{"id":"https://openalex.org/W7164908396","doi":"https://doi.org/10.1186/s12859-026-06512-1","title":"Genestrip: exact and efficient read classification for selected groups of organisms","display_name":"Genestrip: exact and efficient read classification for selected groups of organisms","publication_year":2026,"publication_date":"2026-06-16","ids":{"openalex":"https://openalex.org/W7164908396","doi":"https://doi.org/10.1186/s12859-026-06512-1","pmid":"https://pubmed.ncbi.nlm.nih.gov/42304206"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-026-06512-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-026-06512-1","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/s12859-026-06512-1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051306698","display_name":"Daniel Pfeifer","orcid":"https://orcid.org/0000-0003-1794-1184"},"institutions":[{"id":"https://openalex.org/I41121874","display_name":"Heilbronn University","ror":"https://ror.org/04g5gcg95","country_code":"DE","type":"education","lineage":["https://openalex.org/I41121874"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Daniel Pfeifer","raw_affiliation_strings":["IT Faculty, Heilbronn University, Max-Planck-Str. 39, 74081, Heilbronn, Baden-W\u00fcrttemberg, Germany. daniel.pfeifer@hs-heilbronn.de"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IT Faculty, Heilbronn University, Max-Planck-Str. 39, 74081, Heilbronn, Baden-W\u00fcrttemberg, Germany. daniel.pfeifer@hs-heilbronn.de","institution_ids":["https://openalex.org/I41121874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138742150","display_name":"Markus Graf","orcid":null},"institutions":[{"id":"https://openalex.org/I41121874","display_name":"Heilbronn University","ror":"https://ror.org/04g5gcg95","country_code":"DE","type":"education","lineage":["https://openalex.org/I41121874"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Markus Graf","raw_affiliation_strings":["IT Faculty, Heilbronn University, Max-Planck-Str. 39, 74081, Heilbronn, Baden-W\u00fcrttemberg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IT Faculty, Heilbronn University, Max-Planck-Str. 39, 74081, Heilbronn, Baden-W\u00fcrttemberg, Germany","institution_ids":["https://openalex.org/I41121874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082784814","display_name":"Clas Rurik","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Clas Rurik","raw_affiliation_strings":["codeclap, Kokhaven 20, 6230, R\u00f8dekro, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"codeclap, Kokhaven 20, 6230, R\u00f8dekro, Denmark","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5051306698"],"corresponding_institution_ids":["https://openalex.org/I41121874"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.55221218,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":"1","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":0.8907999992370605,"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":0.8907999992370605,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.030899999663233757,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.012500000186264515,"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/false-positive-paradox","display_name":"False positive paradox","score":0.7078999876976013},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.6662999987602234},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6359999775886536},{"id":"https://openalex.org/keywords/metagenomics","display_name":"Metagenomics","score":0.5916000008583069},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4839000105857849},{"id":"https://openalex.org/keywords/phylogenetic-tree","display_name":"Phylogenetic tree","score":0.43860000371932983},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.40459999442100525},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.39100000262260437},{"id":"https://openalex.org/keywords/ancestor","display_name":"Ancestor","score":0.3725999891757965}],"concepts":[{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.7078999876976013},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.6662999987602234},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6653000116348267},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6359999775886536},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.5916000008583069},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4839000105857849},{"id":"https://openalex.org/C193252679","wikidata":"https://www.wikidata.org/wiki/Q242125","display_name":"Phylogenetic tree","level":3,"score":0.43860000371932983},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.40459999442100525},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.39100000262260437},{"id":"https://openalex.org/C2780422015","wikidata":"https://www.wikidata.org/wiki/Q402152","display_name":"Ancestor","level":2,"score":0.3725999891757965},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3610000014305115},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3571999967098236},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C185181809","wikidata":"https://www.wikidata.org/wiki/Q605704","display_name":"Dozen","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.3346000015735626},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.329800009727478},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32580000162124634},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3167000114917755},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3118000030517578},{"id":"https://openalex.org/C147224247","wikidata":"https://www.wikidata.org/wiki/Q885373","display_name":"Bloom filter","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.29589998722076416},{"id":"https://openalex.org/C137858568","wikidata":"https://www.wikidata.org/wiki/Q7239","display_name":"Organism","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C90132467","wikidata":"https://www.wikidata.org/wiki/Q171184","display_name":"Phylogenetics","level":3,"score":0.26409998536109924},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C71640776","wikidata":"https://www.wikidata.org/wiki/Q16521","display_name":"Taxon","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C2279292","wikidata":"https://www.wikidata.org/wiki/Q6322851","display_name":"k-mer","level":4,"score":0.25540000200271606},{"id":"https://openalex.org/C2989486834","wikidata":"https://www.wikidata.org/wiki/Q3808900","display_name":"True positive rate","level":2,"score":0.2538999915122986}],"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":"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":"D012985","descriptor_name":"Software Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012985","descriptor_name":"Software Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","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},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12859-026-06512-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-026-06512-1","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:42304206","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42304206","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":"Journal Article"},{"id":"pmh:oai:doaj.org/article:c9150aeed9df48db86ec03861bf0260a","is_oa":false,"landing_page_url":"https://doaj.org/article/c9150aeed9df48db86ec03861bf0260a","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 27, Iss 1 (2026)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13273988","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13273988/","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/s12859-026-06512-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-026-06512-1","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":[{"display_name":"Zero hunger","id":"https://metadata.un.org/sdg/2","score":0.562119722366333}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"BACKGROUND:":[0],"The":[1,198],"consumption":[2],"of":[3,40,55,61,90,112,122,156,165,205,265],"main":[4],"memory":[5,64,285],"resources":[6],"is":[7,80],"a":[8,59,144,153,159,162,184,202],"significant":[9],"burden":[10],"in":[11,97,124,143,172],"k-mer-based":[12],"metagenomic":[13],"analysis":[14,103,191,279],"when":[15,21],"creating":[16],"related":[17,190,217,234],"databases":[18,49,149,180,222,247,322],"but":[19,36,57,245],"also":[20,87],"performing":[22],"(unique)":[23],"k-mer-counting":[24],"and":[25,50,107,120,127,167,189,276,286,300,318],"read":[26,102,135,253,301],"classification.":[27],"Genestrip":[28,46,123],"addresses":[29],"this":[30],"issue":[31],"by":[32,86],"focusing":[33],"on":[34,183,201,307],"small":[35,244,320],"freely":[37],"configurable":[38],"groups":[39],"organisms.":[41],"Regarding":[42],"the":[43,73,98,110,117,220,267],"selected":[44],"organisms,":[45],"produces":[47],"k-mer":[48,85,226,321],"results":[51],"comparable":[52],"to":[53,152,161,170,195,213,249,261,314],"those":[54],"KrakenUniq":[56],"at":[58],"fraction":[60],"its":[62],"required":[63],"resources.":[65],"Our":[66,147],"tool":[67],"ensures":[68],"that":[69,129,242],"during":[70,252],"database":[71,274,298],"generation,":[72],"most":[74],"suitable":[75],"lowest":[76,269],"common":[77,270],"ancestor":[78,271],"taxon":[79],"assigned":[81],"for":[82,109,137,210,323],"each":[83],"stored":[84],"considering":[88],"genomes":[89,140,212],"organisms":[91,111,138,218],"whose":[92,139],"k-mers":[93,157],"are":[94,141,237],"not":[95],"included":[96,142,215],"database.":[99,146],"This":[100],"enables":[101],"with":[104,283,287,327],"high":[105,133,257,293],"precision":[106],"recall":[108,251],"interest.":[113],"RESULTS:":[114],"We":[115,240],"assess":[116],"correctness,":[118],"usefulness":[119],"performance":[121,192],"different":[125],"contexts":[126],"show":[128],"it":[130],"indeed":[131],"ascertains":[132],"quality":[134],"classifications":[136],"corresponding":[145],"example":[148],"comprise":[150],"millions":[151],"few":[154,163],"billions":[155],"covering":[158],"dozen":[160],"thousands":[164],"species":[166,208],"lend":[168],"themselves":[169],"usage":[171],"tick":[173],"surveillance,":[174],"medical":[175],"diagnostics":[176],"or":[177,207],"agriculture.":[178],"All":[179],"were":[181],"generated":[182],"regular":[185,308],"PC":[186],"within":[187],"hours,":[188],"was":[193],"competitive":[194],"highly":[196],"favorable.":[197],"deliberate":[199],"focus":[200],"particular":[203,263],"set":[204],"genera":[206],"allows":[209],"more":[211],"be":[214,281,304],"from":[216,233],"while":[219,255],"resulting":[221],"remain":[223],"small.":[224],"Since":[225],"compression":[227],"becomes":[228],"unnecessary,":[229],"false":[230],"positives":[231],"emerging":[232],"information":[235],"loss":[236],"entirely":[238],"avoided.":[239],"exemplify":[241],"such":[243],"deep":[246,329],"tend":[248],"improve":[250],"classification":[254,294,302],"sustaining":[256],"precision.":[258],"CONCLUSIONS:":[259],"Due":[260],"Genestrip's":[262,310],"way":[264],"updating":[266],"k-mers'":[268],"taxa,":[272],"both":[273],"creation":[275,299],"fastq":[277],"file":[278],"can":[280],"realized":[282],"little":[284],"favorable":[288],"runtimes":[289],"as":[290,292],"well":[291],"quality.":[295],"So":[296],"both,":[297],"may":[303],"performed":[305],"even":[306],"PCs.":[309],"qualities":[311],"empower":[312],"users":[313],"flexibly":[315],"design,":[316],"build":[317],"use":[319],"their":[324],"own":[325],"needs":[326],"potentially":[328],"genomic":[330],"coverage.":[331]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-06-17T00:00:00"}