{"id":"https://openalex.org/W3127238141","doi":"https://doi.org/10.1093/bioinformatics/btab083","title":"DNABERT: pre-trained Bidirectional Encoder Representations from Transformers model for DNA-language in genome","display_name":"DNABERT: pre-trained Bidirectional Encoder Representations from Transformers model for DNA-language in genome","publication_year":2021,"publication_date":"2021-02-03","ids":{"openalex":"https://openalex.org/W3127238141","doi":"https://doi.org/10.1093/bioinformatics/btab083","mag":"3127238141","pmid":"https://pubmed.ncbi.nlm.nih.gov/33538820"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btab083","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab083","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"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":null,"license_id":null,"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":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11025658","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012804505","display_name":"Yanrong Ji","orcid":"https://orcid.org/0000-0002-0134-664X"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanrong Ji","raw_affiliation_strings":["Division of Health and Biomedical Informatics, Department of Preventive Medicine, Northwestern University Feinberg School of Medicine , Chicago, IL 60611, USA"],"affiliations":[{"raw_affiliation_string":"Division of Health and Biomedical Informatics, Department of Preventive Medicine, Northwestern University Feinberg School of Medicine , Chicago, IL 60611, USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101957753","display_name":"Zhihan Zhou","orcid":"https://orcid.org/0000-0003-3263-7172"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhihan Zhou","raw_affiliation_strings":["Department of Computer Science, Northwestern University , Evanston, IL 60208, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Northwestern University , Evanston, IL 60208, USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100349037","display_name":"Han Liu","orcid":"https://orcid.org/0000-0002-2470-1755"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Han Liu","raw_affiliation_strings":["Department of Computer Science, Northwestern University , Evanston, IL 60208, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Northwestern University , Evanston, IL 60208, USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017429478","display_name":"Ramana V. Davuluri","orcid":"https://orcid.org/0000-0002-7053-1064"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ramana V Davuluri","raw_affiliation_strings":["Department of Biomedical Informatics, Stony Brook University , Stony Brook, NY 11794, USA"],"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Stony Brook University , Stony Brook, NY 11794, USA","institution_ids":["https://openalex.org/I59553526"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5017429478","https://openalex.org/A5100349037"],"corresponding_institution_ids":["https://openalex.org/I111979921","https://openalex.org/I59553526"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":51.3203,"has_fulltext":false,"cited_by_count":1139,"citation_normalized_percentile":{"value":0.9994805,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"37","issue":"15","first_page":"2112","last_page":"2120"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9918000102043152,"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":0.9918000102043152,"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":0.9871000051498413,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9847000241279602,"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/encoder","display_name":"Encoder","score":0.7776200771331787},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6500840187072754},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5892118811607361},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.4374021887779236},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.4147733747959137},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3844464421272278},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.2390230894088745},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.23694446682929993},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.15746954083442688},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09328198432922363},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.08639037609100342},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.05890458822250366}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7776200771331787},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6500840187072754},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5892118811607361},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.4374021887779236},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.4147733747959137},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3844464421272278},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.2390230894088745},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.23694446682929993},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.15746954083442688},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09328198432922363},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.08639037609100342},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.05890458822250366},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btab083","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab083","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:33538820","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33538820","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:pubmedcentral.nih.gov:11025658","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11025658","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:11025658","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11025658","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7110022956","display_name":null,"funder_award_id":"R01LM011297","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1019830208","https://openalex.org/W1581058135","https://openalex.org/W1988864819","https://openalex.org/W1991864975","https://openalex.org/W1997535872","https://openalex.org/W2013032282","https://openalex.org/W2039176012","https://openalex.org/W2058302256","https://openalex.org/W2060995975","https://openalex.org/W2064675550","https://openalex.org/W2077318478","https://openalex.org/W2083921257","https://openalex.org/W2093205346","https://openalex.org/W2094074349","https://openalex.org/W2095998476","https://openalex.org/W2103777723","https://openalex.org/W2117179531","https://openalex.org/W2117757143","https://openalex.org/W2118118849","https://openalex.org/W2122732537","https://openalex.org/W2137552931","https://openalex.org/W2142768995","https://openalex.org/W2147380886","https://openalex.org/W2151464048","https://openalex.org/W2154866190","https://openalex.org/W2157368769","https://openalex.org/W2163922914","https://openalex.org/W2198606573","https://openalex.org/W2259938310","https://openalex.org/W2336509392","https://openalex.org/W2345512687","https://openalex.org/W2415245143","https://openalex.org/W2519244818","https://openalex.org/W2554247923","https://openalex.org/W2624572223","https://openalex.org/W2737543579","https://openalex.org/W2795716241","https://openalex.org/W2888546502","https://openalex.org/W2896262061","https://openalex.org/W2901218091","https://openalex.org/W2901303766","https://openalex.org/W2908351833","https://openalex.org/W2911489562","https://openalex.org/W2919115771","https://openalex.org/W2932524182","https://openalex.org/W2966164316","https://openalex.org/W2972483465","https://openalex.org/W2979343233","https://openalex.org/W2996771978","https://openalex.org/W2997317337","https://openalex.org/W3000224897","https://openalex.org/W3096508121","https://openalex.org/W4248165980","https://openalex.org/W6753819590","https://openalex.org/W6755483654","https://openalex.org/W6772162023"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2142795561","https://openalex.org/W4205302943","https://openalex.org/W2561132942","https://openalex.org/W3155418658","https://openalex.org/W4243199227","https://openalex.org/W2379948177","https://openalex.org/W2119949815"],"abstract_inverted_index":{"Supplementary":[0],"data":[1],"are":[2],"available":[3],"at":[4],"Bioinformatics":[5],"online.":[6]},"counts_by_year":[{"year":2026,"cited_by_count":112},{"year":2025,"cited_by_count":425},{"year":2024,"cited_by_count":309},{"year":2023,"cited_by_count":189},{"year":2022,"cited_by_count":76},{"year":2021,"cited_by_count":27},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}
