{"id":"https://openalex.org/W7213430701","doi":"https://doi.org/10.48550/arxiv.2609.13341","title":"GrassTop: Grassmannian k-mer Topology for Viral Classification and Phylogenetic Analysis","display_name":"GrassTop: Grassmannian k-mer Topology for Viral Classification and Phylogenetic Analysis","publication_year":2026,"publication_date":"2026-09-11","ids":{"openalex":"https://openalex.org/W7213430701","doi":"https://doi.org/10.48550/arxiv.2609.13341","pmid":"https://pubmed.ncbi.nlm.nih.gov/42780273","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/13596630"},"language":"en","primary_location":{"id":"pmid:42780273","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42780273","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ArXiv","raw_type":"Journal Article"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.13341","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5145185519","display_name":"Xiang Xiang Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang, Xiang Xiang","raw_affiliation_strings":["Department of Mathematics , University of Georgia , Athens , GA 30602 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics , University of Georgia , Athens , GA 30602 , USA","institution_ids":["https://openalex.org/I165733156"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120604046","display_name":"Guo-Wei Wei","orcid":"https://orcid.org/0000-0001-8132-5998","observed_orcids":["https://orcid.org/0000-0001-8132-5998"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Guo-Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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/T12536","display_name":"Topological and Geometric Data Analysis","score":0.5590999722480774,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12536","display_name":"Topological and Geometric Data Analysis","score":0.5590999722480774,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12946","display_name":"Fractal and DNA sequence analysis","score":0.3594000041484833,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.06159999966621399,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/grassmannians","display_name":"Grassmannians","score":0.9409999847412109},{"id":"https://openalex.org/keywords/algebraic-topology","display_name":"algebraic topology","score":0.890999972820282},{"id":"https://openalex.org/keywords/virus-taxonomy","display_name":"virus taxonomy","score":0.8809999823570251},{"id":"https://openalex.org/keywords/viral-phylogeny","display_name":"viral phylogeny","score":0.75},{"id":"https://openalex.org/keywords/spectral-descriptors","display_name":"spectral descriptors","score":0.8980000019073486},{"id":"https://openalex.org/keywords/low-rank-subspace","display_name":"low-rank subspace","score":0.7850000262260437},{"id":"https://openalex.org/keywords/chordal-distance","display_name":"chordal distance","score":0.9819999933242798},{"id":"https://openalex.org/keywords/upgma-tree","display_name":"UPGMA tree","score":0.6349999904632568},{"id":"https://openalex.org/keywords/sars-cov-2","display_name":"SARS-CoV-2","score":0.9909999966621399}],"concepts":[{"id":"https://openalex.org/C193252679","wikidata":"https://www.wikidata.org/wiki/Q242125","display_name":"Phylogenetic tree","level":3,"score":0.7746999859809875},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5777999758720398},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.5364999771118164},{"id":"https://openalex.org/C162929932","wikidata":"https://www.wikidata.org/wiki/Q129638","display_name":"Grassmannian","level":2,"score":0.5135999917984009},{"id":"https://openalex.org/C194898557","wikidata":"https://www.wikidata.org/wiki/Q1779497","display_name":"UPGMA","level":4,"score":0.4810999929904938},{"id":"https://openalex.org/C2776477805","wikidata":"https://www.wikidata.org/wiki/Q4460773","display_name":"Topological data analysis","level":2,"score":0.4300000071525574},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.41999998688697815},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41929998993873596},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.39329999685287476},{"id":"https://openalex.org/C26619641","wikidata":"https://www.wikidata.org/wiki/Q3142246","display_name":"Phylogenetic network","level":4,"score":0.38999998569488525},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.38109999895095825},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.36090001463890076},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3582000136375427},{"id":"https://openalex.org/C198260499","wikidata":"https://www.wikidata.org/wiki/Q2976606","display_name":"Phylogenetic nomenclature","level":5,"score":0.35749998688697815},{"id":"https://openalex.org/C90132467","wikidata":"https://www.wikidata.org/wiki/Q171184","display_name":"Phylogenetics","level":3,"score":0.34709998965263367},{"id":"https://openalex.org/C177918212","wikidata":"https://www.wikidata.org/wiki/Q803623","display_name":"Perturbation (astronomy)","level":2,"score":0.34049999713897705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.337799996137619},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.3303000032901764},{"id":"https://openalex.org/C98722961","wikidata":"https://www.wikidata.org/wiki/Q7189436","display_name":"Phylogenetic diversity","level":4,"score":0.29649999737739563},{"id":"https://openalex.org/C41168302","wikidata":"https://www.wikidata.org/wiki/Q3772859","display_name":"Computational phylogenetics","level":5,"score":0.29269999265670776},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C9376300","wikidata":"https://www.wikidata.org/wiki/Q168817","display_name":"Algebraic number","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.2768999934196472},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C165263651","wikidata":"https://www.wikidata.org/wiki/Q2443460","display_name":"Topological conjugacy","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":4,"locations":[{"id":"pmid:42780273","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42780273","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ArXiv","raw_type":"Journal Article"},{"id":"pmh:oai:arXiv.org:2609.13341","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.13341","pdf_url":"https://arxiv.org/pdf/2609.13341","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":"pmh:oai:pubmedcentral.nih.gov:13596630","doi":null,"is_oa":true,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42780273/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ArXiv","raw_type":"Text"},{"id":"doi:10.48550/arxiv.2609.13341","doi":"https://doi.org/10.48550/arxiv.2609.13341","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.13341","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.13341","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.13341","pdf_url":"https://arxiv.org/pdf/2609.13341","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":[{"id":"https://openalex.org/G9000870742","display_name":"AI-based platform for predicting emerging vaccine-escape variants and designing mutation-proof antibodies","funder_award_id":"R01AI164266","funder_id":"https://openalex.org/F4320337355","funder_display_name":"National Institute of Allergy and Infectious Diseases"}],"funders":[{"id":"https://openalex.org/F4320310010","display_name":"University of Georgia","ror":"https://ror.org/00te3t702"},{"id":"https://openalex.org/F4320310224","display_name":"Georgia Research Alliance","ror":"https://ror.org/030689123"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337355","display_name":"National Institute of Allergy and Infectious Diseases","ror":"https://ror.org/043z4tv69"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7213430701.pdf","grobid_xml":"https://content.openalex.org/works/W7213430701.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W4405955676","https://openalex.org/W7202158896"],"related_works":["https://openalex.org/W4405955676","https://openalex.org/W4400879623","https://openalex.org/W7216516675","https://openalex.org/W4248596639","https://openalex.org/W4405620296","https://openalex.org/W7202158896","https://openalex.org/W2410343409","https://openalex.org/W7137946298","https://openalex.org/W3210464645","https://openalex.org/W2574133781"],"abstract_inverted_index":{"We":[0,69],"introduce":[1],"GrassTop,":[2],"a":[3,36,49,84,134],"genome":[4],"representation":[5,140,174],"that":[6,39],"integrates":[7],"Grassmann":[8],"manifolds":[9],"and":[10,16,26,45,83,108,178],"algebraic":[11],"topology":[12],"for":[13,152,161,175],"viral":[14,76,176],"classification":[15,77,106,177],"phylogenetic":[17,80,128,179],"analysis.":[18,180],"The":[19,130],"framework":[20,61],"begins":[21],"by":[22],"constructing":[23],"multiscale":[24],"topological":[25],"spectral":[27],"descriptors":[28],"of":[29,75,124,147],"(k)-mer":[30],"positional":[31],"patterns.":[32],"It":[33],"then":[34],"extracts":[35],"low-rank":[37],"subspace":[38,139],"summarizes":[40],"variation":[41],"across":[42,103],"the":[43,53,57,60,89,138,148,155,162],"filtration":[44],"compares":[46],"genomes":[47],"using":[48,115],"Grassmannian":[50],"distance.":[51],"Although":[52],"reported":[54,90,105],"implementation":[55],"uses":[56],"chordal":[58],"distance,":[59],"is":[62],"not":[63],"restricted":[64],"to":[65],"this":[66],"particular":[67],"choice.":[68],"evaluate":[70],"GrassTop":[71,93,169],"on":[72,126],"four":[73,79],"families":[74],"datasets,":[78,82],"clustering":[81],"sequence":[85],"perturbation":[86,131],"experiment.":[87],"Under":[88],"5-nearest-neighbor":[91],"protocol,":[92],"achieves":[94],"higher":[95],"scores":[96],"than":[97],"five":[98],"published":[99],"alignment-free":[100],"reference":[101],"methods":[102],"all":[104],"metrics":[107],"datasets.":[109,164],"Its":[110],"UPGMA":[111],"(unweighted":[112],"pair-group":[113],"method":[114],"arithmetic":[116],"averages)":[117],"trees":[118],"achieve":[119],"an":[120,171],"average":[121],"label":[122],"purity":[123],"1.0":[125],"every":[127],"dataset.":[129],"experiment":[132],"provides":[133],"more":[135],"nuanced":[136],"result:":[137],"differs":[141],"most":[142],"clearly":[143],"from":[144],"direct":[145],"comparison":[146],"unprojected":[149],"feature":[150],"matrices":[151],"SARS-CoV-2,":[153],"whereas":[154],"differences":[156],"are":[157],"smaller":[158],"or":[159],"non-monotonic":[160],"other":[163],"Overall,":[165],"these":[166],"results":[167],"support":[168],"as":[170],"effective":[172],"topological-geometric":[173]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-17T00:00:00"}