{"id":"https://openalex.org/W7225115282","doi":"https://doi.org/10.5281/zenodo.23899197","title":"d\u0101naSeq illumina_amplicon: primer-aware amplicon denoising with a Python port of DADA2","display_name":"d\u0101naSeq illumina_amplicon: primer-aware amplicon denoising with a Python port of DADA2","publication_year":2026,"publication_date":"2026-11-02","ids":{"openalex":"https://openalex.org/W7225115282","doi":"https://doi.org/10.5281/zenodo.23899197"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.23899197","doi":"https://doi.org/10.5281/zenodo.23899197","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23899197","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"volume":null,"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.23899197","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054521581","display_name":"R. Eric Collins","orcid":"https://orcid.org/0000-0002-5858-2395","observed_orcids":["https://orcid.org/0000-0002-5858-2395"]},"institutions":[{"id":"https://openalex.org/I46247651","display_name":"University of Manitoba","ror":"https://ror.org/02gfys938","country_code":"CA","type":"education","lineage":["https://openalex.org/I46247651"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Collins, R. Eric","raw_affiliation_strings":["University of Manitoba"],"raw_orcid":"https://orcid.org/0000-0002-5858-2395","affiliations":[{"raw_affiliation_string":"University of Manitoba","institution_ids":["https://openalex.org/I46247651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5054521581"],"corresponding_institution_ids":["https://openalex.org/I46247651"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":0.8666999936103821,"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":0.8666999936103821,"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":0.060600001364946365,"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/T11791","display_name":"Microbial Community Ecology and Physiology","score":0.04349999874830246,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/amplicon-sequence-variants","display_name":"amplicon sequence variants","score":0.9110000133514404},{"id":"https://openalex.org/keywords/dada2","display_name":"DADA2","score":0.7419999837875366},{"id":"https://openalex.org/keywords/nextflow-pipeline","display_name":"Nextflow pipeline","score":0.6430000066757202},{"id":"https://openalex.org/keywords/taxonomic-assignment","display_name":"taxonomic assignment","score":0.6430000066757202},{"id":"https://openalex.org/keywords/containerized-workflows","display_name":"containerized workflows","score":0.49300000071525574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7253999710083008},{"id":"https://openalex.org/C8185291","wikidata":"https://www.wikidata.org/wiki/Q2844457","display_name":"Amplicon","level":4,"score":0.6926000118255615},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.6069999933242798},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5019999742507935},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.49219998717308044},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.4487000107765198},{"id":"https://openalex.org/C174183944","wikidata":"https://www.wikidata.org/wiki/Q334661","display_name":"MIT License","level":3,"score":0.3937999904155731},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.3822000026702881},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.37720000743865967},{"id":"https://openalex.org/C2777683733","wikidata":"https://www.wikidata.org/wiki/Q201456","display_name":"Directory","level":2,"score":0.3756999969482422},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.3612000048160553},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.3434999883174896},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3154999911785126},{"id":"https://openalex.org/C2776841711","wikidata":"https://www.wikidata.org/wiki/Q856","display_name":"Barcode","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.28870001435279846},{"id":"https://openalex.org/C97250363","wikidata":"https://www.wikidata.org/wiki/Q235557","display_name":"File format","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C196832560","wikidata":"https://www.wikidata.org/wiki/Q8815","display_name":"ASCII","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.27810001373291016},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C79386861","wikidata":"https://www.wikidata.org/wiki/Q476697","display_name":"DNA profiling","level":3,"score":0.2768000066280365},{"id":"https://openalex.org/C2993206177","wikidata":"https://www.wikidata.org/wiki/Q2844457","display_name":"Amplicon sequencing","level":4,"score":0.2718000113964081},{"id":"https://openalex.org/C2777563447","wikidata":"https://www.wikidata.org/wiki/Q7243397","display_name":"Primer (cosmetics)","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2694000005722046},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.26010000705718994},{"id":"https://openalex.org/C67953723","wikidata":"https://www.wikidata.org/wiki/Q192525","display_name":"Workstation","level":2,"score":0.2556999921798706}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.23899197","doi":"https://doi.org/10.5281/zenodo.23899197","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23899197","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.5281/zenodo.23899198","doi":"https://doi.org/10.5281/zenodo.23899198","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23899198","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.5281/zenodo.23899197","doi":"https://doi.org/10.5281/zenodo.23899197","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23899197","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4412065973","https://openalex.org/W3043927350","https://openalex.org/W4206367847","https://openalex.org/W3104537718","https://openalex.org/W2401404581","https://openalex.org/W3161184439","https://openalex.org/W2520313574","https://openalex.org/W7225106466","https://openalex.org/W2989719480","https://openalex.org/W3028092618"],"abstract_inverted_index":{"Motivation:":[0],"Marker-gene":[1],"amplicon":[2,109],"studies":[3],"of":[4,63,119],"environmental":[5],"samples":[6,47],"are":[7,159],"increasingly":[8],"assembled":[9],"from":[10,78,86,192,197],"many":[11],"sequencing":[12,126],"runs,":[13],"several":[14],"primer":[15,166],"pairs":[16],"and":[17,52,105,128,149,154,162,167,175,177,221],"public":[18],"archive":[19],"submissions,":[20],"some":[21],"with":[22,103,113,186,207],"primers":[23,42,85,102],"already":[24],"removed.":[25],"Processing":[26],"such":[27],"collections":[28],"reproducibly":[29],"on":[30,212],"shared":[31],"high-performance":[32],"computing":[33],"(HPC)":[34],"systems":[35],"requires":[36],"a":[37,55,79,82,90,141,155,170,181,193,198,208,213,217],"workflow":[38],"that":[39,95],"records":[40],"which":[41],"each":[43],"sample":[44],"carried,":[45],"groups":[46],"sensibly":[48],"for":[49,180],"error":[50,122],"modelling,":[51],"runs":[53,191],"without":[54],"separate":[56],"R":[57],"installation.":[58],"Results:":[59],"illumina_amplicon":[60],"is":[61,224],"one":[62,99,135],"six":[64,187],"Nextflow":[65],"DSL2":[66],"pipelines":[67],"in":[68],"the":[69,87,115,160,203,227],"d\u0101naSeq":[70,223],"suite.":[71],"It":[72],"takes":[73],"paired-end":[74],"Illumina":[75],"FASTQ":[76],"files":[77],"directory":[80],"or":[81,136,196,215],"samplesheet,":[83],"detects":[84],"reads":[88,107],"against":[89,134],"curated":[91],"catalogue,":[92],"splits":[93],"accessions":[94],"contain":[96],"more":[97,137],"than":[98],"assay,":[100],"removes":[101],"cutadapt,":[104],"denoises":[106],"into":[108],"sequence":[110],"variants":[111],"(ASVs)":[112],"papa2,":[114],"author's":[116],"Python":[117],"port":[118],"DADA2,":[120],"using":[121],"models":[123],"grouped":[124],"by":[125],"run":[127,171],"assay.":[129],"Optional":[130],"steps":[131],"assign":[132],"taxonomy":[133,163],"reference":[138],"databases,":[139],"build":[140],"MAFFT/FastTree":[142],"phylogeny,":[143],"renormalize":[144],"counts":[145],"within":[146],"taxonomic":[147],"groups,":[148],"compute":[150],"Bray\u2013Curtis":[151],"t-SNE":[152],"ordinations":[153],"CLR-correlation":[156],"network.":[157],"Outputs":[158],"ASV":[161,184],"tables,":[164],"per-sample":[165],"read-count":[168],"reports,":[169],"manifest":[172],"recording":[173],"versions":[174],"parameters,":[176],"JSON":[178],"data":[179],"Svelte":[182],"single-page":[183],"explorer":[185],"views.":[188],"The":[189],"pipeline":[190],"conda":[194],"environment":[195],"container":[199],"image":[200],"published":[201],"to":[202,235],"GitHub":[204],"Container":[205],"Registry":[206],"matching":[209],"Apptainer":[210],"SIF,":[211],"workstation":[214],"inside":[216],"Slurm":[218],"allocation.":[219],"Availability":[220],"implementation:":[222],"released":[225],"under":[226],"MIT":[228],"license":[229],"at":[230,240],"https://github.com/rec3141/danaSeq":[231],"(this":[232],"description":[233],"corresponds":[234],"release":[236],"v1.3.0,":[237],"https://github.com/rec3141/danaSeq/releases/tag/v1.3.0);":[238],"documentation":[239],"https://rec3141.github.io/danaSeq/.":[241]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-11-03T00:00:00"}