{"id":"https://openalex.org/W7225628474","doi":"https://doi.org/10.64898/2026.11.06.764801","title":"TideCluster: clustering and classification of tandem repeats for comparative and pangenomic analysis","display_name":"TideCluster: clustering and classification of tandem repeats for comparative and pangenomic analysis","publication_year":2026,"publication_date":"2026-11-09","ids":{"openalex":"https://openalex.org/W7225628474","doi":"https://doi.org/10.64898/2026.11.06.764801"},"language":"en","primary_location":{"id":"doi:10.64898/2026.11.06.764801","doi":"https://doi.org/10.64898/2026.11.06.764801","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.06.764801","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/09/2026.11.06.764801.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","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"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/2026/11/09/2026.11.06.764801.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044567919","display_name":"Petr Nov\u00e1k","orcid":"https://orcid.org/0000-0002-5068-9681","observed_orcids":["https://orcid.org/0000-0002-5068-9681"]},"institutions":[{"id":"https://openalex.org/I202391551","display_name":"Czech Academy of Sciences","ror":"https://ror.org/053avzc18","country_code":"CZ","type":"government","lineage":["https://openalex.org/I202391551"]},{"id":"https://openalex.org/I4210164740","display_name":"Czech Academy of Sciences, Biology Centre","ror":"https://ror.org/05pq4yn02","country_code":"CZ","type":"facility","lineage":["https://openalex.org/I202391551","https://openalex.org/I4210164740"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Petr Novak","raw_affiliation_strings":["Biology Centre, Czech Academy of Sciences, Ceske Budejovice, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biology Centre, Czech Academy of Sciences, Ceske Budejovice, Czech Republic","institution_ids":["https://openalex.org/I202391551","https://openalex.org/I4210164740"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074879289","display_name":"Jir\u0306\u00ed Macas","orcid":"https://orcid.org/0000-0003-0829-1570","observed_orcids":["https://orcid.org/0000-0003-0829-1570"]},"institutions":[{"id":"https://openalex.org/I202391551","display_name":"Czech Academy of Sciences","ror":"https://ror.org/053avzc18","country_code":"CZ","type":"government","lineage":["https://openalex.org/I202391551"]},{"id":"https://openalex.org/I4210164740","display_name":"Czech Academy of Sciences, Biology Centre","ror":"https://ror.org/05pq4yn02","country_code":"CZ","type":"facility","lineage":["https://openalex.org/I202391551","https://openalex.org/I4210164740"]}],"countries":["CZ"],"is_corresponding":true,"raw_author_name":"Jiri Macas","raw_affiliation_strings":["Biology Centre, Czech Academy of Sciences, Ceske Budejovice, Czech Republic"],"raw_orcid":"https://orcid.org/0000-0003-0829-1570","affiliations":[{"raw_affiliation_string":"Biology Centre, Czech Academy of Sciences, Ceske Budejovice, Czech Republic","institution_ids":["https://openalex.org/I202391551","https://openalex.org/I4210164740"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5074879289"],"corresponding_institution_ids":["https://openalex.org/I202391551","https://openalex.org/I4210164740"],"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/T10434","display_name":"Chromosomal and Genetic Variations","score":0.9926999807357788,"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"}},"topics":[{"id":"https://openalex.org/T10434","display_name":"Chromosomal and Genetic Variations","score":0.9926999807357788,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.005200000014156103,"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/T13664","display_name":"Genome Rearrangement Algorithms","score":0.0007999999797903001,"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/tandem-repeats","display_name":"tandem repeats","score":0.9039999842643738},{"id":"https://openalex.org/keywords/satellite-dna","display_name":"satellite DNA","score":0.9950000047683716},{"id":"https://openalex.org/keywords/pangenomics","display_name":"pangenomics","score":0.6299999952316284},{"id":"https://openalex.org/keywords/comparative-genomics","display_name":"comparative genomics","score":0.9599999785423279},{"id":"https://openalex.org/keywords/higher-order-repeats","display_name":"higher-order repeats","score":0.8270000219345093},{"id":"https://openalex.org/keywords/periodicity-estimation","display_name":"periodicity estimation","score":0.7409999966621399},{"id":"https://openalex.org/keywords/gff3-annotation","display_name":"GFF3 annotation","score":0.8339999914169312},{"id":"https://openalex.org/keywords/arabidopsis-thaliana","display_name":"Arabidopsis thaliana","score":0.8730000257492065},{"id":"https://openalex.org/keywords/solanum","display_name":"Solanum","score":0.8970000147819519}],"concepts":[{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.7239999771118164},{"id":"https://openalex.org/C27149982","wikidata":"https://www.wikidata.org/wiki/Q3456514","display_name":"Tandem repeat","level":4,"score":0.6434000134468079},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6373000144958496},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5781000256538391},{"id":"https://openalex.org/C61320498","wikidata":"https://www.wikidata.org/wiki/Q265193","display_name":"Microsatellite","level":4,"score":0.5539000034332275},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5493000149726868},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5299000144004822},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.4781999886035919},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.47749999165534973},{"id":"https://openalex.org/C2777814067","wikidata":"https://www.wikidata.org/wiki/Q1752317","display_name":"Tandem","level":2,"score":0.46970000863075256},{"id":"https://openalex.org/C19269812","wikidata":"https://www.wikidata.org/wiki/Q26540","display_name":"Satellite","level":2,"score":0.45210000872612},{"id":"https://openalex.org/C140367098","wikidata":"https://www.wikidata.org/wiki/Q425319","display_name":"Satellite DNA","level":4,"score":0.4481000006198883},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.40450000762939453},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.39079999923706055},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.38999998569488525},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.3547999858856201},{"id":"https://openalex.org/C2775988993","wikidata":"https://www.wikidata.org/wiki/Q158695","display_name":"Arabidopsis thaliana","level":4,"score":0.3240000009536743},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C2779491563","wikidata":"https://www.wikidata.org/wiki/Q157892","display_name":"Arabidopsis","level":4,"score":0.29760000109672546},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C24432333","wikidata":"https://www.wikidata.org/wiki/Q2068526","display_name":"Whole genome sequencing","level":4,"score":0.29100000858306885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28870001435279846},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.28790000081062317},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.28610000014305115},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.28529998660087585},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27300000190734863},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.27000001072883606},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C29511175","wikidata":"https://www.wikidata.org/wiki/Q5280381","display_name":"Direct repeat","level":4,"score":0.2646999955177307},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C54868293","wikidata":"https://www.wikidata.org/wiki/Q7394826","display_name":"STR analysis","level":5,"score":0.26190000772476196},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C193252679","wikidata":"https://www.wikidata.org/wiki/Q242125","display_name":"Phylogenetic tree","level":3,"score":0.2574999928474426},{"id":"https://openalex.org/C197077220","wikidata":"https://www.wikidata.org/wiki/Q720988","display_name":"Human genome","level":4,"score":0.2556999921798706},{"id":"https://openalex.org/C185581394","wikidata":"https://www.wikidata.org/wiki/Q145911","display_name":"Base pair","level":3,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.11.06.764801","doi":"https://doi.org/10.64898/2026.11.06.764801","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.06.764801","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/09/2026.11.06.764801.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","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.11.06.764801","doi":"https://doi.org/10.64898/2026.11.06.764801","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.06.764801","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/09/2026.11.06.764801.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","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321005","display_name":"Ministerstvo \u0160kolstv\u00ed, Ml\u00e1de\u017ee a T\u011blov\u00fdchovy","ror":"https://ror.org/037n8p820"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225628474.pdf","grobid_xml":"https://content.openalex.org/works/W7225628474.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1091117119","https://openalex.org/W1525861996","https://openalex.org/W1968411550","https://openalex.org/W1972062413","https://openalex.org/W1973862547","https://openalex.org/W2012947856","https://openalex.org/W2025218936","https://openalex.org/W2064512698","https://openalex.org/W2065257957","https://openalex.org/W2112814753","https://openalex.org/W2119942722","https://openalex.org/W2120636855","https://openalex.org/W2128953978","https://openalex.org/W2129329558","https://openalex.org/W2142678478","https://openalex.org/W2605445948","https://openalex.org/W2897246893","https://openalex.org/W2897249806","https://openalex.org/W2950954328","https://openalex.org/W2955242233","https://openalex.org/W3213182660","https://openalex.org/W4220937793","https://openalex.org/W4220999759","https://openalex.org/W4280497339","https://openalex.org/W4361207515","https://openalex.org/W4376121976","https://openalex.org/W4403242163","https://openalex.org/W4406198867","https://openalex.org/W4407842186","https://openalex.org/W7211950237"],"related_works":["https://openalex.org/W2605445948","https://openalex.org/W7172399943","https://openalex.org/W4376121976","https://openalex.org/W7140091251","https://openalex.org/W2995596821","https://openalex.org/W2139799953","https://openalex.org/W1991082245","https://openalex.org/W3139565525","https://openalex.org/W7128347679","https://openalex.org/W2079165897"],"abstract_inverted_index":{"Satellite":[0],"DNA,":[1],"composed":[2],"of":[3,6,15,26,108,132,138],"tandem":[4,59],"arrays":[5,80],"relatively":[7],"short":[8],"repeated":[9],"units,":[10],"is":[11],"a":[12,53,70,136,158],"ubiquitous":[13],"component":[14],"plant":[16],"and":[17,45,95,135,152],"animal":[18],"genomes.":[19],"Despite":[20],"its":[21,126],"biological":[22],"importance,":[23],"systematic":[24],"investigation":[25],"satellite":[27,109,144],"DNA":[28],"remains":[29],"challenging,":[30],"in":[31,150],"part":[32],"because":[33],"integrated":[34],"bioinformatic":[35],"tools":[36],"for":[37,120],"structured":[38],"comparative":[39],"analyses":[40],"across":[41],"individual":[42],"arrays,":[43,78],"chromosomes,":[44],"genomes":[46],"are":[47],"lacking.":[48],"Here,":[49],"we":[50],"present":[51],"TideCluster,":[52],"reference-independent":[54],"pipeline":[55],"that":[56,116,147],"converts":[57],"fragmented":[58],"repeat":[60,65,110,145],"detections":[61],"into":[62,77],"genome-wide,":[63],"interpretable":[64],"family":[66],"catalogs.":[67],"Starting":[68],"from":[69,157],"genome":[71,131],"assembly,":[72],"TideCluster":[73,112],"consolidates":[74],"detected":[75],"regions":[76],"clusters":[79],"by":[81],"sequence":[82],"similarity,":[83],"reconstructs":[84],"representative":[85],"monomer":[86,154],"consensus":[87],"sequences,":[88],"estimates":[89],"locus-specific":[90],"periodicity,":[91],"identifies":[92],"higher-order":[93],"repeats,":[94],"generates":[96],"GFF3":[97],"annotations.":[98],"In":[99],"addition":[100],"to":[101,162],"predefined":[102],"visualizations,":[103],"including":[104],"the":[105,129],"chromosomal":[106],"distributions":[107],"families,":[111],"produces":[113],"information-rich":[114],"outputs":[115],"can":[117],"be":[118],"adapted":[119],"user-specific":[121],"downstream":[122],"analyses.":[123],"We":[124],"demonstrate":[125],"capabilities":[127],"using":[128],"well-characterized":[130],"Arabidopsis":[133],"thaliana":[134],"set":[137],"Solanum":[139],"species":[140],"with":[141],"highly":[142],"diverse":[143],"complements":[146],"vary":[148],"markedly":[149],"abundance":[151],"have":[153],"lengths":[155],"ranging":[156],"few":[159],"base":[160],"pairs":[161],"more":[163],"than":[164],"20":[165],"kb.":[166]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-10T00:00:00"}
