{"id":"https://openalex.org/W7223029980","doi":"https://doi.org/10.48550/arxiv.2610.25673","title":"HyperTaxa: Multiscale Genome Representations for Generalized Microbial Taxonomic Inference","display_name":"HyperTaxa: Multiscale Genome Representations for Generalized Microbial Taxonomic Inference","publication_year":2026,"publication_date":"2026-10-19","ids":{"openalex":"https://openalex.org/W7223029980","doi":"https://doi.org/10.48550/arxiv.2610.25673"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.25673","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.25673","pdf_url":"https://arxiv.org/pdf/2610.25673","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.25673","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5159141760","display_name":"Akash Rao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rao, Akash","raw_affiliation_strings":["CSSE Department Auburn University Auburn , AL , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSSE Department Auburn University Auburn , AL , USA","institution_ids":["https://openalex.org/I82497590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159122362","display_name":"Sushim Gupta","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I115475287","display_name":"Oklahoma State University","ror":"https://ror.org/01g9vbr38","country_code":"US","type":"education","lineage":["https://openalex.org/I115475287"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gupta, Sushim","raw_affiliation_strings":["Oklahoma Animal Disease Diagnostic Laboratory Oklahoma State University Stillwater , OK , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oklahoma Animal Disease Diagnostic Laboratory Oklahoma State University Stillwater , OK , USA","institution_ids":["https://openalex.org/I115475287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159116684","display_name":"Vishalini Ramnath","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ramnath, Vishalini","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006895637","display_name":"Akhilesh Ramachandran","orcid":"https://orcid.org/0000-0001-9744-3905","observed_orcids":["https://orcid.org/0000-0001-9744-3905"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ramachandran, Akhilesh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5080710999","display_name":"Sathyanarayanan N. Aakur","orcid":"https://orcid.org/0000-0003-1062-8929","observed_orcids":["https://orcid.org/0000-0003-1062-8929"]},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aakur, Sathyanarayanan","raw_affiliation_strings":["CSSE Department Auburn University Auburn , AL , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSSE Department Auburn University Auburn , AL , USA","institution_ids":["https://openalex.org/I82497590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":0.9731000065803528,"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":0.9731000065803528,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.009800000116229057,"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/T12167","display_name":"Bacterial Identification and Susceptibility Testing","score":0.00430000014603138,"subfield":{"id":"https://openalex.org/subfields/2726","display_name":"Microbiology (medical)"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/node2vec","display_name":"node2vec","score":0.7070000171661377},{"id":"https://openalex.org/keywords/multidimensional-scaling","display_name":"multidimensional scaling","score":0.9070000052452087}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7876999974250793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5702999830245972},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5199999809265137},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.49320000410079956},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4894999861717224},{"id":"https://openalex.org/C189592816","wikidata":"https://www.wikidata.org/wiki/Q427626","display_name":"Taxonomic rank","level":3,"score":0.489300012588501},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.45249998569488525},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44429999589920044},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.398499995470047},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3783000111579895},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.37459999322891235},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.3700999915599823},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3614000082015991},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.33709999918937683},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.3319999873638153},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C48702757","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Biological classification","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2639000117778778},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.25673","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.25673","pdf_url":"https://arxiv.org/pdf/2610.25673","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.25673","doi":"https://doi.org/10.48550/arxiv.2610.25673","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.25673","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.25673","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.25673","pdf_url":"https://arxiv.org/pdf/2610.25673","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7223029980.pdf","grobid_xml":"https://content.openalex.org/works/W7223029980.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W3094502228"],"related_works":["https://openalex.org/W4391248838","https://openalex.org/W4415200193","https://openalex.org/W3008594856","https://openalex.org/W7168240442","https://openalex.org/W7214193756","https://openalex.org/W7164669383","https://openalex.org/W2886687368","https://openalex.org/W1992687107","https://openalex.org/W4205231340","https://openalex.org/W7125469228"],"abstract_inverted_index":{"Reliable":[0],"microbial":[1,51,168],"taxonomic":[2,52,125,138],"inference":[3,34,93,107],"is":[4],"challenged":[5],"by":[6],"the":[7,103,133],"rapid":[8],"growth":[9],"of":[10],"newly":[11],"sequenced":[12],"organisms":[13],"and":[14,20,64,110,113,119,129,147,164,174],"incomplete":[15,171],"reference":[16,172],"coverage.":[17],"While":[18],"alignment-":[19],"database-driven":[21],"tools":[22],"remain":[23],"essential":[24],"for":[25,32,49,167],"reference-backed":[26],"identification,":[27],"they":[28],"are":[29,150],"not":[30],"designed":[31],"learned":[33],"over":[35,94,108,127],"species":[36,95],"absent":[37],"from":[38,97],"genome-level":[39,98],"training.":[40],"We":[41],"introduce":[42],"HyperTaxa,":[43],"a":[44,69,74,160],"taxonomy-aligned":[45],"representation":[46,163],"learning":[47],"framework":[48,166],"open-set":[50,175],"inference.":[53],"HyperTaxa":[54,123,158],"encodes":[55],"whole":[56],"genomes":[57],"as":[58,159],"multiscale":[59,144],"hyperspectral":[60],"k-mer":[61],"transition":[62,145],"fields":[63],"aligns":[65],"these":[66],"representations":[67],"to":[68,153],"taxonomy-derived":[70],"semantic":[71],"space":[72,90],"using":[73],"two-stage":[75],"Node2Vec-to-MDS":[76],"procedure":[77],"that":[78,143],"combines":[79],"local":[80],"graph":[81],"structure":[82],"with":[83,132],"global":[84],"hierarchical":[85],"distance":[86],"preservation.":[87],"The":[88],"resulting":[89],"supports":[91],"zero-shot":[92,106],"excluded":[96],"training":[99],"but":[100],"represented":[101],"in":[102],"taxonomy,":[104],"generalized":[105],"seen":[109],"unseen":[111],"species,":[112],"cascaded":[114],"genus-to-species":[115],"prediction.":[116],"Across":[117],"benchmark":[118],"large-scale":[120],"disjoint-species":[121],"evaluations,":[122],"improves":[124],"prediction":[126],"pseudo-image":[128],"transformer-graph":[130],"baselines,":[131],"strongest":[134],"gains":[135],"at":[136],"higher":[137],"ranks.":[139],"Ablations":[140],"further":[141],"show":[142],"encoding":[146],"taxonomy-aware":[148,162],"alignment":[149],"key":[151],"contributors":[152],"generalization.":[154],"These":[155],"results":[156],"position":[157],"complementary":[161],"candidate-generation":[165],"identification":[169],"under":[170],"coverage":[173],"uncertainty.":[176]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-21T00:00:00"}