{"id":"https://openalex.org/W4411651241","doi":"https://doi.org/10.1186/s13015-026-00304-1","title":"A k-mer-based estimator of the substitution rate between repetitive sequences","display_name":"A k-mer-based estimator of the substitution rate between repetitive sequences","publication_year":2026,"publication_date":"2026-07-03","ids":{"openalex":"https://openalex.org/W4411651241","doi":"https://doi.org/10.1186/s13015-026-00304-1","pmid":"https://pubmed.ncbi.nlm.nih.gov/40667124","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/12262547"},"language":"en","primary_location":{"id":"doi:10.1186/s13015-026-00304-1","doi":"https://doi.org/10.1186/s13015-026-00304-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13015-026-00304-1","pdf_url":null,"source":{"id":"https://openalex.org/S205663195","display_name":"Algorithms for Molecular Biology","issn_l":"1748-7188","issn":["1748-7188"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-c","jufo-1","norway-1","oarl","poland-70","russia-white-list-2"],"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms for Molecular Biology","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","datacite","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1186/s13015-026-00304-1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113093216","display_name":"Haonan Wu","orcid":"https://orcid.org/0000-0002-4158-8678","observed_orcids":["https://orcid.org/0000-0002-4158-8678"]},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haonan Wu","raw_affiliation_strings":["Department of Computer Science and Engineering, The Pennsylvania State University"],"raw_orcid":"https://orcid.org/0000-0002-4158-8678","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008395399","display_name":"Antonio Blanca","orcid":"https://orcid.org/0000-0002-4675-2596","observed_orcids":["https://orcid.org/0000-0002-4675-2596"]},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Antonio Blanca","raw_affiliation_strings":["Department of Computer Science and Engineering, The Pennsylvania State University"],"raw_orcid":"https://orcid.org/0000-0002-4675-2596","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066909672","display_name":"Paul Medvedev","orcid":"https://orcid.org/0000-0003-3143-594X","observed_orcids":["https://orcid.org/0000-0003-3143-594X"]},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Paul Medvedev","raw_affiliation_strings":["Department of Biochemistry and Molecular Biology, The Pennsylvania State University","Department of Computer Science and Engineering, The Pennsylvania State University","Huck Institutes of the Life Sciences, The Pennsylvania State University"],"raw_orcid":"https://orcid.org/0000-0003-3143-594X","affiliations":[{"raw_affiliation_string":"Department of Biochemistry and Molecular Biology, The Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Huck Institutes of the Life Sciences, The Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5066909672"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":{"value":2490,"currency":"USD","value_usd":2490},"apc_paid":{"value":2490,"currency":"USD","value_usd":2490},"fwci":5.1516,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.93955684,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"21","issue":"1","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":0.923799991607666,"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":0.923799991607666,"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/T11269","display_name":"Algorithms and Data Compression","score":0.050999999046325684,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.013500000350177288,"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/repetitive-dna","display_name":"repetitive DNA","score":0.8539999723434448},{"id":"https://openalex.org/keywords/mash","display_name":"MASH","score":0.7889999747276306},{"id":"https://openalex.org/keywords/mutation-rate-estimation","display_name":"mutation rate estimation","score":0.6919999718666077},{"id":"https://openalex.org/keywords/centromere","display_name":"centromere","score":0.6610000133514404},{"id":"https://openalex.org/keywords/genomic-sequence-comparison","display_name":"genomic sequence comparison","score":0.44600000977516174},{"id":"https://openalex.org/keywords/k-mer-size","display_name":"k-mer size","score":0.48500001430511475}],"concepts":[{"id":"https://openalex.org/C2778220771","wikidata":"https://www.wikidata.org/wiki/Q1522579","display_name":"Substitution (logic)","level":2,"score":0.799015998840332},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6361681222915649},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.41170066595077515},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3585467040538788},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3277958631515503},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32636308670043945},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.32065489888191223},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06558957695960999}],"mesh":[],"locations_count":11,"locations":[{"id":"doi:10.1186/s13015-026-00304-1","doi":"https://doi.org/10.1186/s13015-026-00304-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13015-026-00304-1","pdf_url":null,"source":{"id":"https://openalex.org/S205663195","display_name":"Algorithms for Molecular Biology","issn_l":"1748-7188","issn":["1748-7188"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-c","jufo-1","norway-1","oarl","poland-70","russia-white-list-2"],"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms for Molecular Biology","raw_type":"journal-article"},{"id":"doi:10.1101/2025.06.19.660607","doi":"https://doi.org/10.1101/2025.06.19.660607","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2025.06.19.660607","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2025/06/25/2025.06.19.660607.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-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},{"id":"pmid:40667124","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40667124","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":"bioRxiv : the preprint server for biology","raw_type":"Journal Article"},{"id":"pmid:42006138","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42006138","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":"Algorithms in bioinformatics : ... International Workshop, WABI ..., proceedings. WABI (Workshop)","raw_type":"Journal Article"},{"id":"pmid:42399959","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42399959","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":"Algorithms for molecular biology : AMB","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13087736","doi":null,"is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13087736/","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms Bioinform","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:13602792","doi":null,"is_oa":true,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42399959/","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms Mol Biol","raw_type":"Text"},{"id":"pmh:oai:drops-oai.dagstuhl.de:23946","doi":null,"is_oa":true,"landing_page_url":"https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.WABI.2025.20","pdf_url":"https://drops.dagstuhl.de/storage/00lipics/lipics-vol344-wabi2025/LIPIcs.WABI.2025.20/LIPIcs.WABI.2025.20.pdf","source":{"id":"https://openalex.org/S4377196569","display_name":"DROPS (Schloss Dagstuhl \u2013 Leibniz Center for Informatics)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2799853480","host_organization_name":"Schloss Dagstuhl \u2013 Leibniz Center for Informatics","host_organization_lineage":["https://openalex.org/I2799853480"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"InProceedings"},{"id":"pmh:oai:pubmedcentral.nih.gov:12262547","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12262547","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":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:53311ccc204c4f5fb1c773837da3af10","doi":null,"is_oa":false,"landing_page_url":"https://doaj.org/article/53311ccc204c4f5fb1c773837da3af10","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms for Molecular Biology, Vol 21, Iss 1 (2026)","raw_type":"article"},{"id":"doi:10.4230/lipics.wabi.2025.20","doi":"https://doi.org/10.4230/lipics.wabi.2025.20","is_oa":true,"landing_page_url":"https://doi.org/10.4230/lipics.wabi.2025.20","pdf_url":null,"source":{"id":"https://openalex.org/S4393917817","display_name":"Leibniz international proceedings in informatics","issn_l":"1868-8969","issn":["1868-8969"],"is_oa":true,"is_in_doaj":true,"is_core":false,"listed_in":["doaj","jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"}],"best_oa_location":{"id":"doi:10.1186/s13015-026-00304-1","doi":"https://doi.org/10.1186/s13015-026-00304-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13015-026-00304-1","pdf_url":null,"source":{"id":"https://openalex.org/S205663195","display_name":"Algorithms for Molecular Biology","issn_l":"1748-7188","issn":["1748-7188"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-c","jufo-1","norway-1","oarl","poland-70","russia-white-list-2"],"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms for Molecular Biology","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G174627229","display_name":"Frameworks: Re-Engineering Galaxy for Performance, Scalability and Energy Efficiency","funder_award_id":"1931531","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6636646442","display_name":"A k-mer-based search engine for sequencing databases","funder_award_id":"2138585","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G9000871591","display_name":"Leveraging k-mer sketching statistics to enhance metagenomic methods and alignment algorithms","funder_award_id":"R01GM146462","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411651241.pdf","grobid_xml":"https://content.openalex.org/works/W4411651241.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1533146036","https://openalex.org/W2006075770","https://openalex.org/W2094890728","https://openalex.org/W2112814753","https://openalex.org/W2120902911","https://openalex.org/W2141865968","https://openalex.org/W2149792928","https://openalex.org/W2777639606","https://openalex.org/W2789843538","https://openalex.org/W2815423913","https://openalex.org/W2883729812","https://openalex.org/W2937044610","https://openalex.org/W2949086752","https://openalex.org/W2950150251","https://openalex.org/W2950993016","https://openalex.org/W2959670948","https://openalex.org/W2964150838","https://openalex.org/W2969627863","https://openalex.org/W2972805712","https://openalex.org/W2983384703","https://openalex.org/W4214573178","https://openalex.org/W4220999759","https://openalex.org/W4221104280","https://openalex.org/W4226289813","https://openalex.org/W4361298788","https://openalex.org/W4381489623","https://openalex.org/W4386022705","https://openalex.org/W4386113054","https://openalex.org/W4386923678","https://openalex.org/W4392201117","https://openalex.org/W4396638317"],"related_works":["https://openalex.org/W7167622081","https://openalex.org/W4410468487","https://openalex.org/W7162197711","https://openalex.org/W2523684193","https://openalex.org/W6891681262","https://openalex.org/W7166184428","https://openalex.org/W1779017450","https://openalex.org/W7123512181","https://openalex.org/W2994892085","https://openalex.org/W2215130704"],"abstract_inverted_index":{"BACKGROUND:":[0],"K-mer-based":[1],"analysis":[2],"of":[3,11,21,58,111,175],"genomic":[4,152],"data":[5],"is":[6,49,85,202],"ubiquitous,":[7],"but":[8],"the":[9,19,26,36,56,83,97,109,123,132,156,176],"presence":[10,110],"repetitive":[12,52,151],"k-mers":[13],"continues":[14],"to":[15,71,106,190],"pose":[16],"problems":[17],"for":[18,100,131,150],"accuracy":[20],"many":[22],"methods.":[23],"For":[24],"example,":[25],"Mash":[27,105],"tool":[28],"(Ondov":[29],"et":[30,66],"al":[31],"2016)":[32],"can":[33,187],"accurately":[34],"estimate":[35],"substitution":[37,177],"rate":[38,178],"between":[39],"two":[40],"low-repetitive":[41],"sequences":[42,53,113],"from":[43],"their":[44],"k-mer":[45,76,94,180,195],"sketches;":[46],"however,":[47],"it":[48,147],"inaccurate":[50],"on":[51,79,139],"such":[54,154],"as":[55,155],"centromere":[57],"a":[59,128],"human":[60],"chromosome.":[61],"Follow-up":[62],"work":[63,107],"by":[64],"Blanca":[65],"al.":[67],"(2021)":[68],"has":[69],"attempted":[70],"model":[72],"how":[73,185],"mutations":[74,89],"affect":[75],"sets":[77,196],"based":[78],"strong":[80],"assumptions":[81],"that":[82,88,146],"sequence":[84],"non-repetitive":[86,124],"and":[87,126,172,179],"do":[90],"not":[91],"create":[92],"spurious":[93],"matches.":[95],"However,":[96],"theoretical":[98,137],"foundations":[99],"extending":[101],"an":[102],"estimator":[103,130],"like":[104],"in":[108,162],"repeat":[112],"have":[114],"been":[115],"lacking.":[116],"RESULTS:":[117],"In":[118],"this":[119],"work,":[120],"we":[121,183],"relax":[122],"assumption":[125],"propose":[127],"novel":[129],"mutation":[133],"rate.":[134],"We":[135,164],"derive":[136],"bounds":[138],"our":[140,166],"estimator's":[141,167],"bias.":[142],"Our":[143,200],"experiments":[144],"show":[145,184],"remains":[148],"accurate":[149],"sequences,":[153],"alpha":[157],"satellite":[158],"higher":[159],"order":[160],"repeats":[161],"centromeres.":[163],"demonstrate":[165],"robustness":[168],"across":[169],"diverse":[170],"datasets":[171],"various":[173],"ranges":[174],"size.":[181],"Finally,":[182],"sketching":[186],"be":[188],"used":[189],"avoid":[191],"dealing":[192],"with":[193],"large":[194],"while":[197],"retaining":[198],"accuracy.":[199],"software":[201],"available":[203],"at":[204],"https://github.com/medvedevgroup/Repeat-Aware_Substitution_Rate_Estimator":[205],".":[206]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2025-10-10T00:00:00"}