{"id":"https://openalex.org/W7204997165","doi":"https://doi.org/10.64898/2026.09.01.748377","title":"Taxonomic classification cost tracks neither sequencing depth nor community richness at single-sample scale: a measured resource protocol for 16S rRNA amplicon pipelines","display_name":"Taxonomic classification cost tracks neither sequencing depth nor community richness at single-sample scale: a measured resource protocol for 16S rRNA amplicon pipelines","publication_year":2026,"publication_date":"2026-09-01","ids":{"openalex":"https://openalex.org/W7204997165","doi":"https://doi.org/10.64898/2026.09.01.748377"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.01.748377","doi":"https://doi.org/10.64898/2026.09.01.748377","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.01.748377","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/01/2026.09.01.748377.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","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/01/2026.09.01.748377.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5149022912","display_name":"Sam Victor","orcid":"https://orcid.org/0009-0009-3061-5392","observed_orcids":["https://orcid.org/0009-0009-3061-5392"]},"institutions":[{"id":"https://openalex.org/I4387155381","display_name":"Sri Eshwar College of Engineering","ror":"https://ror.org/02f1z8215","country_code":"IN","type":"education","lineage":["https://openalex.org/I4387155381"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Sam Victor","raw_affiliation_strings":["Sri Eshwar College of Engineering, Coimbatore, Tamil Nadu, India"],"raw_orcid":"https://orcid.org/0009-0009-3061-5392","affiliations":[{"raw_affiliation_string":"Sri Eshwar College of Engineering, Coimbatore, Tamil Nadu, India","institution_ids":["https://openalex.org/I4387155381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5149053340","display_name":"Siddharth Sadasivam","orcid":"https://orcid.org/0009-0000-5712-9137","observed_orcids":["https://orcid.org/0009-0000-5712-9137"]},"institutions":[{"id":"https://openalex.org/I4387155381","display_name":"Sri Eshwar College of Engineering","ror":"https://ror.org/02f1z8215","country_code":"IN","type":"education","lineage":["https://openalex.org/I4387155381"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Siddharth Sadasivam","raw_affiliation_strings":["Sri Eshwar College of Engineering, Coimbatore, Tamil Nadu, India"],"raw_orcid":"https://orcid.org/0009-0000-5712-9137","affiliations":[{"raw_affiliation_string":"Sri Eshwar College of Engineering, Coimbatore, Tamil Nadu, India","institution_ids":["https://openalex.org/I4387155381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057610876","display_name":"S Yuvaraj","orcid":"https://orcid.org/0000-0001-5002-7285","observed_orcids":["https://orcid.org/0000-0001-5002-7285"]},"institutions":[{"id":"https://openalex.org/I4387155381","display_name":"Sri Eshwar College of Engineering","ror":"https://ror.org/02f1z8215","country_code":"IN","type":"education","lineage":["https://openalex.org/I4387155381"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Yuvaraj S","raw_affiliation_strings":["Sri Eshwar College of Engineering, Coimbatore, Tamil Nadu, India"],"raw_orcid":"https://orcid.org/0000-0001-5002-7285","affiliations":[{"raw_affiliation_string":"Sri Eshwar College of Engineering, Coimbatore, Tamil Nadu, India","institution_ids":["https://openalex.org/I4387155381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002705396","display_name":"R. Subha","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4387155381","display_name":"Sri Eshwar College of Engineering","ror":"https://ror.org/02f1z8215","country_code":"IN","type":"education","lineage":["https://openalex.org/I4387155381"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Subha R","raw_affiliation_strings":["Sri Eshwar College of Engineering, Coimbatore, Tamil Nadu, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sri Eshwar College of Engineering, Coimbatore, Tamil Nadu, India","institution_ids":["https://openalex.org/I4387155381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148989676","display_name":"Shravan Aarya P","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4387155381","display_name":"Sri Eshwar College of Engineering","ror":"https://ror.org/02f1z8215","country_code":"IN","type":"education","lineage":["https://openalex.org/I4387155381"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shravan Aarya P","raw_affiliation_strings":["Sri Eshwar College of Engineering, Coimbatore, Tamil Nadu, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sri Eshwar College of Engineering, Coimbatore, Tamil Nadu, India","institution_ids":["https://openalex.org/I4387155381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5148971645","display_name":"Gugan Satheesh","orcid":"https://orcid.org/0009-0002-8889-1022","observed_orcids":["https://orcid.org/0009-0002-8889-1022"]},"institutions":[{"id":"https://openalex.org/I4387155381","display_name":"Sri Eshwar College of Engineering","ror":"https://ror.org/02f1z8215","country_code":"IN","type":"education","lineage":["https://openalex.org/I4387155381"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Gugan Satheesh","raw_affiliation_strings":["Sri Eshwar College of Engineering, Coimbatore, Tamil Nadu, India"],"raw_orcid":"https://orcid.org/0009-0002-8889-1022","affiliations":[{"raw_affiliation_string":"Sri Eshwar College of Engineering, Coimbatore, Tamil Nadu, India","institution_ids":["https://openalex.org/I4387155381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5149022912"],"corresponding_institution_ids":["https://openalex.org/I4387155381"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":0.8047000169754028,"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":0.8047000169754028,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.06499999761581421,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11791","display_name":"Microbial Community Ecology and Physiology","score":0.053700000047683716,"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/16s-rrna-amplicon-sequencing","display_name":"16S rRNA amplicon sequencing","score":0.9070000052452087},{"id":"https://openalex.org/keywords/taxonomic-classification","display_name":"taxonomic classification","score":0.7329999804496765},{"id":"https://openalex.org/keywords/qiime2","display_name":"QIIME2","score":0.8090000152587891},{"id":"https://openalex.org/keywords/sequencing-depth","display_name":"sequencing depth","score":0.8489999771118164},{"id":"https://openalex.org/keywords/amplicon-sequence-variants","display_name":"amplicon sequence variants","score":0.8889999985694885},{"id":"https://openalex.org/keywords/community-richness","display_name":"community richness","score":0.777999997138977},{"id":"https://openalex.org/keywords/resource-allocation","display_name":"resource allocation","score":0.609000027179718},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"parallel computing","score":0.5809999704360962},{"id":"https://openalex.org/keywords/upper-respiratory-tract","display_name":"upper respiratory tract","score":0.8410000205039978},{"id":"https://openalex.org/keywords/computational-throughput","display_name":"computational throughput","score":0.31700000166893005},{"id":"https://openalex.org/keywords/shared-computing-resources","display_name":"shared computing resources","score":0.44999998807907104}],"concepts":[{"id":"https://openalex.org/C8185291","wikidata":"https://www.wikidata.org/wiki/Q2844457","display_name":"Amplicon","level":4,"score":0.7875000238418579},{"id":"https://openalex.org/C53565203","wikidata":"https://www.wikidata.org/wiki/Q17146659","display_name":"Species richness","level":2,"score":0.6122999787330627},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47519999742507935},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47269999980926514},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.44679999351501465},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4406999945640564},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.4088999927043915},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.383899986743927},{"id":"https://openalex.org/C125009961","wikidata":"https://www.wikidata.org/wiki/Q2342248","display_name":"Pyrosequencing","level":3,"score":0.3718000054359436},{"id":"https://openalex.org/C189592816","wikidata":"https://www.wikidata.org/wiki/Q427626","display_name":"Taxonomic rank","level":3,"score":0.3596999943256378},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.3476000130176544},{"id":"https://openalex.org/C49020025","wikidata":"https://www.wikidata.org/wiki/Q1059099","display_name":"Chaining","level":2,"score":0.34360000491142273},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3093000054359436},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.29829999804496765},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2928999960422516},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.28209999203681946},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28110000491142273},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C165525559","wikidata":"https://www.wikidata.org/wiki/Q224180","display_name":"Homology (biology)","level":3,"score":0.27059999108314514},{"id":"https://openalex.org/C42062724","wikidata":"https://www.wikidata.org/wiki/Q1209205","display_name":"16S ribosomal RNA","level":3,"score":0.2694000005722046},{"id":"https://openalex.org/C2779259728","wikidata":"https://www.wikidata.org/wiki/Q281472","display_name":"Suffix array","level":3,"score":0.26190000772476196},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.09.01.748377","doi":"https://doi.org/10.64898/2026.09.01.748377","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.01.748377","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/01/2026.09.01.748377.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","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.09.01.748377","doi":"https://doi.org/10.64898/2026.09.01.748377","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.01.748377","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/01/2026.09.01.748377.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","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204997165.pdf","grobid_xml":"https://content.openalex.org/works/W7204997165.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1952026831","https://openalex.org/W2004014148","https://openalex.org/W2034285706","https://openalex.org/W2079942837","https://openalex.org/W2080283023","https://openalex.org/W2091627137","https://openalex.org/W2103296919","https://openalex.org/W2107794977","https://openalex.org/W2110417468","https://openalex.org/W2150871235","https://openalex.org/W2310259903","https://openalex.org/W2397246897","https://openalex.org/W2401404581","https://openalex.org/W2605897695","https://openalex.org/W2766358903","https://openalex.org/W2787925891","https://openalex.org/W2797413896","https://openalex.org/W2807194798","https://openalex.org/W2952768760","https://openalex.org/W2963276645","https://openalex.org/W2999369378","https://openalex.org/W3094521503","https://openalex.org/W3154779414","https://openalex.org/W3213732104","https://openalex.org/W4236568581","https://openalex.org/W4280539437","https://openalex.org/W4288468208","https://openalex.org/W4301446022","https://openalex.org/W4408717485"],"related_works":["https://openalex.org/W2807194798","https://openalex.org/W4417154168","https://openalex.org/W2752925036","https://openalex.org/W309861177","https://openalex.org/W4213427769","https://openalex.org/W7214243302","https://openalex.org/W4206367847","https://openalex.org/W4288468208","https://openalex.org/W4256736905","https://openalex.org/W4241125554"],"abstract_inverted_index":{"ABSTRACT":[0],"Marker-gene":[1],"amplicon":[2],"workflows":[3],"are":[4,18,20,323],"routinely":[5],"run":[6],"on":[7],"shared":[8],"compute,":[9],"yet":[10],"the":[11,37,71,128,211,235,243,283,298,326],"cores,":[12],"memory":[13,106],"and":[14,24,50,103,159,167,175,196,217,226,264,267,312,320],"wall":[15,94],"time":[16,95],"they":[17],"given":[19],"chosen":[21],"by":[22,26,101,132,291],"convention":[23],"not":[25,69,107,125,238],"measurement.":[27],"We":[28],"present":[29],"a":[30,42,60,87,133,138,156,160,230,308],"protocol":[31],"for":[32,305],"measuring":[33],"them,":[34],"applied":[35],"to":[36,143,246],"two":[38,66,251,278],"dominant":[39],"stages":[40,67],"of":[41,90,141,280],"QIIME":[43],"2":[44],"16S":[45],"rRNA":[46],"pipeline,":[47],"DADA2":[48],"denoising":[49,74,93,146,290],"N\u00e4\u0131ve":[51],"Bayes":[52],"taxonomic":[53,219],"classification,":[54],"across":[55,86],"nine":[56],"upper-respiratory":[57],"samples":[58],"from":[59,315],"paediatric":[61],"otitis":[62],"media":[63],"cohort.":[64],"The":[65],"do":[68],"consume":[70],"same":[72],"input:":[73],"reads":[75],"every":[76,203],"sequence,":[77],"classification":[78,99,153,199,295,306],"only":[79],"those":[80],"surviving":[81],"it.":[82],"Subsampling":[83],"one":[84,206,258,303],"library":[85],"27-fold":[88],"range":[89],"sequencing":[91],"depth,":[92],"rose":[96,117],"14.3-fold":[97],"while":[98,152],"changed":[100],"1%":[102],"its":[104],"peak":[105],"at":[108,190,202,213,223,259,272],"all":[109],"(3.11":[110],"GiB).":[111],"Amplicon":[112],"sequence":[113],"variant":[114],"(ASV)":[115],"richness":[116,126],"2.8-fold":[118],"over":[119],"that":[120],"range,":[121],"so":[122,229],"this":[123],"is":[124,130],"saturating:":[127],"stage":[129],"dominated":[131],"fixed":[134,181,266],"per-invocation":[135],"cost.":[136,182],"Across":[137],"body-site":[139],"gradient":[140],"5":[142,261],"70":[144],"ASVs,":[145],"followed":[147,154],"read":[148,292],"count":[149],"(exponent":[150],"0.75)":[151],"neither:":[155],"5-ASV":[157],"effusion":[158],"70-ASV":[161],"adenoid":[162],"community":[163],"cost":[164],"40.81":[165],"s":[166,174],"40.79":[168],"s.":[169],"One":[170],"ASV":[171],"took":[172,177],"36.20":[173],"218":[176],"37.27":[178],"s,":[179],"97%":[180],"Thread-level":[183],"parallelism":[184],"offered":[185],"little":[186],"benefit.":[187],"Denoising":[188],"peaked":[189],"1.18":[191],"\u00d7":[192],"near":[193],"8":[194],"threads":[195],"then":[197],"declined;":[198],"was":[200],"slower":[201],"setting":[204],"above":[205,282],"job,":[207],"consuming":[208],"10.5":[209],"times":[210],"CPU":[212],"40.":[214],"Representative":[215],"sequences":[216,249],"their":[218],"assignments":[220],"were":[221],"identical":[222],"1,":[224],"4":[225],"40":[227],"threads,":[228],"reduced":[231],"allocation":[232],"changes":[233],"what":[234,239],"analysis":[236,321],"costs,":[237],"it":[240],"reports.":[241],"Extending":[242],"query":[244],"set":[245],"10":[247],"000":[248,262],"located":[250],"distinct":[252],"boundaries:":[253],"eight":[254],"jobs":[255],"first":[256],"beat":[257],"roughly":[260,277],"queries,":[263],"fitted":[265],"per-query":[268],"costs":[269],"become":[270],"equal":[271],"15":[273],"248.":[274],"Both":[275],"lie":[276],"orders":[279],"magnitude":[281],"richest":[284],"single":[285],"sample":[286],"measured.":[287],"Practically:":[288],"size":[289],"count,":[293],"calibrate":[294],"once":[296],"against":[297],"reference":[299],"in":[300],"use,":[301],"request":[302],"job":[304],"below":[307],"few":[309],"thousand":[310],"sequences,":[311],"take":[313],"throughput":[314],"sample-level":[316],"parallelism.":[317],"Protocol,":[318],"data":[319],"code":[322],"released":[324],"with":[325],"pipeline.":[327]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-09-02T00:00:00"}