{"id":"https://openalex.org/W7212379070","doi":"https://doi.org/10.1177/15578666261485334","title":"Using Mapping-Profiles to Refine Strain-Level Metagenomic Classification","display_name":"Using Mapping-Profiles to Refine Strain-Level Metagenomic Classification","publication_year":2026,"publication_date":"2026-09-12","ids":{"openalex":"https://openalex.org/W7212379070","doi":"https://doi.org/10.1177/15578666261485334","pmid":"https://pubmed.ncbi.nlm.nih.gov/42730546"},"language":"en","primary_location":{"id":"doi:10.1177/15578666261485334","doi":"https://doi.org/10.1177/15578666261485334","is_oa":false,"landing_page_url":"https://doi.org/10.1177/15578666261485334","pdf_url":null,"source":{"id":"https://openalex.org/S78571599","display_name":"Journal of Computational Biology","issn_l":"1066-5277","issn":["1066-5277","1557-8666"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-70","russia-white-list-1"],"host_organization":"https://openalex.org/P4310320443","host_organization_name":"Mary Ann Liebert, Inc.","host_organization_lineage":["https://openalex.org/P4310320443","https://openalex.org/P4310320017"],"host_organization_lineage_names":["Mary Ann Liebert, Inc.","SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Biology","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/05/20/2026.05.18.725856.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011277784","display_name":"Josipa Lipovac","orcid":"https://orcid.org/0009-0003-4943-5179","observed_orcids":["https://orcid.org/0009-0003-4943-5179"]},"institutions":[{"id":"https://openalex.org/I181343428","display_name":"University of Zagreb","ror":"https://ror.org/00mv6sv71","country_code":"HR","type":"education","lineage":["https://openalex.org/I181343428"]},{"id":"https://openalex.org/I4390039327","display_name":"Faculty of Electrical Engineering and Computing in Zagreb","ror":"https://ror.org/04e90ca47","country_code":"HR","type":"education","lineage":["https://openalex.org/I181343428","https://openalex.org/I4390039327"]}],"countries":["HR"],"is_corresponding":true,"raw_author_name":"Josipa Lipovac","raw_affiliation_strings":["Laboratory for Bioinformatics and Computational Biology, University of Zagreb Faculty of Electrical Engineering and Computing, Zagreb, Croatia"],"raw_orcid":"https://orcid.org/0009-0003-4943-5179","affiliations":[{"raw_affiliation_string":"Laboratory for Bioinformatics and Computational Biology, University of Zagreb Faculty of Electrical Engineering and Computing, Zagreb, Croatia","institution_ids":["https://openalex.org/I181343428","https://openalex.org/I4390039327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120540637","display_name":"Lune Angevin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I154526488","display_name":"Inserm","ror":"https://ror.org/02vjkv261","country_code":"FR","type":"government","lineage":["https://openalex.org/I154526488"]},{"id":"https://openalex.org/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]},{"id":"https://openalex.org/I4210088668","display_name":"Institut National de Recherche pour l'Agriculture, l'Alimentation et l'Environnement","ror":"https://ror.org/003vg9w96","country_code":"FR","type":"government","lineage":["https://openalex.org/I4210088668"]},{"id":"https://openalex.org/I4387156410","display_name":"Nutrition, m\u00e9tabolismes et cancer","ror":"https://ror.org/03zb6nw87","country_code":"FR","type":"facility","lineage":["https://openalex.org/I154526488","https://openalex.org/I4210088668","https://openalex.org/I4387156410","https://openalex.org/I56067802"]},{"id":"https://openalex.org/I56067802","display_name":"Universit\u00e9 de Rennes","ror":"https://ror.org/015m7wh34","country_code":"FR","type":"education","lineage":["https://openalex.org/I56067802"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Lune Angevin","raw_affiliation_strings":["NuMeCan, INRAE, INSERM, Univ. Rennes, Rennes, France and GenScale, Univ. Rennes, Inria, IRISA, Rennes, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NuMeCan, INRAE, INSERM, Univ. Rennes, Rennes, France and GenScale, Univ. Rennes, Inria, IRISA, Rennes, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I154526488","https://openalex.org/I2802519937","https://openalex.org/I4210088668","https://openalex.org/I4387156410","https://openalex.org/I56067802"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041580711","display_name":"Kre\u0161imir Kri\u017eanovi\u0107","orcid":"https://orcid.org/0000-0002-2514-0988","observed_orcids":["https://orcid.org/0000-0002-2514-0988"]},"institutions":[{"id":"https://openalex.org/I181343428","display_name":"University of Zagreb","ror":"https://ror.org/00mv6sv71","country_code":"HR","type":"education","lineage":["https://openalex.org/I181343428"]},{"id":"https://openalex.org/I4390039327","display_name":"Faculty of Electrical Engineering and Computing in Zagreb","ror":"https://ror.org/04e90ca47","country_code":"HR","type":"education","lineage":["https://openalex.org/I181343428","https://openalex.org/I4390039327"]}],"countries":["HR"],"is_corresponding":false,"raw_author_name":"Kre\u0161imir Kri\u017eanoviC\u2019","raw_affiliation_strings":["Laboratory for Bioinformatics and Computational Biology, University of Zagreb Faculty of Electrical Engineering and Computing, Zagreb, Croatia"],"raw_orcid":"https://orcid.org/0000-0002-2514-0988","affiliations":[{"raw_affiliation_string":"Laboratory for Bioinformatics and Computational Biology, University of Zagreb Faculty of Electrical Engineering and Computing, Zagreb, Croatia","institution_ids":["https://openalex.org/I181343428","https://openalex.org/I4390039327"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5011277784"],"corresponding_institution_ids":["https://openalex.org/I181343428","https://openalex.org/I4390039327"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.64751644,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"15578666261485334","last_page":"15578666261485334"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9976000189781189,"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":0.9976000189781189,"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/T12640","display_name":"Environmental DNA in Biodiversity Studies","score":0.0003000000142492354,"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/T12167","display_name":"Bacterial Identification and Susceptibility Testing","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/1308","display_name":"Clinical Biochemistry"},"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/pathogen-detection","display_name":"pathogen detection","score":0.8610000014305115}],"concepts":[{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.8192999958992004},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6743999719619751},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5942999720573425},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5827999711036682},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5734999775886536},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.40450000762939453},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3849000036716461},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37059998512268066},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.36160001158714294},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3610000014305115},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.34049999713897705},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3073999881744385},{"id":"https://openalex.org/C2778022156","wikidata":"https://www.wikidata.org/wiki/Q576145","display_name":"Strain (injury)","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.2879999876022339},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.2644999921321869},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.260699987411499}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1177/15578666261485334","doi":"https://doi.org/10.1177/15578666261485334","is_oa":false,"landing_page_url":"https://doi.org/10.1177/15578666261485334","pdf_url":null,"source":{"id":"https://openalex.org/S78571599","display_name":"Journal of Computational Biology","issn_l":"1066-5277","issn":["1066-5277","1557-8666"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-1","poland-70","russia-white-list-1"],"host_organization":"https://openalex.org/P4310320443","host_organization_name":"Mary Ann Liebert, Inc.","host_organization_lineage":["https://openalex.org/P4310320443","https://openalex.org/P4310320017"],"host_organization_lineage_names":["Mary Ann Liebert, Inc.","SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Biology","raw_type":"journal-article"},{"id":"doi:10.64898/2026.05.18.725856","doi":"https://doi.org/10.64898/2026.05.18.725856","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.05.18.725856","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/05/20/2026.05.18.725856.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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},{"id":"pmid:42730546","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42730546","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,"listed_in":[],"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":"Journal of computational biology : a journal of computational molecular cell biology","raw_type":"Journal Article"},{"id":"pmh:oai:HAL:hal-05786018v1","doi":null,"is_oa":false,"landing_page_url":"https://hal.science/hal-05786018","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Computational Biology, 2026, pp.15578666261485334-15578666261485334. &#x27E8;10.1177/15578666261485334&#x27E9;","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.64898/2026.05.18.725856","doi":"https://doi.org/10.64898/2026.05.18.725856","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.05.18.725856","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/05/20/2026.05.18.725856.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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4693876124","display_name":null,"funder_award_id":"SIGMA IP-2018-01-5886","funder_id":"https://openalex.org/F4320322674","funder_display_name":"Hrvatska Zaklada za Znanost"},{"id":"https://openalex.org/G4901951209","display_name":null,"funder_award_id":"DATACROSS 2024\u20132026,PK.1.1.10.0007","funder_id":"https://openalex.org/F4320322674","funder_display_name":"Hrvatska Zaklada za Znanost"}],"funders":[{"id":"https://openalex.org/F4320322674","display_name":"Hrvatska Zaklada za Znanost","ror":"https://ror.org/03n51vw80"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7212379070.pdf","grobid_xml":"https://content.openalex.org/works/W7212379070.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1853921426","https://openalex.org/W2086320398","https://openalex.org/W2106533426","https://openalex.org/W2150991111","https://openalex.org/W2173732482","https://openalex.org/W2525954034","https://openalex.org/W2929062889","https://openalex.org/W2951160681","https://openalex.org/W2952204926","https://openalex.org/W2958388979","https://openalex.org/W2990618091","https://openalex.org/W4221044588","https://openalex.org/W4310705341","https://openalex.org/W4313261720","https://openalex.org/W4385898694","https://openalex.org/W4390747654","https://openalex.org/W4391291174","https://openalex.org/W4395047680","https://openalex.org/W4395465130","https://openalex.org/W6892655497","https://openalex.org/W7140120293"],"related_works":[],"abstract_inverted_index":{"Metagenomic":[0],"classification":[1,155],"at":[2],"the":[3,32,148,152,158],"strain":[4,26,117],"level":[5],"remains":[6],"challenging":[7],"due":[8],"to":[9,19,58,104],"high":[10],"sequence":[11],"similarity":[12,81,200],"among":[13,62],"closely":[14],"related":[15],"genomes,":[16,100],"which":[17,37],"leads":[18],"ambiguous":[20,60],"read":[21],"mappings":[22],"and":[23,79,101,122,127],"frequent":[24],"false-positive":[25,116],"detections.":[27],"Reducing":[28],"such":[29,42],"errors":[30],"improves":[31],"reliability":[33],"of":[34,110],"strain-level":[35,165,207],"analyses,":[36],"is":[38],"critical":[39],"for":[40,168,205],"applications":[41],"as":[43,201],"pathogen":[44],"detection.":[45],"We":[46],"introduce":[47],"StrainRefine,":[48],"a":[49,137],"post-mapping":[50],"refinement":[51],"method":[52,67,89,150],"that":[53,75],"analyzes":[54],"read-reference":[55],"mapping":[56,95],"profiles":[57,74],"resolve":[59],"assignments":[61],"highly":[63],"similar":[64,94],"genomes.":[65],"The":[66,88],"represents":[68],"candidate":[69],"reference":[70,182,194],"genomes":[71],"using":[72],"binary":[73],"capture":[76],"read-support":[77],"patterns":[78],"measures":[80],"between":[82,125],"references":[83,91],"based":[84,92],"on":[85,93,157,192],"profile":[86],"overlap.":[87],"clusters":[90],"profiles,":[96],"filters":[97],"weakly":[98],"supported":[99],"reassigns":[102],"reads":[103],"representative":[105],"references,":[106],"reducing":[107],"redundant":[108],"reporting":[109],"near-identical":[111],"strains.":[112],"StrainRefine":[113,171],"substantially":[114,138],"reduces":[115],"detections":[118],"while":[119,184],"preserving":[120],"recall":[121],"improving":[123,206],"agreement":[124],"predicted":[126],"true":[128],"abundance":[129],"profiles.":[130],"On":[131],"large-scale":[132],"metagenomic":[133,208],"datasets,":[134],"it":[135],"achieves":[136],"improved":[139],"precision-recall":[140],"balance":[141],"compared":[142],"with":[143,147],"existing":[144],"mapping-based":[145],"approaches,":[146],"standalone":[149],"obtaining":[151],"highest":[153],"read-level":[154],"accuracy":[156],"most":[159],"complex":[160],"evaluated":[161],"dataset.":[162],"Unlike":[163],"many":[164],"tools":[166],"designed":[167],"individual":[169],"species,":[170],"operates":[172],"without":[173],"prior":[174],"assumptions":[175],"about":[176],"sample":[177],"composition":[178],"or":[179],"curated":[180],"species-specific":[181,193],"collections,":[183],"still":[185],"achieving":[186],"comparable":[187],"performance":[188],"in":[189],"single-species":[190],"settings":[191],"databases.":[195],"These":[196],"results":[197],"highlight":[198],"mapping-profile":[199],"an":[202],"effective":[203],"signal":[204],"classification.":[209]},"counts_by_year":[],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2026-09-13T00:00:00"}
