.34700000286102295},{"id":"https://openalex.org/C20850961","wikidata":"https://www.wikidata.org/wiki/Q478216","display_name":"Virus classification","level":4,"score":0.3149999976158142},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.27480000257492065},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.26409998536109924},{"id":"https://openalex.org/C48702757","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Biological classification","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C159047783","wikidata":"https://www.wikidata.org/wiki/Q7215","display_name":"Virology","level":1,"score":0.2526000142097473},{"id":"https://openalex.org/C90132467","wikidata":"https://www.wikidata.org/wiki/Q171184","display_name":"Phylogenetics","level":3,"score":0.24860000610351562}],"mesh":[{"descriptor_ui":"D000072441","descriptor_name":"DNA, Ancient","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000072441","descriptor_name":"DNA, Ancient","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000072441","descriptor_name":"DNA, Ancient","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":true},{"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":"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":"D014780","descriptor_name":"Viruses","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":true},{"descriptor_ui":"D014780","descriptor_name":"Viruses","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":true},{"descriptor_ui":"D014780","descriptor_name":"Viruses","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":true},{"descriptor_ui":"D014780","descriptor_name":"Viruses","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D014780","descriptor_name":"Viruses","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D014780","descriptor_name":"Viruses","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","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":"D056186","descriptor_name":"Metagenomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btag155","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag155","pdf_url":null,"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:41913056","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41913056","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:13157221","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13157221/","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":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btag155","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag155","pdf_url":null,"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":[{"score":0.5115512609481812,"id":"https://metadata.un.org/sdg/2","display_name":"Zero hunger"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1966716734","https://openalex.org/W1994263888","https://openalex.org/W2003347102","https://openalex.org/W2008386840","https://openalex.org/W2013367562","https://openalex.org/W2034552366","https://openalex.org/W2070720545","https://openalex.org/W2072970694","https://openalex.org/W2106378427","https://openalex.org/W2110300022","https://openalex.org/W2112954194","https://openalex.org/W2117825194","https://openalex.org/W2128859735","https://openalex.org/W2156330112","https://openalex.org/W2157539385","https://openalex.org/W2343039634","https://openalex.org/W2544029679","https://openalex.org/W2791921867","https://openalex.org/W2803108192","https://openalex.org/W2951160681","https://openalex.org/W2990618091","https://openalex.org/W4313427532","https://openalex.org/W4404577234"],"related_works":[],"abstract_inverted_index":{"MOTIVATION:":[0],"Ancient":[1],"DNA":[2],"(aDNA)":[3],"sequences":[4],"present":[5,52],"unique":[6],"challenges":[7],"for":[8,102,202],"taxonomic":[9],"classification":[10],"due":[11],"to":[12,63],"extreme":[13],"fragmentation":[14],"(reads":[15],"20-100":[16],"bp),":[17,173],"end-biased":[18],"cytosine":[19],"deamination,":[20],"and":[21,41,98,111,140,155,220],"high":[22,65],"contamination":[23],"rates.":[24],"Conventional":[25],"metagenomic":[26,56],"classifiers":[27],"based":[28],"on":[29,38,67,114,160,169,196],"exact":[30,175],"k-mer":[31],"matching":[32],"or":[33],"alignment":[34],"lose":[35],"discriminative":[36],"power":[37],"such":[39],"short":[40],"damaged":[42],"reads,":[43],"limiting":[44],"the":[45,74,123],"analysis":[46],"of":[47,76,92,125,130,138,143],"paleogenomic":[48],"samples.":[49,104],"RESULTS:":[50],"We":[51],"FALCON2,":[53],"a":[54,81],"compression-based":[55],"classifier":[57],"that":[58],"leverages":[59],"position-aware":[60],"finite-context":[61],"models":[62],"maintain":[64],"accuracy":[66],"degraded":[68],"viral":[69,116],"ancient":[70],"viruses.":[71],"FALCON2":[72,118,179,194,208],"consolidates":[73],"capabilities":[75],"its":[77],"predecessor,":[78],"FALCON-meta,":[79],"into":[80],"unified":[82],"executable":[83],"with":[84,108,190,198],"enhanced":[85],"features":[86],"including":[87],"model":[88],"persistence,":[89],"direct":[90],"processing":[91],"compressed":[93],"inputs,":[94],"multiple":[95],"file":[96],"handling,":[97],"optional":[99],"pre-filtering":[100,180],"methodologies":[101],"contaminated":[103],"Under":[105,122,134],"controlled":[106],"benchmarking":[107],"database,":[109],"taxonomy,":[110],"thread":[112],"parity":[113],"simulated":[115],"datasets,":[117],"achieved":[119],"an":[120,132,141],"Area":[121,133],"Curve":[124,136],"Receiver":[126],"Operating":[127],"Characteristic":[128],"(AUC-ROC)":[129],"0.999,":[131],"Precision-Recall":[135],"(AUPRC)":[137],"0.968,":[139],"F1-score":[142],"0.918,":[144],"substantially":[145],"outperforming":[146],"Centrifuge":[147],"(AUPRC":[148,152,157],"=":[149,153,158],"0.625),":[150],"Kraken2":[151],"0.184),":[154],"CLARK-S":[156],"0.013)":[159],"pooled":[161],"micro-averaged":[162],"metrics.":[163],"FALCON2's":[164],"advantage":[165],"is":[166,209],"most":[167],"pronounced":[168],"ultra-short":[170],"reads":[171],"(20-40":[172],"where":[174],"k-mers":[176],"become":[177],"sparse.":[178],"at":[181,212,224],"threshold":[182],"0.7":[183],"improved":[184],"precision":[185],"by":[186],"10":[187],"percentage":[188],"points":[189],"negligible":[191],"recall":[192],"loss.":[193],"runs":[195],"systems":[197],"4-8":[199],"GB":[200],"RAM":[201],"typical":[203],"analyses.":[204],"AVAILABILITY":[205],"AND":[206],"IMPLEMENTATION:":[207],"freely":[210],"available":[211],"https://github.com/cobilab/FALCON2":[213],"under":[214],"GPL":[215],"v3":[216],"license.":[217],"Benchmarking":[218],"data":[219],"scripts":[221],"are":[222],"archived":[223],"DOI:":[225],"https://doi.org/10.5281/zenodo.17291214.":[226]},"counts_by_year":[],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2026-04-02T00:00:00"}
