{"id":"https://openalex.org/W4416411860","doi":"https://doi.org/10.1093/bioinformatics/btaf632","title":"Cleanifier: contamination removal from microbial sequences using spaced seeds of a human pangenome index","display_name":"Cleanifier: contamination removal from microbial sequences using spaced seeds of a human pangenome index","publication_year":2025,"publication_date":"2025-11-16","ids":{"openalex":"https://openalex.org/W4416411860","doi":"https://doi.org/10.1093/bioinformatics/btaf632","pmid":"https://pubmed.ncbi.nlm.nih.gov/41252442"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btaf632","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf632","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btaf632/65372192/btaf632.pdf","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://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btaf632/65372192/btaf632.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021804671","display_name":"Jens Zentgraf","orcid":"https://orcid.org/0000-0001-9444-2755"},"institutions":[{"id":"https://openalex.org/I4210120512","display_name":"Hochschule f\u00fcr Technik und Wirtschaft des Saarlandes","ror":"https://ror.org/02ge27m07","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210120512"]},{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jens Zentgraf","raw_affiliation_strings":["Algorithmic Bioinformatics, Saarland University , Saarbr\u00fccken 66123,","Center for Bioinformatics Saar, Saarland Informatics Campus , Saarbr\u00fccken 66123,","Saarbr\u00fccken Graduate School of Computer Science, Saarland Informatics Campus , Saarbr\u00fccken 66123,","Saarland Informatics Campus Center for Bioinformatics Saar, , Saarbr\u00fccken, 66123,","Saarland Informatics Campus Saarbr\u00fccken Graduate School of Computer Science, , Saarbr\u00fccken, 66123,"],"raw_orcid":"https://orcid.org/0000-0001-9444-2755","affiliations":[{"raw_affiliation_string":"Algorithmic Bioinformatics, Saarland University , Saarbr\u00fccken 66123,","institution_ids":["https://openalex.org/I91712215"]},{"raw_affiliation_string":"Center for Bioinformatics Saar, Saarland Informatics Campus , Saarbr\u00fccken 66123,","institution_ids":["https://openalex.org/I91712215"]},{"raw_affiliation_string":"Saarbr\u00fccken Graduate School of Computer Science, Saarland Informatics Campus , Saarbr\u00fccken 66123,","institution_ids":["https://openalex.org/I4210120512"]},{"raw_affiliation_string":"Saarland Informatics Campus Center for Bioinformatics Saar, , Saarbr\u00fccken, 66123,","institution_ids":["https://openalex.org/I91712215"]},{"raw_affiliation_string":"Saarland Informatics Campus Saarbr\u00fccken Graduate School of Computer Science, , Saarbr\u00fccken, 66123,","institution_ids":["https://openalex.org/I4210120512"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042896044","display_name":"Johanna Elena Schmitz","orcid":"https://orcid.org/0009-0002-6377-2561"},"institutions":[{"id":"https://openalex.org/I4210120512","display_name":"Hochschule f\u00fcr Technik und Wirtschaft des Saarlandes","ror":"https://ror.org/02ge27m07","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210120512"]},{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Johanna Elena Schmitz","raw_affiliation_strings":["Algorithmic Bioinformatics, Saarland University , Saarbr\u00fccken 66123,","Center for Bioinformatics Saar, Saarland Informatics Campus , Saarbr\u00fccken 66123,","Saarbr\u00fccken Graduate School of Computer Science, Saarland Informatics Campus , Saarbr\u00fccken 66123,","Saarland Informatics Campus Saarbr\u00fccken Graduate School of Computer Science, , Saarbr\u00fccken, 66123,","Saarland University Algorithmic Bioinformatics, , Saarbr\u00fccken, 66123,"],"raw_orcid":"https://orcid.org/0009-0002-6377-2561","affiliations":[{"raw_affiliation_string":"Algorithmic Bioinformatics, Saarland University , Saarbr\u00fccken 66123,","institution_ids":["https://openalex.org/I91712215"]},{"raw_affiliation_string":"Center for Bioinformatics Saar, Saarland Informatics Campus , Saarbr\u00fccken 66123,","institution_ids":["https://openalex.org/I91712215"]},{"raw_affiliation_string":"Saarbr\u00fccken Graduate School of Computer Science, Saarland Informatics Campus , Saarbr\u00fccken 66123,","institution_ids":["https://openalex.org/I4210120512"]},{"raw_affiliation_string":"Saarland Informatics Campus Saarbr\u00fccken Graduate School of Computer Science, , Saarbr\u00fccken, 66123,","institution_ids":["https://openalex.org/I4210120512"]},{"raw_affiliation_string":"Saarland University Algorithmic Bioinformatics, , Saarbr\u00fccken, 66123,","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059606670","display_name":"Sven Rahmann","orcid":"https://orcid.org/0000-0002-8536-6065"},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sven Rahmann","raw_affiliation_strings":["Algorithmic Bioinformatics, Saarland University , Saarbr\u00fccken 66123,","Center for Bioinformatics Saar, Saarland Informatics Campus , Saarbr\u00fccken 66123,","Saarland University Algorithmic Bioinformatics, , Saarbr\u00fccken, 66123,"],"raw_orcid":"https://orcid.org/0000-0002-8536-6065","affiliations":[{"raw_affiliation_string":"Algorithmic Bioinformatics, Saarland University , Saarbr\u00fccken 66123,","institution_ids":["https://openalex.org/I91712215"]},{"raw_affiliation_string":"Center for Bioinformatics Saar, Saarland Informatics Campus , Saarbr\u00fccken 66123,","institution_ids":["https://openalex.org/I91712215"]},{"raw_affiliation_string":"Saarland University Algorithmic Bioinformatics, , Saarbr\u00fccken, 66123,","institution_ids":["https://openalex.org/I91712215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":1.196,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85934079,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"42","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12859","display_name":"Cell Image Analysis Techniques","score":0.08420000225305557,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.08420000225305557,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"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/T10593","display_name":"Bacterial biofilms and quorum sensing","score":0.04639999940991402,"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/T11970","display_name":"Molecular Biology Techniques and Applications","score":0.04149999842047691,"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/contamination","display_name":"Contamination","score":0.6740999817848206},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.6147000193595886}],"concepts":[{"id":"https://openalex.org/C112570922","wikidata":"https://www.wikidata.org/wiki/Q60528603","display_name":"Contamination","level":2,"score":0.6740999817848206},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.6147000193595886},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3617999851703644},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.3321000039577484},{"id":"https://openalex.org/C31903555","wikidata":"https://www.wikidata.org/wiki/Q1637030","display_name":"Food science","level":1,"score":0.32359999418258667},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3109000027179718},{"id":"https://openalex.org/C39432304","wikidata":"https://www.wikidata.org/wiki/Q188847","display_name":"Environmental science","level":0,"score":0.3050999939441681},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.2928999960422516},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2847999930381775},{"id":"https://openalex.org/C42972112","wikidata":"https://www.wikidata.org/wiki/Q170201","display_name":"Veterinary medicine","level":1,"score":0.2676999866962433}],"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":"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":"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":"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":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"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},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D059018","descriptor_name":"DNA Contamination","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059018","descriptor_name":"DNA Contamination","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059018","descriptor_name":"DNA Contamination","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059018","descriptor_name":"DNA Contamination","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D064307","descriptor_name":"Microbiota","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D064307","descriptor_name":"Microbiota","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D064307","descriptor_name":"Microbiota","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D064307","descriptor_name":"Microbiota","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btaf632","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf632","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btaf632/65372192/btaf632.pdf","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:41252442","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41252442","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:12758600","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12758600/","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/btaf632","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf632","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btaf632/65372192/btaf632.pdf","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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416411860.pdf","grobid_xml":"https://content.openalex.org/works/W4416411860.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W2103441770","https://openalex.org/W2104549677","https://openalex.org/W2116412478","https://openalex.org/W2128769815","https://openalex.org/W2165446840","https://openalex.org/W2170551349","https://openalex.org/W2245493112","https://openalex.org/W2737172134","https://openalex.org/W2789843538","https://openalex.org/W2949098970","https://openalex.org/W2950964375","https://openalex.org/W2952870794","https://openalex.org/W2990249310","https://openalex.org/W2990618091","https://openalex.org/W3122109253","https://openalex.org/W3199437591","https://openalex.org/W4220999759","https://openalex.org/W4225258284","https://openalex.org/W4297498241","https://openalex.org/W4308637256","https://openalex.org/W4376133202","https://openalex.org/W4376609018","https://openalex.org/W4389234745","https://openalex.org/W4393934002","https://openalex.org/W4405231264","https://openalex.org/W4406558191","https://openalex.org/W4408141939","https://openalex.org/W4410190590","https://openalex.org/W4411226742","https://openalex.org/W4417085603","https://openalex.org/W6910344901","https://openalex.org/W6928758969","https://openalex.org/W6948004943"],"related_works":[],"abstract_inverted_index":{"MOTIVATION:":[0],"The":[1,233],"first":[2],"step":[3],"when":[4],"working":[5],"with":[6,158,172],"DNA":[7],"data":[8,27,36,40],"of":[9,72,107,117,152,156],"human-derived":[10],"microbiomes":[11],"is":[12,75,120,205,223,238],"to":[13,129,181,192],"remove":[14],"human":[15,31,39,49,73,93,109,235],"contamination":[16,50,74,94],"for":[17,30,89],"two":[18,136],"reasons.":[19],"First,":[20],"many":[21],"countries":[22],"have":[23],"strict":[24],"privacy":[25],"and":[26,69,84,91,112,115,126,145,230],"protection":[28],"guidelines":[29],"sequence":[32],"data,":[33],"so":[34],"microbiome":[35],"containing":[37],"partly":[38],"cannot":[41],"be":[42],"easily":[43],"further":[44],"processed":[45],"or":[46,61,99],"published.":[47],"Second,":[48],"may":[51],"cause":[52],"problems":[53],"in":[54],"downstream":[55],"analysis,":[56],"such":[57],"as":[58],"metagenomic":[59],"binning":[60],"genome":[62],"assembly.":[63],"For":[64],"large-scale":[65],"metagenomics":[66],"projects,":[67],"fast":[68,83],"accurate":[70],"removal":[71],"therefore":[76],"critical.":[77],"RESULTS:":[78],"We":[79],"introduce":[80],"Cleanifier,":[81],"a":[82,104,150,177,196],"memory":[85,190],"frugal":[86],"alignment-free":[87],"tool":[88],"detecting":[90],"removing":[92],"based":[95],"on":[96,215],"gapped":[97,110,131,143],"k-mers,":[98,111],"spaced":[100],"seeds.":[101],"Cleanifier":[102,134,157,168,187,204,222],"uses":[103],"pangenome":[105,236],"index":[106,237],"known":[108],"the":[113,164,169,183,201,216],"creation":[114],"use":[116,195,211],"alternative":[118],"references":[119],"also":[121],"possible.":[122],"Reads":[123],"are":[124],"classified":[125],"filtered":[127],"according":[128],"their":[130],"k-mer":[132,185],"content.":[133],"supports":[135],"filtering":[137],"modes:":[138],"one":[139,146],"that":[140,147,163,194],"queries":[141,148],"all":[142],"k-mers":[144],"only":[149],"sample":[151],"them.":[153],"A":[154],"comparison":[155],"other":[159],"state-of-the-art":[160],"tools":[161],"shows":[162],"sampling":[165,213],"mode":[166],"makes":[167],"fastest":[170],"method":[171],"comparable":[173],"accuracy.":[174],"When":[175],"using":[176],"probabilistic":[178],"Cuckoo":[179],"filter":[180],"store":[182],"complete":[184],"set,":[186],"has":[188],"similar":[189],"requirements":[191],"methods":[193,214],"sampled":[197],"minimizer":[198],"index.":[199,218],"At":[200],"same":[202,217],"time,":[203],"more":[206],"flexible,":[207],"because":[208],"it":[209],"can":[210],"different":[212],"AVAILABILITY":[219],"AND":[220],"IMPLEMENTATION:":[221],"available":[224,239],"via":[225],"gitlab":[226],"(https://gitlab.com/rahmannlab/cleanifier),":[227],"PyPi":[228],"(https://pypi.org/project/cleanifier/),":[229],"Bioconda":[231],"(https://anaconda.org/bioconda/cleanifier).":[232],"pre-computed":[234],"at":[240],"Zenodo":[241],"(https://doi.org/10.5281/zenodo.15639519).":[242]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-19T00:00:00"}
