{"id":"https://openalex.org/W4407265556","doi":"https://doi.org/10.1093/bioinformatics/btaf041","title":"Embed-Search-Align: DNA sequence alignment using Transformer models","display_name":"Embed-Search-Align: DNA sequence alignment using Transformer models","publication_year":2025,"publication_date":"2025-02-03","ids":{"openalex":"https://openalex.org/W4407265556","doi":"https://doi.org/10.1093/bioinformatics/btaf041","pmid":"https://pubmed.ncbi.nlm.nih.gov/39913380"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btaf041","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf041","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/41/3/btaf041/61778456/btaf041.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/article-pdf/41/3/btaf041/61778456/btaf041.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057287572","display_name":"Pavan Holur","orcid":"https://orcid.org/0000-0002-8495-9416"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]},{"id":"https://openalex.org/I2799798094","display_name":"UCLA Health","ror":"https://ror.org/01d88se56","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799798094"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pavan Holur","raw_affiliation_strings":["Department of Electrical and Computer Engineering, UCLA , Los Angeles, California, 90024,","Department of Electrical and Computer Engineering, UCLA"],"raw_orcid":"https://orcid.org/0000-0002-8495-9416","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, UCLA , Los Angeles, California, 90024,","institution_ids":["https://openalex.org/I161318765","https://openalex.org/I2799798094"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, UCLA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087151587","display_name":"Kenneth Enevoldsen","orcid":"https://orcid.org/0000-0001-8733-0966"},"institutions":[{"id":"https://openalex.org/I204337017","display_name":"Aarhus University","ror":"https://ror.org/01aj84f44","country_code":"DK","type":"education","lineage":["https://openalex.org/I204337017"]},{"id":"https://openalex.org/I2802335433","display_name":"Aarhus University Hospital","ror":"https://ror.org/040r8fr65","country_code":"DK","type":"healthcare","lineage":["https://openalex.org/I2802335433"]},{"id":"https://openalex.org/I4210151791","display_name":"Genomics (United Kingdom)","ror":"https://ror.org/053a6xa29","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210151791"]}],"countries":["DK","GB"],"is_corresponding":false,"raw_author_name":"K C Enevoldsen","raw_affiliation_strings":["Center for Humanities Computing, Aarhus University , Aarhus, 8000,","Center for Quantitative Genetics and Genomics, Aarhus University , Aarhus, 8000,","Center for Quantitative Genetics and Genomics, Aarhus University","Center for Humanities Computing, Aarhus University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Humanities Computing, Aarhus University , Aarhus, 8000,","institution_ids":["https://openalex.org/I204337017","https://openalex.org/I2802335433"]},{"raw_affiliation_string":"Center for Quantitative Genetics and Genomics, Aarhus University , Aarhus, 8000,","institution_ids":["https://openalex.org/I204337017"]},{"raw_affiliation_string":"Center for Quantitative Genetics and Genomics, Aarhus University","institution_ids":["https://openalex.org/I4210151791","https://openalex.org/I204337017"]},{"raw_affiliation_string":"Center for Humanities Computing, Aarhus University","institution_ids":["https://openalex.org/I204337017"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088303386","display_name":"Shreyas Rajesh","orcid":"https://orcid.org/0009-0002-8077-530X"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]},{"id":"https://openalex.org/I2799798094","display_name":"UCLA Health","ror":"https://ror.org/01d88se56","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799798094"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shreyas Rajesh","raw_affiliation_strings":["Department of Electrical and Computer Engineering, UCLA , Los Angeles, California, 90024,","Department of Electrical and Computer Engineering, UCLA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, UCLA , Los Angeles, California, 90024,","institution_ids":["https://openalex.org/I161318765","https://openalex.org/I2799798094"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, UCLA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092919253","display_name":"Lajoyce Mboning","orcid":"https://orcid.org/0009-0004-5047-5351"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]},{"id":"https://openalex.org/I2799798094","display_name":"UCLA Health","ror":"https://ror.org/01d88se56","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799798094"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lajoyce Mboning","raw_affiliation_strings":["Department of Chemistry and Biochemistry, UCLA , Los Angeles, California, 90024,","Department of Chemistry and Biochemistry, UCLA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry and Biochemistry, UCLA , Los Angeles, California, 90024,","institution_ids":["https://openalex.org/I161318765","https://openalex.org/I2799798094"]},{"raw_affiliation_string":"Department of Chemistry and Biochemistry, UCLA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104172306","display_name":"Thalia Georgiou","orcid":"https://orcid.org/0000-0003-1502-0058"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thalia Georgiou","raw_affiliation_strings":["Department of Biochemistry, Biophysics, and Structural Biology (MBIDP), UCLA , Los Angeles, California, 90024,","Department of Biochemistry, Biophysics, and Structural Biology (MBIDP), UCLA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biochemistry, Biophysics, and Structural Biology (MBIDP), UCLA , Los Angeles, California, 90024,","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"Department of Biochemistry, Biophysics, and Structural Biology (MBIDP), UCLA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053925403","display_name":"Louis\u2010S. Bouchard","orcid":"https://orcid.org/0000-0003-4151-5628"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]},{"id":"https://openalex.org/I2799798094","display_name":"UCLA Health","ror":"https://ror.org/01d88se56","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799798094"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Louis-S Bouchard","raw_affiliation_strings":["Department of Chemistry and Biochemistry, UCLA , Los Angeles, California, 90024,","Department of Chemistry and Biochemistry, UCLA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry and Biochemistry, UCLA , Los Angeles, California, 90024,","institution_ids":["https://openalex.org/I161318765","https://openalex.org/I2799798094"]},{"raw_affiliation_string":"Department of Chemistry and Biochemistry, UCLA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011670317","display_name":"Matteo Pellegrini","orcid":"https://orcid.org/0000-0001-9355-9564"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matteo Pellegrini","raw_affiliation_strings":["Department of Molecular, Cell, and Developmental Biology, UCLA , Los Angeles, California, 90024,","Molecular, Cell, and Developmental Biology, UCLA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Molecular, Cell, and Developmental Biology, UCLA , Los Angeles, California, 90024,","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"Molecular, Cell, and Developmental Biology, UCLA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043479061","display_name":"Vwani Roychowdhury","orcid":"https://orcid.org/0000-0003-0832-6489"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]},{"id":"https://openalex.org/I2799798094","display_name":"UCLA Health","ror":"https://ror.org/01d88se56","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799798094"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vwani Roychowdhury","raw_affiliation_strings":["Department of Electrical and Computer Engineering, UCLA , Los Angeles, California, 90024,","Department of Electrical and Computer Engineering, UCLA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, UCLA , Los Angeles, California, 90024,","institution_ids":["https://openalex.org/I161318765","https://openalex.org/I2799798094"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, UCLA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":3.9765,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.93498867,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"41","issue":"3","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.4307999908924103,"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":0.4307999908924103,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.13379999995231628,"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":0.11829999834299088,"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/computer-science","display_name":"Computer science","score":0.6387219429016113},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.5287073850631714},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.5164670944213867},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5046108961105347},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4962199330329895},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.49377354979515076},{"id":"https://openalex.org/keywords/multiple-sequence-alignment","display_name":"Multiple sequence alignment","score":0.47362133860588074},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.46801674365997314},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.41149190068244934},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36129212379455566},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32374829053878784},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.23711726069450378},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.21521106362342834},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1971648633480072},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.14002004265785217},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.12545186281204224},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11866870522499084},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08550560474395752}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6387219429016113},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.5287073850631714},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.5164670944213867},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5046108961105347},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4962199330329895},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.49377354979515076},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.47362133860588074},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.46801674365997314},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.41149190068244934},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36129212379455566},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32374829053878784},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.23711726069450378},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.21521106362342834},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1971648633480072},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.14002004265785217},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.12545186281204224},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11866870522499084},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08550560474395752},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[{"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":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","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":"D006801","descriptor_name":"Humans","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":false},{"descriptor_ui":"D012984","descriptor_name":"Software","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":false},{"descriptor_ui":"D012984","descriptor_name":"Software","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":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","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":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btaf041","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf041","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/41/3/btaf041/61778456/btaf041.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:39913380","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39913380","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:pure.atira.dk:openaire/314824bd-cd89-4781-8c89-cb331d3140ef","is_oa":true,"landing_page_url":"https://pure.au.dk/portal/en/publications/314824bd-cd89-4781-8c89-cb331d3140ef","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Holur, P, Enevoldsen, K C, Rajesh, S, Mboning, L, Georgiou, T, Bouchard, L S, Pellegrini, M & Roychowdhury, V 2025, 'Embed-Search-Align : DNA sequence alignment using Transformer models', Bioinformatics, vol. 41, no. 3, btaf041. https://doi.org/10.1093/bioinformatics/btaf041","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pubmedcentral.nih.gov:11919449","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11919449","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11919449/pdf/btaf041.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":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btaf041","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf041","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/41/3/btaf041/61778456/btaf041.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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5199999809265137}],"awards":[{"id":"https://openalex.org/G8730814777","display_name":null,"funder_award_id":"T32 HG002536","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"}],"funders":[{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407265556.pdf"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W2007213224","https://openalex.org/W2060108852","https://openalex.org/W2114850508","https://openalex.org/W2137591261","https://openalex.org/W2157539385","https://openalex.org/W2158874082","https://openalex.org/W2789843538","https://openalex.org/W2952597168","https://openalex.org/W2952870794","https://openalex.org/W2961460076","https://openalex.org/W2963469388","https://openalex.org/W2998702515","https://openalex.org/W3017152484","https://openalex.org/W3127238141","https://openalex.org/W4220999759","https://openalex.org/W4376133202","https://openalex.org/W4386022705","https://openalex.org/W4404821554","https://openalex.org/W4406419344","https://openalex.org/W6739901393","https://openalex.org/W6777615688","https://openalex.org/W6785413630"],"related_works":["https://openalex.org/W2051969447","https://openalex.org/W2111937814","https://openalex.org/W2162923930","https://openalex.org/W1482324242","https://openalex.org/W2133116680","https://openalex.org/W2091678889","https://openalex.org/W2029514038","https://openalex.org/W2149492307","https://openalex.org/W1985408726","https://openalex.org/W2141411672"],"abstract_inverted_index":{"MOTIVATION:":[0],"DNA":[1,11,68,85,133,174,185],"sequence":[2,89,96,163,175,217],"alignment,":[3,97],"an":[4,19],"important":[5],"genomic":[6],"task,":[7],"involves":[8],"assigning":[9],"short":[10,84],"reads":[12,142,204],"to":[13,37,102,107,188],"the":[14,46,58,146,228],"most":[15],"probable":[16],"locations":[17],"on":[18,45,193],"extensive":[20],"reference":[21,147,208],"genome.":[22],"Conventional":[23],"methods":[24,219],"tackle":[25],"this":[26,121],"challenge":[27],"in":[28,52,79,148],"two":[29],"steps:":[30],"genome":[31,209],"indexing":[32],"followed":[33],"by":[34,116,123],"efficient":[35],"search":[36,106,190],"locate":[38],"likely":[39],"positions":[40],"for":[41,162,170],"given":[42],"reads.":[43],"Building":[44],"success":[47],"of":[48,83,141,145,173,210,230],"Large":[49],"Language":[50],"Models":[51],"encoding":[53],"text":[54],"into":[55,70],"embeddings,":[56,181],"where":[57,98,129],"distance":[59,154],"metric":[60,155],"captures":[61],"semantic":[62],"similarity,":[63],"recent":[64,232],"efforts":[65],"have":[66,75],"encoded":[67],"sequences":[69],"vectors":[71],"using":[72],"Transformers":[73],"and":[74,143,182,223,241,247],"shown":[76],"promising":[77],"results":[78],"tasks":[80,91],"involving":[81],"classification":[82,90],"sequences.":[86],"Performance":[87],"at":[88],"does":[92],"not,":[93],"however,":[94],"guarantee":[95],"it":[99],"is":[100,156,198],"necessary":[101],"conduct":[103],"a":[104,112,125,130,149,160,184,194,206],"genome-wide":[105],"align":[108],"every":[109],"read":[110],"successfully,":[111],"significantly":[113],"longer-range":[114],"task":[115,243],"comparison.":[117],"RESULTS:":[118],"We":[119],"bridge":[120],"gap":[122],"developing":[124],"\"Embed-Search-Align\"":[126],"(ESA)":[127],"framework,":[128],"novel":[131],"Reference-Free":[132],"Embedding":[134],"(RDE)":[135],"Transformer":[136],"model":[137,234],"generates":[138],"vector":[139,151,186],"embeddings":[140],"fragments":[144,192],"shared":[150],"space;":[152],"read-fragment":[153],"then":[157],"used":[158],"as":[159,221,237],"surrogate":[161],"similarity.":[164],"ESA":[165],"introduces:":[166],"(i)":[167],"Contrastive":[168],"loss":[169],"self-supervised":[171],"training":[172],"representations,":[176],"facilitating":[177],"rich":[178],"reference-free,":[179],"sequence-level":[180],"(ii)":[183],"store":[187],"enable":[189],"across":[191,245],"global":[195],"scale.":[196],"RDE":[197,225],"99%":[199],"accurate":[200],"when":[201],"aligning":[202],"250-length":[203],"onto":[205],"human":[207],"3":[211],"gigabases":[212],"(single-haploid),":[213],"rivaling":[214],"conventional":[215],"algorithmic":[216],"alignment":[218],"such":[220,236],"Bowtie":[222],"BWA-Mem.":[224],"far":[226],"exceeds":[227],"performance":[229],"six":[231],"DNA-Transformer":[233],"baselines":[235],"Nucleotide":[238],"Transformer,":[239],"Hyena-DNA,":[240],"shows":[242],"transfer":[244],"chromosomes":[246],"species.":[248],"AVAILABILITY":[249],"AND":[250],"IMPLEMENTATION:":[251],"Please":[252],"see":[253],"https://anonymous.4open.science/r/dna2vec-7E4E/readme.md.":[254]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-08T08:33:18.762332","created_date":"2025-10-10T00:00:00"}