{"id":"https://openalex.org/W7170063076","doi":"https://doi.org/10.1186/s12859-026-06562-5","title":"Interpretable prediction of DNA replication origins in S. cerevisiae using DNABERT and DNABERT-2","display_name":"Interpretable prediction of DNA replication origins in S. cerevisiae using DNABERT and DNABERT-2","publication_year":2026,"publication_date":"2026-07-22","ids":{"openalex":"https://openalex.org/W7170063076","doi":"https://doi.org/10.1186/s12859-026-06562-5","pmid":"https://pubmed.ncbi.nlm.nih.gov/42487110"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-026-06562-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-026-06562-5","pdf_url":"https://link.springer.com/content/pdf/10.1186/s12859-026-06562-5.pdf","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1186/s12859-026-06562-5.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124021036","display_name":"Zohreh Piroozeh","orcid":null},"institutions":[{"id":"https://openalex.org/I171892758","display_name":"Forschungszentrum J\u00fclich","ror":"https://ror.org/02nv7yv05","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I171892758"]},{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Zohreh Piroozeh","raw_affiliation_strings":["Centre for Bioinformatics, Saarland University, Saarbr\u00fccken, Germany. z.piroozeh@fz-juelich.de","J\u00fclich Supercomputing Centre, Forschungszentrum J\u00fclich, J\u00fclich, Germany. z.piroozeh@fz-juelich.de"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Bioinformatics, Saarland University, Saarbr\u00fccken, Germany. z.piroozeh@fz-juelich.de","institution_ids":["https://openalex.org/I91712215"]},{"raw_affiliation_string":"J\u00fclich Supercomputing Centre, Forschungszentrum J\u00fclich, J\u00fclich, Germany. z.piroozeh@fz-juelich.de","institution_ids":["https://openalex.org/I171892758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067665792","display_name":"\u0130ldem Akerman","orcid":"https://orcid.org/0000-0002-9875-1421"},"institutions":[{"id":"https://openalex.org/I4210162943","display_name":"NIHR Birmingham Biomedical Research Centre","ror":"https://ror.org/05ccjmp23","country_code":"GB","type":"facility","lineage":["https://openalex.org/I34931013","https://openalex.org/I4210162943"]},{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ildem Akerman","raw_affiliation_strings":["Institute of Biomedical Research, University of Birmingham, Birmingham, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Biomedical Research, University of Birmingham, Birmingham, UK","institution_ids":["https://openalex.org/I4210162943","https://openalex.org/I79619799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101632496","display_name":"Olga V. Kalinina","orcid":"https://orcid.org/0000-0002-9445-477X"},"institutions":[{"id":"https://openalex.org/I4210124929","display_name":"Helmholtz Centre for Infection Research","ror":"https://ror.org/03d0p2685","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I4210124929"]},{"id":"https://openalex.org/I4210142777","display_name":"Helmholtz Institute for Pharmaceutical Research Saarland","ror":"https://ror.org/042dsac10","country_code":"DE","type":"government","lineage":["https://openalex.org/I1305996414","https://openalex.org/I4210124929","https://openalex.org/I4210142777"]},{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Olga V. Kalinina","raw_affiliation_strings":["Centre for Bioinformatics, Saarland University, Saarbr\u00fccken, Germany","Helmholtz Institute for Pharmaceutical Research Saarland (HIPS), Helmholtz Centre for Infection Research (HZI), Saarbr\u00fccken, Germany","Medical Faculty, Saarland University, Homburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Bioinformatics, Saarland University, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I91712215"]},{"raw_affiliation_string":"Helmholtz Institute for Pharmaceutical Research Saarland (HIPS), Helmholtz Centre for Infection Research (HZI), Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I4210124929","https://openalex.org/I4210142777"]},{"raw_affiliation_string":"Medical Faculty, Saarland University, Homburg, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143415482","display_name":"Stefan Kesselheim","orcid":null},"institutions":[{"id":"https://openalex.org/I171892758","display_name":"Forschungszentrum J\u00fclich","ror":"https://ror.org/02nv7yv05","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I171892758"]},{"id":"https://openalex.org/I180923762","display_name":"University of Cologne","ror":"https://ror.org/00rcxh774","country_code":"DE","type":"education","lineage":["https://openalex.org/I180923762"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Kesselheim","raw_affiliation_strings":["Faculty of Mathetmatics and Natural Sciences, University of Cologne, Cologne, Germany","Helmholtz AI, Munich, Germany","J\u00fclich Supercomputing Centre, Forschungszentrum J\u00fclich, J\u00fclich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Mathetmatics and Natural Sciences, University of Cologne, Cologne, Germany","institution_ids":["https://openalex.org/I180923762"]},{"raw_affiliation_string":"Helmholtz AI, Munich, Germany","institution_ids":[]},{"raw_affiliation_string":"J\u00fclich Supercomputing Centre, Forschungszentrum J\u00fclich, J\u00fclich, Germany","institution_ids":["https://openalex.org/I171892758"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023066254","display_name":"Alina Bazarova","orcid":"https://orcid.org/0000-0001-8874-1783"},"institutions":[{"id":"https://openalex.org/I171892758","display_name":"Forschungszentrum J\u00fclich","ror":"https://ror.org/02nv7yv05","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I171892758"]},{"id":"https://openalex.org/I3018134672","display_name":"Helmholtz Munich","ror":"https://ror.org/00cfam450","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I3018134672"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Alina Bazarova","raw_affiliation_strings":["Helmholtz AI, Munich, Germany. al.bazarova@fz-juelich.de","J\u00fclich Supercomputing Centre, Forschungszentrum J\u00fclich, J\u00fclich, Germany. al.bazarova@fz-juelich.de"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Helmholtz AI, Munich, Germany. al.bazarova@fz-juelich.de","institution_ids":["https://openalex.org/I3018134672"]},{"raw_affiliation_string":"J\u00fclich Supercomputing Centre, Forschungszentrum J\u00fclich, J\u00fclich, Germany. al.bazarova@fz-juelich.de","institution_ids":["https://openalex.org/I171892758"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5023066254","https://openalex.org/A5124021036"],"corresponding_institution_ids":["https://openalex.org/I171892758","https://openalex.org/I3018134672","https://openalex.org/I91712215"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.7038372,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10123","display_name":"DNA Repair Mechanisms","score":0.569599986076355,"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/T10123","display_name":"DNA Repair Mechanisms","score":0.569599986076355,"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/T10269","display_name":"Epigenetics and DNA Methylation","score":0.16290000081062317,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.04769999906420708,"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/dna-replication","display_name":"DNA replication","score":0.498199999332428},{"id":"https://openalex.org/keywords/replication","display_name":"Replication (statistics)","score":0.4691999852657318},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.4683000147342682},{"id":"https://openalex.org/keywords/sequence-motif","display_name":"Sequence motif","score":0.43709999322891235},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.43459999561309814},{"id":"https://openalex.org/keywords/dna-microarray","display_name":"DNA microarray","score":0.3880000114440918},{"id":"https://openalex.org/keywords/origin-of-replication","display_name":"Origin of replication","score":0.3727000057697296},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.35109999775886536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5734999775886536},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5652999877929688},{"id":"https://openalex.org/C73573662","wikidata":"https://www.wikidata.org/wiki/Q130996","display_name":"DNA replication","level":3,"score":0.498199999332428},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4867999851703644},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.4860999882221222},{"id":"https://openalex.org/C12590798","wikidata":"https://www.wikidata.org/wiki/Q3933199","display_name":"Replication (statistics)","level":2,"score":0.4691999852657318},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.4683000147342682},{"id":"https://openalex.org/C117745874","wikidata":"https://www.wikidata.org/wiki/Q901612","display_name":"Sequence motif","level":3,"score":0.43709999322891235},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.43459999561309814},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.3880000114440918},{"id":"https://openalex.org/C58337764","wikidata":"https://www.wikidata.org/wiki/Q976651","display_name":"Origin of replication","level":4,"score":0.3727000057697296},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.35109999775886536},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3508000075817108},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.34369999170303345},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3422999978065491},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.33090001344680786},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.328000009059906},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3278000056743622},{"id":"https://openalex.org/C2775905019","wikidata":"https://www.wikidata.org/wiki/Q192572","display_name":"In silico","level":3,"score":0.2996000051498413},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.2937999963760376},{"id":"https://openalex.org/C61053724","wikidata":"https://www.wikidata.org/wiki/Q1154615","display_name":"Sequence analysis","level":3,"score":0.2921999990940094},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.2743000090122223},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.2513999938964844}],"mesh":[{"descriptor_ui":"D004261","descriptor_name":"DNA Replication","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004261","descriptor_name":"DNA Replication","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004261","descriptor_name":"DNA Replication","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004271","descriptor_name":"DNA, Fungal","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004271","descriptor_name":"DNA, Fungal","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004271","descriptor_name":"DNA, Fungal","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012441","descriptor_name":"Saccharomyces cerevisiae","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D012441","descriptor_name":"Saccharomyces cerevisiae","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D012441","descriptor_name":"Saccharomyces cerevisiae","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D018741","descriptor_name":"Replication Origin","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D018741","descriptor_name":"Replication Origin","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D018741","descriptor_name":"Replication Origin","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12859-026-06562-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-026-06562-5","pdf_url":"https://link.springer.com/content/pdf/10.1186/s12859-026-06562-5.pdf","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:42487110","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42487110","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":"BMC bioinformatics","raw_type":"Journal Article"},{"id":"pmh:oai:doaj.org/article:18737e881e8f4159b7833265841247cd","is_oa":false,"landing_page_url":"https://doaj.org/article/18737e881e8f4159b7833265841247cd","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,"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":"BMC Bioinformatics, Vol 27, Iss 1 (2026)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13393499","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13393499/","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,"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":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s12859-026-06562-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-026-06562-5","pdf_url":"https://link.springer.com/content/pdf/10.1186/s12859-026-06562-5.pdf","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.5349037647247314}],"awards":[],"funders":[{"id":"https://openalex.org/F4320313434","display_name":"Institute for Catastrophic Loss Reduction","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7170063076.pdf","grobid_xml":"https://content.openalex.org/works/W7170063076.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1964262489","https://openalex.org/W1976791027","https://openalex.org/W1983983428","https://openalex.org/W1988580441","https://openalex.org/W2014677321","https://openalex.org/W2021823827","https://openalex.org/W2036240398","https://openalex.org/W2056298514","https://openalex.org/W2059553154","https://openalex.org/W2061449183","https://openalex.org/W2076952384","https://openalex.org/W2112429774","https://openalex.org/W2156206373","https://openalex.org/W2166459599","https://openalex.org/W2295598076","https://openalex.org/W2344859163","https://openalex.org/W2517008357","https://openalex.org/W2771200722","https://openalex.org/W2901754076","https://openalex.org/W2962784628","https://openalex.org/W2964260111","https://openalex.org/W2970965315","https://openalex.org/W3000887590","https://openalex.org/W3087179545","https://openalex.org/W3109595616","https://openalex.org/W3118460357","https://openalex.org/W3120018424","https://openalex.org/W3124020797","https://openalex.org/W3127238141","https://openalex.org/W4247594067","https://openalex.org/W4307655495","https://openalex.org/W4367627891","https://openalex.org/W4384819450","https://openalex.org/W4389010890","https://openalex.org/W4390490761","https://openalex.org/W4392230073","https://openalex.org/W4402520149","https://openalex.org/W4404349982","https://openalex.org/W4404821554"],"related_works":[],"abstract_inverted_index":{"BACKGROUND:":[0],"DNA":[1,11,41,86],"replication":[2,22,25,78,107,208,246],"is":[3,13,34,97],"a":[4,9,98],"biological":[5],"process":[6],"in":[7,80,263,271,286,312],"which":[8],"single":[10],"molecule":[12],"duplicated,":[14],"initiating":[15],"from":[16,198],"multiple":[17],"genomic":[18,103],"sites":[19],"known":[20,204],"as":[21,310],"origins.":[23,209],"Identifying":[24],"origins":[26,79],"and":[27,49,74,83,128,149,165,179,260,302],"analyzing":[28,102],"their":[29],"underlying":[30],"base":[31,87],"sequence":[32,126,205,236,304],"composition":[33,88],"crucial":[35],"for":[36,53,101,106,162,167],"understanding":[37],"the":[38,85,143,168,182,191,280,293],"mechanisms":[39],"of":[40,94,160,177,193,207],"replication.":[42],"Although":[43],"there":[44],"are":[45],"various":[46],"machine":[47],"learning":[48,51,222,252,259,324],"deep":[50],"approaches":[52,131],"origin":[54,108,247],"prediction,":[55,109],"many":[56],"rely":[57],"on":[58,142,181],"labor":[59],"intensive":[60],"feature":[61],"engineering":[62],"or":[63],"lack":[64],"interpretability.":[65],"We":[66,138,288],"fine-tune":[67],"two":[68],"genome-based":[69],"pretrained":[70],"language":[71,104],"models,":[72],"DNABERT":[73,152,272,297],"DNABERT-2,":[75],"to":[76,118,146,219,256,279],"predict":[77],"budding":[81],"yeast":[82],"unravel":[84],"behind":[89],"them.":[90],"The":[91,266],"key":[92],"contribution":[93],"this":[95],"study":[96,240],"systematic":[99],"framework":[100],"models":[105,141,244],"combining":[110],"controlled":[111],"dataset":[112],"design":[113],"with":[114,228,233],"model-specific":[115],"explainability":[116],"pipelines":[117],"examine":[119],"how":[120],"different":[121,251],"tokenization":[122,269,284,320],"strategies":[123],"influence":[124,257],"learned":[125],"features":[127],"whether":[129],"such":[130],"can":[132],"highlight":[133],"biologically":[134,234],"meaningful":[135],"signals.":[136],"RESULTS:":[137],"evaluate":[139],"both":[140,243],"designed":[144],"datasets":[145],"ensure":[147],"robustness":[148],"support":[150],"explainability.":[151],"demonstrates":[153,241],"consistent":[154],"performance,":[155],"achieving":[156],"an":[157],"average":[158],"accuracy":[159],"0.72":[161,178],"more":[163,274],"challenging":[164],"0.83":[166],"easier":[169],"dataset.":[170],"In":[171,316],"comparison,":[172],"DNABERT-2":[173],"achieved":[174],"comparable":[175],"scores":[176,231],"0.81":[180],"same":[183,294],"datasets.":[184],"Our":[185,239],"attention-based":[186],"motif":[187],"discovery":[188],"pipeline":[189],"enhances":[190],"interpretability":[192],"DNABERT,":[194],"by":[195,329],"identifying":[196],"motifs":[197],"high-attention":[199],"fragments":[200],"that":[201,242,290],"closely":[202],"match":[203],"patterns":[206,301,328],"Perturbation-based":[210],"explanation":[211],"methods,":[212],"including":[213],"Shapley":[214],"additive":[215],"explanations,":[216],"were":[217],"applied":[218],"interpret":[220],"DNABERT-2's":[221,318],"mechanism.":[223],"This":[224],"analysis":[225],"identified":[226],"tokens":[227],"high":[229],"attribution":[230],"aligned":[232],"relevant":[235,299,326],"composition.":[237],"CONCLUSION:":[238],"identify":[245],"sequences,":[248],"albeit":[249],"through":[250],"strategies.":[253],"Tokenization":[254],"appears":[255],"model":[258],"attention":[261,276,314],"behavior":[262],"these":[264],"models.":[265],"overlapping":[267],"k-mer":[268],"used":[270],"yields":[273],"interpretable":[275],"maps":[277],"compared":[278],"byte":[281],"pair":[282],"encoding":[283],"employed":[285],"DNABERT-2.":[287],"show":[289],"despite":[291],"sharing":[292],"BERT-style":[295],"architecture,":[296],"captures":[298],"short-range":[300,327],"some":[303],"dependencies":[305],"beyond":[306],"just":[307],"local":[308],"context,":[309],"reflected":[311],"its":[313,323],"maps.":[315],"contrast,":[317],"alternative":[319],"strategy":[321],"biases":[322],"toward":[325],"optimizing":[330],"token":[331],"weighting.":[332]},"counts_by_year":[],"updated_date":"2026-08-23T07:36:19.812096","created_date":"2026-07-23T00:00:00"}
