{"id":"https://openalex.org/W4402520149","doi":"https://doi.org/10.1186/s12859-024-05869-5","title":"Distinguishing word identity and sequence context in DNA language models","display_name":"Distinguishing word identity and sequence context in DNA language models","publication_year":2024,"publication_date":"2024-09-13","ids":{"openalex":"https://openalex.org/W4402520149","doi":"https://doi.org/10.1186/s12859-024-05869-5","pmid":"https://pubmed.ncbi.nlm.nih.gov/39272021"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-024-05869-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-024-05869-5","pdf_url":"https://link.springer.com/content/pdf/10.1186/s12859-024-05869-5.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/s12859-024-05869-5.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021041939","display_name":"Melissa Sanabria","orcid":"https://orcid.org/0000-0003-4345-1074"},"institutions":[{"id":"https://openalex.org/I4210148197","display_name":"Center for Systems Biology Dresden","ror":"https://ror.org/05hrn3e05","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I149899117","https://openalex.org/I4210111875","https://openalex.org/I4210148197","https://openalex.org/I4210159854","https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Melissa Sanabria","raw_affiliation_strings":["Biomedical Genomics, Biotechnology Center, Center for Molecular and Cellular Bioengineering, Technische Universitat Dresden, Dresden, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biomedical Genomics, Biotechnology Center, Center for Molecular and Cellular Bioengineering, Technische Universitat Dresden, Dresden, Germany","institution_ids":["https://openalex.org/I4210148197"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057724103","display_name":"Jonas Hirsch","orcid":"https://orcid.org/0000-0003-2962-5963"},"institutions":[{"id":"https://openalex.org/I4210148197","display_name":"Center for Systems Biology Dresden","ror":"https://ror.org/05hrn3e05","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I149899117","https://openalex.org/I4210111875","https://openalex.org/I4210148197","https://openalex.org/I4210159854","https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jonas Hirsch","raw_affiliation_strings":["Biomedical Genomics, Biotechnology Center, Center for Molecular and Cellular Bioengineering, Technische Universitat Dresden, Dresden, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biomedical Genomics, Biotechnology Center, Center for Molecular and Cellular Bioengineering, Technische Universitat Dresden, Dresden, Germany","institution_ids":["https://openalex.org/I4210148197"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029443962","display_name":"Anna R. Poetsch","orcid":"https://orcid.org/0000-0003-3056-4360"},"institutions":[{"id":"https://openalex.org/I4210111460","display_name":"National Center for Tumor Diseases","ror":"https://ror.org/01txwsw02","country_code":"DE","type":"funder","lineage":["https://openalex.org/I4210111460"]},{"id":"https://openalex.org/I4210148197","display_name":"Center for Systems Biology Dresden","ror":"https://ror.org/05hrn3e05","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I149899117","https://openalex.org/I4210111875","https://openalex.org/I4210148197","https://openalex.org/I4210159854","https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Anna R. Poetsch","raw_affiliation_strings":["Biomedical Genomics, Biotechnology Center, Center for Molecular and Cellular Bioengineering, Technische Universitat Dresden, Dresden, Germany. arpoetsch@gmail.com","National Center for Tumor Diseases, Partner site Dresden, German Cancer Research Center, Dresden, Germany. arpoetsch@gmail.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biomedical Genomics, Biotechnology Center, Center for Molecular and Cellular Bioengineering, Technische Universitat Dresden, Dresden, Germany. arpoetsch@gmail.com","institution_ids":["https://openalex.org/I4210148197"]},{"raw_affiliation_string":"National Center for Tumor Diseases, Partner site Dresden, German Cancer Research Center, Dresden, Germany. arpoetsch@gmail.com","institution_ids":["https://openalex.org/I4210111460"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":3.0617,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.92139272,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"25","issue":"1","first_page":"301","last_page":"301"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9980000257492065,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9979000091552734,"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":0.9962999820709229,"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/security-token","display_name":"Security token","score":0.7364683151245117},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7205023169517517},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.5929048657417297},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5477374196052551},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5361663103103638},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4977612793445587},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.49149882793426514},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.44450095295906067},{"id":"https://openalex.org/keywords/sequence-learning","display_name":"Sequence learning","score":0.44212013483047485},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2072020173072815},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.10959124565124512}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7364683151245117},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7205023169517517},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.5929048657417297},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5477374196052551},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5361663103103638},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4977612793445587},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.49149882793426514},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.44450095295906067},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.44212013483047485},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2072020173072815},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.10959124565124512},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"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":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12859-024-05869-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-024-05869-5","pdf_url":"https://link.springer.com/content/pdf/10.1186/s12859-024-05869-5.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:39272021","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39272021","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":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11395559","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11395559","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11395559/pdf/12859_2024_Article_5869.pdf","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"},{"id":"pmh:oai:doaj.org/article:6e63f94ecd8e4da89df64f9d46d19663","is_oa":false,"landing_page_url":"https://doaj.org/article/6e63f94ecd8e4da89df64f9d46d19663","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 25, Iss 1, Pp 1-12 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s12859-024-05869-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-024-05869-5","pdf_url":"https://link.springer.com/content/pdf/10.1186/s12859-024-05869-5.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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8299999833106995}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321613","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30"},{"id":"https://openalex.org/F4320323556","display_name":"Deutsche Krebshilfe","ror":"https://ror.org/01wxdd722"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402520149.pdf","grobid_xml":"https://content.openalex.org/works/W4402520149.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W2012627860","https://openalex.org/W2889326414","https://openalex.org/W2896457183","https://openalex.org/W2935703330","https://openalex.org/W2988217457","https://openalex.org/W3127238141","https://openalex.org/W3203588026","https://openalex.org/W4400921533","https://openalex.org/W6739901393","https://openalex.org/W6778883912","https://openalex.org/W6894165791","https://openalex.org/W6931930075"],"related_works":["https://openalex.org/W4298195702","https://openalex.org/W3093768914","https://openalex.org/W2883195674","https://openalex.org/W4378498597","https://openalex.org/W2945402993","https://openalex.org/W2072736607","https://openalex.org/W3101140821","https://openalex.org/W4287816966","https://openalex.org/W3015650676","https://openalex.org/W4389520445"],"abstract_inverted_index":{"Transformer-based":[0],"large":[1],"language":[2,80],"models":[3,35,129],"(LLMs)":[4],"are":[5],"very":[6],"suited":[7],"for":[8,61,72,205,216],"biological":[9,246],"sequence":[10,44,48,176,190,221,230],"data,":[11],"because":[12,23],"of":[13,26,64,120,149,157,175,224],"analogies":[14],"to":[15,53,68,115,171,187,241],"natural":[16],"language.":[17],"Complex":[18],"relationships":[19],"can":[20,28],"be":[21,29,214],"learned,":[22],"a":[24,78,111,219],"concept":[25],"\"words\"":[27],"generated":[30],"through":[31],"tokenization.":[32],"Training":[33],"the":[34,62,65,84,96,102,117,144,147,163,173,181,193,228,233,239],"with":[36,87,183,210],"masked":[37],"token":[38,43,107,160,198,229],"prediction,":[39],"they":[40],"learn":[41,188],"both":[42,59],"identity":[45,161],"and":[46,67,109],"larger":[47,189,220],"context.":[49,177,191],"We":[50,75,178],"developed":[51],"methodology":[52],"interrogate":[54,242],"model":[55,66,81,103,182],"learning,":[56,98],"which":[57,166],"is":[58,154,203,223],"relevant":[60],"interpretability":[63],"evaluate":[69,172],"its":[70],"potential":[71],"specific":[73,132],"tasks.":[74,208],"used":[76,215],"DNABERT,":[77],"DNA":[79],"trained":[82],"on":[83,139],"human":[85],"genome":[86,133],"overlapping":[88,184,211],"k-mers":[89,185],"as":[90],"tokens.":[91],"To":[92],"gain":[93],"insight":[94],"into":[95,162],"model's":[97],"we":[99],"interrogated":[100],"how":[101],"performs":[104],"predictions,":[105],"extracted":[106],"embeddings,":[108],"defined":[110],"fine-tuning":[112,207],"benchmarking":[113],"task":[114,126],"predict":[116],"next":[118],"tokens":[119,212],"different":[121],"sizes":[122],"without":[123,130],"overlaps.":[124],"This":[125,237],"evaluates":[127],"foundation":[128],"interrogating":[131],"biology,":[134],"it":[135,168],"does":[136],"not":[137],"depend":[138],"tokenization":[140],"strategies,":[141],"vocabulary":[142],"size,":[143],"dictionary,":[145],"or":[146],"number":[148],"training":[150],"parameters.":[151],"Lastly,":[152],"there":[153],"no":[155],"leakage":[156],"information":[158],"from":[159],"prediction":[164],"task,":[165],"makes":[167],"particularly":[169],"useful":[170],"learning":[174,235],"discovered":[179],"that":[180],"struggles":[186],"Instead,":[192],"learned":[194],"embeddings":[195],"largely":[196],"represent":[197],"sequence.":[199],"Still,":[200],"good":[201],"performance":[202],"achieved":[204],"genome-biology-inspired":[206],"Models":[209],"may":[213],"tasks":[217],"where":[218],"context":[222],"less":[225],"relevance,":[226],"but":[227],"directly":[231],"represents":[232],"desired":[234],"features.":[236],"emphasizes":[238],"need":[240],"knowledge":[243],"representation":[244],"in":[245],"LLMs.":[247]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
