{"id":"https://openalex.org/W4387472400","doi":"https://doi.org/10.1093/bioinformatics/btad617","title":"Investigation of the BERT model on nucleotide sequences with non-standard pre-training and evaluation of different k-mer embeddings","display_name":"Investigation of the BERT model on nucleotide sequences with non-standard pre-training and evaluation of different k-mer embeddings","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4387472400","doi":"https://doi.org/10.1093/bioinformatics/btad617","pmid":"https://pubmed.ncbi.nlm.nih.gov/37815839"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btad617","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad617","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad617/51990559/btad617.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/btad617/51990559/btad617.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101711221","display_name":"Yaozhong Zhang","orcid":"https://orcid.org/0000-0001-5598-2521"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yao-zhong Zhang","raw_affiliation_strings":["Division of Health Medical Intelligence, Human Genome Center, The Institute of Medical Science, The University of Tokyo , Minato-ku, Tokyo 108-8639, Japan"],"affiliations":[{"raw_affiliation_string":"Division of Health Medical Intelligence, Human Genome Center, The Institute of Medical Science, The University of Tokyo , Minato-ku, Tokyo 108-8639, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087847911","display_name":"Zeheng Bai","orcid":"https://orcid.org/0000-0002-4921-0936"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Zeheng Bai","raw_affiliation_strings":["Division of Health Medical Intelligence, Human Genome Center, The Institute of Medical Science, The University of Tokyo , Minato-ku, Tokyo 108-8639, Japan"],"affiliations":[{"raw_affiliation_string":"Division of Health Medical Intelligence, Human Genome Center, The Institute of Medical Science, The University of Tokyo , Minato-ku, Tokyo 108-8639, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090788230","display_name":"Seiya Imoto","orcid":"https://orcid.org/0000-0002-2989-308X"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Seiya Imoto","raw_affiliation_strings":["Division of Health Medical Intelligence, Human Genome Center, The Institute of Medical Science, The University of Tokyo , Minato-ku, Tokyo 108-8639, Japan"],"affiliations":[{"raw_affiliation_string":"Division of Health Medical Intelligence, Human Genome Center, The Institute of Medical Science, The University of Tokyo , Minato-ku, Tokyo 108-8639, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101711221"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":1.3703,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.81411652,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"39","issue":"10","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9965000152587891,"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":0.9965000152587891,"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":0.9896000027656555,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.9886999726295471,"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/training","display_name":"Training (meteorology)","score":0.6148573160171509},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5602641701698303},{"id":"https://openalex.org/keywords/nucleotide","display_name":"Nucleotide","score":0.5475916266441345},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.42556631565093994},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40280821919441223},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3681265711784363},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2788196802139282},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.25316113233566284},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.15486028790473938},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06958663463592529}],"concepts":[{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6148573160171509},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5602641701698303},{"id":"https://openalex.org/C512185932","wikidata":"https://www.wikidata.org/wiki/Q28745","display_name":"Nucleotide","level":3,"score":0.5475916266441345},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.42556631565093994},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40280821919441223},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3681265711784363},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2788196802139282},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.25316113233566284},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.15486028790473938},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06958663463592529},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btad617","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad617","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad617/51990559/btad617.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:37815839","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37815839","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:10612406","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10612406","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10612406/pdf/btad617.pdf","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/btad617","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad617","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad617/51990559/btad617.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/G1069223013","display_name":null,"funder_award_id":"JSPS KAKENHI","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G2428335076","display_name":null,"funder_award_id":"Grant-in-Aid","funder_id":"https://openalex.org/F4320310760","funder_display_name":"Uehara Memorial Foundation"},{"id":"https://openalex.org/G2983449479","display_name":null,"funder_award_id":"Scientific Research","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3236194794","display_name":null,"funder_award_id":"Grant-in-Aid","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G341696990","display_name":null,"funder_award_id":"21H0353","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3459562248","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3837059165","display_name":null,"funder_award_id":"JP21K12104","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4227499671","display_name":null,"funder_award_id":"KAKENHI Grant","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4636223006","display_name":null,"funder_award_id":"JSPS KAK","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4856980766","display_name":null,"funder_award_id":"grant","funder_id":"https://openalex.org/F4320310760","funder_display_name":"Uehara Memorial Foundation"},{"id":"https://openalex.org/G4874944895","display_name":null,"funder_award_id":"-in-Aid","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G5737339462","display_name":"The development of a high-performance nanopore methylation detection method with consideration of structural variation","funder_award_id":"21K12104","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7167128334","display_name":null,"funder_award_id":"Grant-in-Aid for Scientific Researc","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7337825077","display_name":null,"funder_award_id":"Grant-in-Aid for Sc","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7752643416","display_name":null,"funder_award_id":"Japan","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8295330643","display_name":null,"funder_award_id":"21H03538","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8430481527","display_name":null,"funder_award_id":"Number","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8759943101","display_name":null,"funder_award_id":"rant-in-Aid for Scientific Research","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8798871029","display_name":null,"funder_award_id":"Uehara","funder_id":"https://openalex.org/F4320310760","funder_display_name":"Uehara Memorial Foundation"}],"funders":[{"id":"https://openalex.org/F4320310760","display_name":"Uehara Memorial Foundation","ror":"https://ror.org/00gc20a07"},{"id":"https://openalex.org/F4320322832","display_name":"University of Tokyo","ror":"https://ror.org/057zh3y96"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387472400.pdf"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W2101234009","https://openalex.org/W2433743436","https://openalex.org/W2558947257","https://openalex.org/W2791796577","https://openalex.org/W2932524182","https://openalex.org/W3127238141","https://openalex.org/W3177500196","https://openalex.org/W3177828909","https://openalex.org/W3186029797","https://openalex.org/W4225852959","https://openalex.org/W4300862723","https://openalex.org/W6675354045","https://openalex.org/W6798769241"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W4379233589","https://openalex.org/W2997094352","https://openalex.org/W2335033221","https://openalex.org/W3216976533","https://openalex.org/W2092808452","https://openalex.org/W2551249631"],"abstract_inverted_index":{"The":[0],"source":[1],"code":[2],"and":[3],"associated":[4],"data":[5],"can":[6],"be":[7],"accessed":[8],"at":[9],"https://github.com/yaozhong/bert_investigation.":[10]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}