{"id":"https://openalex.org/W7220999514","doi":"https://doi.org/10.64898/2026.10.07.757277","title":"Unsupervised Clustering Enables Cohort-Specific Variant Recalibration in Crops","display_name":"Unsupervised Clustering Enables Cohort-Specific Variant Recalibration in Crops","publication_year":2026,"publication_date":"2026-10-08","ids":{"openalex":"https://openalex.org/W7220999514","doi":"https://doi.org/10.64898/2026.10.07.757277"},"language":"en","primary_location":{"id":"doi:10.64898/2026.10.07.757277","doi":"https://doi.org/10.64898/2026.10.07.757277","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.07.757277","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/08/2026.10.07.757277.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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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/2026/10/08/2026.10.07.757277.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012373938","display_name":"Thomas Bergmann","orcid":"https://orcid.org/0009-0005-5430-5381","observed_orcids":["https://orcid.org/0009-0005-5430-5381"]},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Thomas Bergmann","raw_affiliation_strings":["Centre for Applied Bioinformatics, University of Western Australia, 6009 Perth, Australia","School of Biological Sciences, University of Western Australia, 6009 Perth, Australia"],"raw_orcid":"https://orcid.org/0009-0005-5430-5381","affiliations":[{"raw_affiliation_string":"Centre for Applied Bioinformatics, University of Western Australia, 6009 Perth, Australia","institution_ids":["https://openalex.org/I177877127"]},{"raw_affiliation_string":"School of Biological Sciences, University of Western Australia, 6009 Perth, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115067284","display_name":"Tessa R MacNish","orcid":"https://orcid.org/0009-0008-8985-7348","observed_orcids":["https://orcid.org/0009-0008-8985-7348"]},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tessa R. MacNish","raw_affiliation_strings":["Centre for Applied Bioinformatics, University of Western Australia, 6009 Perth, Australia","School of Biological Sciences, University of Western Australia, 6009 Perth, Australia"],"raw_orcid":"https://orcid.org/0009-0008-8985-7348","affiliations":[{"raw_affiliation_string":"Centre for Applied Bioinformatics, University of Western Australia, 6009 Perth, Australia","institution_ids":["https://openalex.org/I177877127"]},{"raw_affiliation_string":"School of Biological Sciences, University of Western Australia, 6009 Perth, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086358262","display_name":"Jacqueline Batley","orcid":"https://orcid.org/0000-0002-5391-5824","observed_orcids":["https://orcid.org/0000-0002-5391-5824"]},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jacqueline Batley","raw_affiliation_strings":["School of Biological Sciences, University of Western Australia, 6009 Perth, Australia"],"raw_orcid":"https://orcid.org/0000-0002-5391-5824","affiliations":[{"raw_affiliation_string":"School of Biological Sciences, University of Western Australia, 6009 Perth, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016277624","display_name":"David Edwards","orcid":"https://orcid.org/0000-0001-7599-6760","observed_orcids":["https://orcid.org/0000-0001-7599-6760","https://orcid.org/0000-0003-4488-8083"]},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"David Edwards","raw_affiliation_strings":["Centre for Applied Bioinformatics, University of Western Australia, 6009 Perth, Australia","School of Biological Sciences, University of Western Australia, 6009 Perth, Australia"],"raw_orcid":"https://orcid.org/0000-0001-7599-6760","affiliations":[{"raw_affiliation_string":"Centre for Applied Bioinformatics, University of Western Australia, 6009 Perth, Australia","institution_ids":["https://openalex.org/I177877127"]},{"raw_affiliation_string":"School of Biological Sciences, University of Western Australia, 6009 Perth, Australia","institution_ids":["https://openalex.org/I177877127"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5012373938"],"corresponding_institution_ids":["https://openalex.org/I177877127"],"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":0.49219998717308044,"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":0.49219998717308044,"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/T11468","display_name":"Genetic Mapping and Diversity in Plants and Animals","score":0.30570000410079956,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T10594","display_name":"Genetic and phenotypic traits in livestock","score":0.14669999480247498,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/unsupervised-clustering","display_name":"unsupervised clustering","score":0.8799999952316284},{"id":"https://openalex.org/keywords/gaussian-mixture-model","display_name":"Gaussian mixture model","score":0.8840000033378601},{"id":"https://openalex.org/keywords/crop-genomics","display_name":"crop genomics","score":0.8119999766349792},{"id":"https://openalex.org/keywords/brassica-napus","display_name":"Brassica napus","score":0.8149999976158142},{"id":"https://openalex.org/keywords/brassica-oleracea","display_name":"Brassica oleracea","score":0.9900000095367432},{"id":"https://openalex.org/keywords/wheat","display_name":"wheat","score":0.9340000152587891},{"id":"https://openalex.org/keywords/snp-discovery","display_name":"SNP discovery","score":0.7429999709129333},{"id":"https://openalex.org/keywords/gatk-best-practices","display_name":"GATK Best Practices","score":0.8199999928474426},{"id":"https://openalex.org/keywords/marker-discovery","display_name":"marker discovery","score":0.39899998903274536},{"id":"https://openalex.org/keywords/plant-breeding","display_name":"plant breeding","score":0.4950000047683716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5929999947547913},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5748999714851379},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.5274999737739563},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5156999826431274},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48559999465942383},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.48069998621940613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4715000092983246},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.4537000060081482},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.4277999997138977},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3952000141143799},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.3781000077724457},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.37070000171661377},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.36169999837875366},{"id":"https://openalex.org/C106934330","wikidata":"https://www.wikidata.org/wiki/Q1971873","display_name":"Trait","level":2,"score":0.34850001335144043},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.33959999680519104},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33869999647140503},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.33309999108314514},{"id":"https://openalex.org/C81941488","wikidata":"https://www.wikidata.org/wiki/Q853421","display_name":"Quantitative trait locus","level":3,"score":0.3328000009059906},{"id":"https://openalex.org/C2779346075","wikidata":"https://www.wikidata.org/wiki/Q7268763","display_name":"Quality Score","level":3,"score":0.29820001125335693},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C2992444039","wikidata":"https://www.wikidata.org/wiki/Q17145598","display_name":"Genomic selection","level":5,"score":0.26829999685287476},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2619999945163727}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.10.07.757277","doi":"https://doi.org/10.64898/2026.10.07.757277","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.07.757277","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/08/2026.10.07.757277.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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.10.07.757277","doi":"https://doi.org/10.64898/2026.10.07.757277","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.07.757277","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/08/2026.10.07.757277.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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[{"display_name":"Zero hunger","id":"https://metadata.un.org/sdg/2","score":0.9208999872207642}],"study_designs":[],"awards":[{"id":"https://openalex.org/G2160201532","display_name":null,"funder_award_id":"DP210100296","funder_id":"https://openalex.org/F4320326768","funder_display_name":"Government of Western Australia"},{"id":"https://openalex.org/G3447565519","display_name":null,"funder_award_id":"DP200100762","funder_id":"https://openalex.org/F4320326768","funder_display_name":"Government of Western Australia"},{"id":"https://openalex.org/G7441113143","display_name":null,"funder_award_id":"DP200100762","funder_id":"https://openalex.org/F4320315885","funder_display_name":"Australian Government"},{"id":"https://openalex.org/G8734083284","display_name":null,"funder_award_id":"DP210100296","funder_id":"https://openalex.org/F4320315885","funder_display_name":"Australian Government"}],"funders":[{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"},{"id":"https://openalex.org/F4320326768","display_name":"Government of Western Australia","ror":"https://ror.org/00wqdbc63"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220999514.pdf","grobid_xml":"https://content.openalex.org/works/W7220999514.grobid-xml"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W1513618424","https://openalex.org/W1543011164","https://openalex.org/W1919257374","https://openalex.org/W1974964336","https://openalex.org/W1999257770","https://openalex.org/W2033302785","https://openalex.org/W2056243712","https://openalex.org/W2072885673","https://openalex.org/W2087441320","https://openalex.org/W2095645518","https://openalex.org/W2103441770","https://openalex.org/W2104549677","https://openalex.org/W2108234281","https://openalex.org/W2119180969","https://openalex.org/W2120774482","https://openalex.org/W2127495773","https://openalex.org/W2138060931","https://openalex.org/W2162292623","https://openalex.org/W2168133698","https://openalex.org/W2168844255","https://openalex.org/W2168900882","https://openalex.org/W2224056471","https://openalex.org/W2412589610","https://openalex.org/W2464082129","https://openalex.org/W2524721548","https://openalex.org/W2569837677","https://openalex.org/W2605897695","https://openalex.org/W2728397586","https://openalex.org/W2800434159","https://openalex.org/W2889664156","https://openalex.org/W2900491351","https://openalex.org/W2904432901","https://openalex.org/W2922397686","https://openalex.org/W2940391028","https://openalex.org/W2951912016","https://openalex.org/W2972952311","https://openalex.org/W2995057955","https://openalex.org/W3005935381","https://openalex.org/W3014638255","https://openalex.org/W3026621107","https://openalex.org/W3029661147","https://openalex.org/W3049762379","https://openalex.org/W3091217648","https://openalex.org/W3111806715","https://openalex.org/W3113144574","https://openalex.org/W3119033511","https://openalex.org/W3131055609","https://openalex.org/W4210874166","https://openalex.org/W4225113160","https://openalex.org/W4283210431","https://openalex.org/W4324144473","https://openalex.org/W4328106245","https://openalex.org/W4387996690","https://openalex.org/W4390878940","https://openalex.org/W4391226778","https://openalex.org/W4391899125","https://openalex.org/W4392285533","https://openalex.org/W4392714200","https://openalex.org/W4399731458","https://openalex.org/W4404282917","https://openalex.org/W4406074608"],"related_works":["https://openalex.org/W7098745482","https://openalex.org/W2070437870","https://openalex.org/W3049762379","https://openalex.org/W1985769575","https://openalex.org/W2896674366","https://openalex.org/W2972952311","https://openalex.org/W7125393362","https://openalex.org/W4396747041","https://openalex.org/W6920705509","https://openalex.org/W2239374790"],"abstract_inverted_index":{"Abstract":[0],"Genomic":[1],"selection":[2],"(GS)":[3],"and":[4,40,84,89,122,148,172,187,206,213,246],"trait":[5],"discovery":[6,15,92],"in":[7,70,168,182,194],"crops":[8],"require":[9],"reliable":[10],"marker":[11],"datasets,":[12],"yet":[13],"variant":[14,42,63,81,97,142,150,195,203,241],"remains":[16,68],"constrained":[17],"by":[18],"the":[19,52,107,166],"lack":[20],"of":[21,51,125,140,210],"standardised,":[22],"high-confidence":[23,95],"reference":[24,36,96],"resources.":[25,134],"Publicly":[26],"available":[27],"plant":[28],"genomic":[29,232],"resources":[30,155],"are":[31],"often":[32],"based":[33],"on":[34],"outdated":[35],"genomes,":[37],"heterogenous":[38],"pipelines,":[39],"generic":[41],"hard-filtering":[43],"thresholds":[44],"derived":[45],"from":[46],"human":[47],"studies.":[48],"Consequently,":[49],"implementation":[50],"Genome":[53],"Analysis":[54],"Toolkit":[55],"(GATK)":[56],"Best":[57,225],"Practices":[58,226],"framework,":[59],"including":[60],"machine":[61,220],"learning-based":[62],"quality":[64,82,204],"score":[65],"recalibration":[66,209],"(VQSR),":[67],"challenging":[69],"crop":[71,228,244],"genomes.":[72],"Here,":[73],"we":[74,105],"present":[75],"a":[76,103,115,235],"crop-adapted":[77],"framework":[78,167],"for":[79,119,130,156,238,243],"unsupervised":[80,127,219],"assessment":[83],"VQSR":[85,133,157],"enabling":[86],"advanced":[87],"SNP":[88,111],"insertion-deletion":[90],"(INDEL)":[91],"without":[93,158],"predefined":[94],"sets.":[98],"Using":[99],"Brassica":[100,110,170],"napus":[101],"as":[102],"model,":[104],"use":[106],"Illumina":[108],"60k":[109],"array":[112],"to":[113,227],"generate":[114],"reference-specific":[116],"truth":[117],"set":[118],"data":[120],"pre-processing":[121],"independent":[123],"evaluation":[124],"an":[126],"machine-learning":[128],"approach":[129,237],"constructing":[131],"cohort-specific":[132,208],"Gaussian":[135],"mixture":[136],"model":[137],"(GMM)-based":[138],"clustering":[139,199],"multidimensional":[141],"annotation":[143,196],"profiles":[144],"identifies":[145,201],"high-,":[146],"intermediate-,":[147],"low-quality":[149],"classes,":[151],"providing":[152,234],"flexible":[153],"training":[154,161],"requiring":[159],"labelled":[160],"data.":[162],"We":[163],"further":[164],"validate":[165],"diploid":[169],"oleracea":[171],"hexaploid":[173],"wheat":[174],"(":[175],"Triticum":[176],"aestivum":[177],")":[178],"across":[179],"cohorts":[180],"differing":[181],"population":[183],"size,":[184],"genetic":[185],"diversity,":[186],"genome":[188],"architecture.":[189],"Despite":[190],"population-and":[191],"species-specific":[192],"differences":[193],"profiles,":[197],"GMM-based":[198],"consistently":[200],"informative":[202],"classes":[205],"enables":[207],"both":[211],"SNPs":[212],"INDELs.":[214],"Our":[215],"results":[216],"demonstrate":[217],"that":[218],"learning":[221],"can":[222],"extend":[223],"GATK":[224],"species":[229],"lacking":[230],"comprehensive":[231],"resources,":[233],"scalable":[236],"generating":[239],"high-quality":[240],"datasets":[242],"genomics":[245],"downstream":[247],"breeding":[248],"applications.":[249]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-10-09T00:00:00"}
