{"id":"https://openalex.org/W4413308914","doi":"https://doi.org/10.1093/bioinformatics/btaf456","title":"The impact of tokenizer selection in genomic language models","display_name":"The impact of tokenizer selection in genomic language models","publication_year":2025,"publication_date":"2025-08-18","ids":{"openalex":"https://openalex.org/W4413308914","doi":"https://doi.org/10.1093/bioinformatics/btaf456","pmid":"https://pubmed.ncbi.nlm.nih.gov/40824067"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btaf456","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf456","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btaf456/64076938/btaf456.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btaf456/64076938/btaf456.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043977099","display_name":"LeAnn M. Lindsey","orcid":"https://orcid.org/0000-0002-0515-0118"},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]},{"id":"https://openalex.org/I2800548410","display_name":"United States National Library of Medicine","ror":"https://ror.org/0060t0j89","country_code":"US","type":"archive","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"LeAnn M Lindsey","raw_affiliation_strings":["Kahlert School of Computing, University of Utah , Salt Lake City, Utah 84112,","National Library of Medicine, National Institutes of Health , Bethesda, Maryland 20892,","Kahlert School of Computing, University of Utah, UT, USA","National Library of Medicine, National Institutes of Health, MD, USA"],"affiliations":[{"raw_affiliation_string":"Kahlert School of Computing, University of Utah , Salt Lake City, Utah 84112,","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"National Library of Medicine, National Institutes of Health , Bethesda, Maryland 20892,","institution_ids":["https://openalex.org/I2800548410"]},{"raw_affiliation_string":"Kahlert School of Computing, University of Utah, UT, USA","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"National Library of Medicine, National Institutes of Health, MD, USA","institution_ids":["https://openalex.org/I2800548410","https://openalex.org/I1299303238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108009351","display_name":"Nicole L. Pershing","orcid":"https://orcid.org/0000-0002-5399-5668"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicole L Pershing","raw_affiliation_strings":["Department of Pediatrics, School of Medicine, University of Utah , Salt Lake City, Utah 84112,","Department of Pediatrics, School of Medicine, University of Utah, UT, USA"],"affiliations":[{"raw_affiliation_string":"Department of Pediatrics, School of Medicine, University of Utah , Salt Lake City, Utah 84112,","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"Department of Pediatrics, School of Medicine, University of Utah, UT, USA","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113988171","display_name":"A K M Rubaiyat Reza Habib","orcid":null},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anisa Habib","raw_affiliation_strings":["Kahlert School of Computing, University of Utah , Salt Lake City, Utah 84112,","Kahlert School of Computing, University of Utah, UT, USA"],"affiliations":[{"raw_affiliation_string":"Kahlert School of Computing, University of Utah , Salt Lake City, Utah 84112,","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"Kahlert School of Computing, University of Utah, UT, USA","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055557829","display_name":"Keith Dufault\u2010Thompson","orcid":"https://orcid.org/0000-0002-0991-2255"},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I2800548410","display_name":"United States National Library of Medicine","ror":"https://ror.org/0060t0j89","country_code":"US","type":"archive","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Keith Dufault-Thompson","raw_affiliation_strings":["National Library of Medicine, National Institutes of Health , Bethesda, Maryland 20892,","National Library of Medicine, National Institutes of Health, MD, USA"],"affiliations":[{"raw_affiliation_string":"National Library of Medicine, National Institutes of Health , Bethesda, Maryland 20892,","institution_ids":["https://openalex.org/I2800548410"]},{"raw_affiliation_string":"National Library of Medicine, National Institutes of Health, MD, USA","institution_ids":["https://openalex.org/I2800548410","https://openalex.org/I1299303238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088866676","display_name":"W. Zac Stephens","orcid":"https://orcid.org/0000-0002-8072-9023"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"W Zac Stephens","raw_affiliation_strings":["Department of Pathology, School of Medicine, University of Utah , Salt Lake City, Utah 84112,","Department of Pathology, School of Medicine, University of Utah, UT, USA"],"affiliations":[{"raw_affiliation_string":"Department of Pathology, School of Medicine, University of Utah , Salt Lake City, Utah 84112,","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"Department of Pathology, School of Medicine, University of Utah, UT, USA","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073087668","display_name":"Anne J. Blaschke","orcid":"https://orcid.org/0000-0002-2968-3007"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anne J Blaschke","raw_affiliation_strings":["Department of Pediatrics, School of Medicine, University of Utah , Salt Lake City, Utah 84112,","Department of Pediatrics, School of Medicine, University of Utah, UT, USA"],"affiliations":[{"raw_affiliation_string":"Department of Pediatrics, School of Medicine, University of Utah , Salt Lake City, Utah 84112,","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"Department of Pediatrics, School of Medicine, University of Utah, UT, USA","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057955021","display_name":"Xiaofang Jiang","orcid":"https://orcid.org/0000-0002-0955-8284"},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I2800548410","display_name":"United States National Library of Medicine","ror":"https://ror.org/0060t0j89","country_code":"US","type":"archive","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaofang Jiang","raw_affiliation_strings":["National Library of Medicine, National Institutes of Health , Bethesda, Maryland 20892,","National Library of Medicine, National Institutes of Health, MD, USA"],"affiliations":[{"raw_affiliation_string":"National Library of Medicine, National Institutes of Health , Bethesda, Maryland 20892,","institution_ids":["https://openalex.org/I2800548410"]},{"raw_affiliation_string":"National Library of Medicine, National Institutes of Health, MD, USA","institution_ids":["https://openalex.org/I2800548410","https://openalex.org/I1299303238"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051806400","display_name":"Hari Sundar","orcid":"https://orcid.org/0000-0001-9001-5107"},"institutions":[{"id":"https://openalex.org/I121934306","display_name":"Tufts University","ror":"https://ror.org/05wvpxv85","country_code":"US","type":"education","lineage":["https://openalex.org/I121934306"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hari Sundar","raw_affiliation_strings":["Department of Computer Science, Tufts University , Medford, MA 02115,","Department of Computer Science, Tufts University, MA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tufts University , Medford, MA 02115,","institution_ids":["https://openalex.org/I121934306"]},{"raw_affiliation_string":"Department of Computer Science, Tufts University, MA, USA","institution_ids":["https://openalex.org/I121934306"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5043977099"],"corresponding_institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I223532165","https://openalex.org/I2800548410"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":7.0294,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.96736169,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"41","issue":"9","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9110999703407288,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9110999703407288,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.8182170391082764},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6169497966766357},{"id":"https://openalex.org/keywords/genomic-selection","display_name":"Genomic selection","score":0.49357664585113525},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.44981318712234497},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.3403530716896057},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.30484625697135925},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2068721354007721},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.1335226595401764},{"id":"https://openalex.org/keywords/genotype","display_name":"Genotype","score":0.06304553151130676}],"concepts":[{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.8182170391082764},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6169497966766357},{"id":"https://openalex.org/C2992444039","wikidata":"https://www.wikidata.org/wiki/Q17145598","display_name":"Genomic selection","level":5,"score":0.49357664585113525},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.44981318712234497},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.3403530716896057},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.30484625697135925},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2068721354007721},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.1335226595401764},{"id":"https://openalex.org/C135763542","wikidata":"https://www.wikidata.org/wiki/Q106016","display_name":"Genotype","level":3,"score":0.06304553151130676},{"id":"https://openalex.org/C153209595","wikidata":"https://www.wikidata.org/wiki/Q501128","display_name":"Single-nucleotide polymorphism","level":4,"score":0.0}],"mesh":[{"descriptor_ui":"D000086382","descriptor_name":"COVID-19","qualifier_ui":"Q000821","qualifier_name":"virology","is_major_topic":false},{"descriptor_ui":"D000086382","descriptor_name":"COVID-19","qualifier_ui":"Q000821","qualifier_name":"virology","is_major_topic":false},{"descriptor_ui":"D000086382","descriptor_name":"COVID-19","qualifier_ui":"Q000821","qualifier_name":"virology","is_major_topic":false},{"descriptor_ui":"D000086382","descriptor_name":"COVID-19","qualifier_ui":"Q000821","qualifier_name":"virology","is_major_topic":false},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btaf456","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf456","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btaf456/64076938/btaf456.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:40824067","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40824067","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,"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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:europepmc.org:11262692","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12453675","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:12453675","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12453675/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btaf456","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf456","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btaf456/64076938/btaf456.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1170470956","display_name":null,"funder_award_id":"1K12TR004413","funder_id":"https://openalex.org/F4320337472","funder_display_name":"National Center for Advancing Translational Sciences"},{"id":"https://openalex.org/G1353381076","display_name":null,"funder_award_id":"2138296","funder_id":"https://openalex.org/F4320312143","funder_display_name":"National Centre for Supercomputing Applications"},{"id":"https://openalex.org/G1912064254","display_name":null,"funder_award_id":"2137603","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2507572247","display_name":null,"funder_award_id":"2138286","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G292365264","display_name":null,"funder_award_id":"UM1TR004409","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G34258105","display_name":null,"funder_award_id":"2138307","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G360632185","display_name":null,"funder_award_id":"UM1TR004409","funder_id":"https://openalex.org/F4320310050","funder_display_name":"University of Utah"},{"id":"https://openalex.org/G4006316252","display_name":null,"funder_award_id":"2138259","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4010157413","display_name":null,"funder_award_id":"2138259","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G4275568664","display_name":null,"funder_award_id":"2138286","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G4354429237","display_name":null,"funder_award_id":"2222322","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4676224565","display_name":null,"funder_award_id":"2138296","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4801515358","display_name":null,"funder_award_id":"ACCESS","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G4968279142","display_name":null,"funder_award_id":"2138307","funder_id":"https://openalex.org/F4320312143","funder_display_name":"National Centre for Supercomputing Applications"},{"id":"https://openalex.org/G509285653","display_name":null,"funder_award_id":"2138307","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5156331529","display_name":null,"funder_award_id":"2138296","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G5173294414","display_name":null,"funder_award_id":"2138286","funder_id":"https://openalex.org/F4320312143","funder_display_name":"National Centre for Supercomputing Applications"},{"id":"https://openalex.org/G5464919783","display_name":null,"funder_award_id":"2137603","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G6262263222","display_name":null,"funder_award_id":"UM1TR004409","funder_id":"https://openalex.org/F4320337472","funder_display_name":"National Center for Advancing Translational Sciences"},{"id":"https://openalex.org/G6345853531","display_name":null,"funder_award_id":"unknown","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6664589177","display_name":null,"funder_award_id":"2138307","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G7472514984","display_name":null,"funder_award_id":"1K12TR004413","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G7526614437","display_name":null,"funder_award_id":"2137603","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G7622549653","display_name":null,"funder_award_id":"213829","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8165146668","display_name":null,"funder_award_id":"2138259","funder_id":"https://openalex.org/F4320312143","funder_display_name":"National Centre for Supercomputing Applications"},{"id":"https://openalex.org/G8300691027","display_name":null,"funder_award_id":"2138286","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8499740153","display_name":null,"funder_award_id":"2138259","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G8819975937","display_name":null,"funder_award_id":"2137603","funder_id":"https://openalex.org/F4320312143","funder_display_name":"National Centre for Supercomputing Applications"},{"id":"https://openalex.org/G8897435675","display_name":null,"funder_award_id":"2138296","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320310050","display_name":"University of Utah","ror":"https://ror.org/03r0ha626"},{"id":"https://openalex.org/F4320312143","display_name":"National Centre for Supercomputing Applications","ror":"https://ror.org/03r10zj06"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"},{"id":"https://openalex.org/F4320337377","display_name":"Office of Advanced Cyberinfrastructure","ror":"https://ror.org/04nh1dc89"},{"id":"https://openalex.org/F4320337472","display_name":"National Center for Advancing Translational Sciences","ror":"https://ror.org/04pw6fb54"},{"id":"https://openalex.org/F4320338421","display_name":"NHLBI Division of Intramural Research","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413308914.pdf","grobid_xml":"https://content.openalex.org/works/W4413308914.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1979137652","https://openalex.org/W1991259976","https://openalex.org/W2012150214","https://openalex.org/W2045362835","https://openalex.org/W2102659607","https://openalex.org/W2121879602","https://openalex.org/W2134977238","https://openalex.org/W2141402301","https://openalex.org/W2962784628","https://openalex.org/W2963979492","https://openalex.org/W2979826702","https://openalex.org/W2996771978","https://openalex.org/W3101140821","https://openalex.org/W3127238141","https://openalex.org/W3164045210","https://openalex.org/W3173954987","https://openalex.org/W4205247356","https://openalex.org/W4286238659","https://openalex.org/W4367597910","https://openalex.org/W4386699927","https://openalex.org/W4388667244","https://openalex.org/W4389523974","https://openalex.org/W4392575276","https://openalex.org/W4394769874","https://openalex.org/W4404782336","https://openalex.org/W4404783106","https://openalex.org/W6910631630"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2099180796","https://openalex.org/W4293558767","https://openalex.org/W4226103311","https://openalex.org/W2476508363","https://openalex.org/W2157628892","https://openalex.org/W2374640358","https://openalex.org/W4412313245","https://openalex.org/W2550568080","https://openalex.org/W2778305812"],"abstract_inverted_index":{"Detailed":[0],"results":[1],"of":[2],"all":[3],"benchmarking":[4],"experiments":[5],"are":[6,15,23],"available":[7,16,24],"in":[8],"https://github.com/leannmlindsey/DNAtokenization.":[9],"Training":[10],"datasets":[11],"and":[12,20,28],"pretrained":[13],"models":[14],"at":[17,25],"https://huggingface.co/datasets/leannmlindsey.":[18],"Datasets":[19],"processing":[21],"scripts":[22],"doi:":[26,29],"10.5281/zenodo.16287401":[27],"10.5281/zenodo.16287130.":[30]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
