{"id":"https://openalex.org/W7204666317","doi":"https://doi.org/10.64898/2026.08.25.746527","title":"AmPair: automating housekeeping-gene primer design for species-level metataxonomics","display_name":"AmPair: automating housekeeping-gene primer design for species-level metataxonomics","publication_year":2026,"publication_date":"2026-08-28","ids":{"openalex":"https://openalex.org/W7204666317","doi":"https://doi.org/10.64898/2026.08.25.746527"},"language":"en","primary_location":{"id":"doi:10.64898/2026.08.25.746527","doi":"https://doi.org/10.64898/2026.08.25.746527","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.25.746527","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/08/28/2026.08.25.746527.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":null,"license_id":null,"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/2026/08/28/2026.08.25.746527.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031659442","display_name":"Xinming Xu","orcid":"https://orcid.org/0000-0002-3203-4526","observed_orcids":["https://orcid.org/0000-0002-3203-4526"]},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]},{"id":"https://openalex.org/I4210107786","display_name":"Netherlands Institute of Ecology","ror":"https://ror.org/01g25jp36","country_code":"NL","type":"facility","lineage":["https://openalex.org/I1322597698","https://openalex.org/I4210107786"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Xinming Xu","raw_affiliation_strings":["Department of Microbial Ecology, Netherlands Institute of Ecology (NIOO-KNAW), Droevendaalsesteeg 10, 6708 PB Wageningen, The Netherlands","Institute of Biology, Leiden University, Leiden 2333 BE, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-3203-4526","affiliations":[{"raw_affiliation_string":"Department of Microbial Ecology, Netherlands Institute of Ecology (NIOO-KNAW), Droevendaalsesteeg 10, 6708 PB Wageningen, The Netherlands","institution_ids":["https://openalex.org/I4210107786"]},{"raw_affiliation_string":"Institute of Biology, Leiden University, Leiden 2333 BE, The Netherlands","institution_ids":["https://openalex.org/I121797337"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5148591439","display_name":"Xinbin Yang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinbin Yang","raw_affiliation_strings":["Department Center of Big Data and Artificial Intelligence, Huanghe Science and Technology University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department Center of Big Data and Artificial Intelligence, Huanghe Science and Technology University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5031659442"],"corresponding_institution_ids":["https://openalex.org/I121797337","https://openalex.org/I4210107786"],"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":0.9189000129699707,"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":0.9189000129699707,"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/T11791","display_name":"Microbial Community Ecology and Physiology","score":0.06019999831914902,"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/T12640","display_name":"Environmental DNA in Biodiversity Studies","score":0.009800000116229057,"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/primer-design","display_name":"primer design","score":0.7059999704360962},{"id":"https://openalex.org/keywords/housekeeping-genes","display_name":"housekeeping genes","score":0.9929999709129333},{"id":"https://openalex.org/keywords/species-discrimination","display_name":"species discrimination","score":0.7039999961853027},{"id":"https://openalex.org/keywords/16s-rrna-gene","display_name":"16S rRNA gene","score":0.7200000286102295},{"id":"https://openalex.org/keywords/metataxonomics","display_name":"metataxonomics","score":0.7860000133514404},{"id":"https://openalex.org/keywords/amplicon-sequencing","display_name":"amplicon sequencing","score":0.753000020980835},{"id":"https://openalex.org/keywords/tuf-gene","display_name":"tuf gene","score":0.7360000014305115},{"id":"https://openalex.org/keywords/bacillus","display_name":"Bacillus","score":0.984000027179718},{"id":"https://openalex.org/keywords/conserved-domains","display_name":"conserved domains","score":0.5170000195503235},{"id":"https://openalex.org/keywords/variable-region","display_name":"variable region","score":0.5960000157356262},{"id":"https://openalex.org/keywords/nanopore-sequencing","display_name":"nanopore sequencing","score":0.6650000214576721},{"id":"https://openalex.org/keywords/bacterial-community-profiling","display_name":"bacterial community profiling","score":0.7310000061988831},{"id":"https://openalex.org/keywords/snakemake-workflow","display_name":"Snakemake workflow","score":0.777999997138977}],"concepts":[{"id":"https://openalex.org/C33922130","wikidata":"https://www.wikidata.org/wiki/Q419232","display_name":"Housekeeping gene","level":4,"score":0.7333999872207642},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.7053999900817871},{"id":"https://openalex.org/C8185291","wikidata":"https://www.wikidata.org/wiki/Q2844457","display_name":"Amplicon","level":4,"score":0.6769000291824341},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.6175000071525574},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.6000000238418579},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5763000249862671},{"id":"https://openalex.org/C101985253","wikidata":"https://www.wikidata.org/wiki/Q1073526","display_name":"Shotgun sequencing","level":4,"score":0.5192000269889832},{"id":"https://openalex.org/C2777563447","wikidata":"https://www.wikidata.org/wiki/Q7243397","display_name":"Primer (cosmetics)","level":2,"score":0.4943000078201294},{"id":"https://openalex.org/C42062724","wikidata":"https://www.wikidata.org/wiki/Q1209205","display_name":"16S ribosomal RNA","level":3,"score":0.4562999904155731},{"id":"https://openalex.org/C2775905019","wikidata":"https://www.wikidata.org/wiki/Q192572","display_name":"In silico","level":3,"score":0.43950000405311584},{"id":"https://openalex.org/C67905577","wikidata":"https://www.wikidata.org/wiki/Q215980","display_name":"Ribosomal RNA","level":3,"score":0.38670000433921814},{"id":"https://openalex.org/C61053724","wikidata":"https://www.wikidata.org/wiki/Q1154615","display_name":"Sequence analysis","level":3,"score":0.34220001101493835},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.3287000060081482},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.3158999979496002},{"id":"https://openalex.org/C126513998","wikidata":"https://www.wikidata.org/wiki/Q8973627","display_name":"Nanopore sequencing","level":4,"score":0.30559998750686646},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.29330000281333923},{"id":"https://openalex.org/C125009961","wikidata":"https://www.wikidata.org/wiki/Q2342248","display_name":"Pyrosequencing","level":3,"score":0.2773999869823456},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.2736000120639801},{"id":"https://openalex.org/C193252679","wikidata":"https://www.wikidata.org/wiki/Q242125","display_name":"Phylogenetic tree","level":3,"score":0.26159998774528503},{"id":"https://openalex.org/C180754005","wikidata":"https://www.wikidata.org/wiki/Q80726","display_name":"Allele","level":3,"score":0.2563000023365021},{"id":"https://openalex.org/C189592816","wikidata":"https://www.wikidata.org/wiki/Q427626","display_name":"Taxonomic rank","level":3,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.08.25.746527","doi":"https://doi.org/10.64898/2026.08.25.746527","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.25.746527","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/08/28/2026.08.25.746527.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":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.08.25.746527","doi":"https://doi.org/10.64898/2026.08.25.746527","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.25.746527","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/08/28/2026.08.25.746527.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":null,"license_id":null,"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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204666317.pdf","grobid_xml":"https://content.openalex.org/works/W7204666317.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W3192044664"],"related_works":["https://openalex.org/W7161558468","https://openalex.org/W7162797479","https://openalex.org/W3000206804","https://openalex.org/W4415735100","https://openalex.org/W7147060406","https://openalex.org/W2892657299","https://openalex.org/W4288707402","https://openalex.org/W6911107065","https://openalex.org/W4416975440","https://openalex.org/W4389047712"],"abstract_inverted_index":{"Abstract":[0],"Amplicon":[1,69],"sequencing":[2,48,70],"of":[3,67,71,128,161],"the":[4,9,26,141,145,153,182,197],"16S":[5,34,184],"rRNA":[6,35,185],"gene":[7,147],"is":[8,22,66],"most":[10],"widely":[11],"used":[12],"approach":[13],"for":[14,90,181],"profiling":[15],"bacterial":[16],"communities,":[17],"but":[18,57],"its":[19],"taxonomic":[20],"resolution":[21,56],"typically":[23],"limited":[24],"to":[25,85,189,212],"genus":[27,65,106,142],"level.":[28],"Many":[29],"species":[30,40],"carry":[31],"multiple":[32,167],"divergent":[33],"alleles":[36,168],"that":[37,44],"overlap":[38],"across":[39,136],"boundaries,":[41],"an":[42],"ambiguity":[43],"even":[45],"full-length,":[46],"long-read":[47],"cannot":[49],"fully":[50],"resolve.":[51],"Shotgun":[52],"metagenomics":[53],"achieves":[54],"species-level":[55,129,213],"remains":[58],"costly,":[59],"particularly":[60],"when":[61],"only":[62,164],"a":[63,78,91,99,104,124,150,190,207],"single":[64],"interest.":[68],"rapidly":[72],"evolving,":[73],"protein-coding":[74],"housekeeping":[75,112,146],"genes":[76],"offers":[77,206],"cost-effective":[79],"alternative,":[80],"yet":[81],"no":[82],"tool":[83],"exists":[84],"identify":[86],"suitable":[87],"primer":[88,117,154],"sets":[89],"given":[92,103],"target":[93,105],"taxon.":[94],"Here":[95],"we":[96],"present":[97],"AmPair,":[98],"Snakemake":[100],"pipeline":[101],"that,":[102],"and":[107,115,131,144,169,178,209],"one":[108],"or":[109],"more":[110],"candidate":[111],"genes,":[113],"designs":[114],"ranks":[116],"pairs":[118],"binding":[119],"conserved":[120],"regions":[121],"while":[122],"flanking":[123],"variable":[125],"region":[126],"capable":[127],"discrimination,":[130],"validates":[132],"them":[133],"in":[134],"silico":[135],"all":[137],"available":[138],"genomes.":[139],"Using":[140],"Bacillus":[143,191],"tuf":[148],"as":[149],"case":[151],"study,":[152],"set":[155],"recommended":[156],"by":[157,194],"AmPair":[158,204],"amplified":[159],"99%":[160],"2,392":[162],"genomes;":[163],"0.04%":[165],"carried":[166],"none":[170],"showed":[171],"inter-species":[172],"allele":[173],"overlap,":[174],"compared":[175],"with":[176],"91.41%":[177],"69.49%,":[179],"respectively,":[180],"standard":[183],"V1\u2013V9":[186],"region.":[187],"Applied":[188],"community":[192,214],"profiled":[193],"Nanopore":[195],"sequencing,":[196],"same":[198],"primers":[199],"resolved":[200],"closely":[201],"related":[202],"species.":[203],"thus":[205],"generalizable":[208],"accessible":[210],"route":[211],"profiling.":[215]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-08-30T00:00:00"}
