{"id":"https://openalex.org/W4390590489","doi":"https://doi.org/10.1093/bioinformatics/btad786","title":"Embedding-based alignment: combining protein language models with dynamic programming alignment to detect structural similarities in the twilight-zone","display_name":"Embedding-based alignment: combining protein language models with dynamic programming alignment to detect structural similarities in the twilight-zone","publication_year":2023,"publication_date":"2023-12-29","ids":{"openalex":"https://openalex.org/W4390590489","doi":"https://doi.org/10.1093/bioinformatics/btad786","pmid":"https://pubmed.ncbi.nlm.nih.gov/38175775"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btad786","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad786","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad786/55024500/btad786.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/btad786/55024500/btad786.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033190613","display_name":"Lorenzo Pantolini","orcid":"https://orcid.org/0009-0008-8641-8526"},"institutions":[{"id":"https://openalex.org/I12708293","display_name":"SIB Swiss Institute of Bioinformatics","ror":"https://ror.org/002n09z45","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I12708293"]},{"id":"https://openalex.org/I1850255","display_name":"University of Basel","ror":"https://ror.org/02s6k3f65","country_code":"CH","type":"education","lineage":["https://openalex.org/I1850255"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Lorenzo Pantolini","raw_affiliation_strings":["Biozentrum, University of Basel , Basel 4056, Switzerland","SIB Swiss Institute of Bioinformatics , Basel 4056, Switzerland","Biozentrum, University of Basel, Basel, 4056, Switzerland","SIB: Swiss Institute of Bioinformatics, Basel, 4056, Switzerland"],"raw_orcid":"https://orcid.org/0009-0008-8641-8526","affiliations":[{"raw_affiliation_string":"Biozentrum, University of Basel , Basel 4056, Switzerland","institution_ids":["https://openalex.org/I1850255"]},{"raw_affiliation_string":"SIB Swiss Institute of Bioinformatics , Basel 4056, Switzerland","institution_ids":["https://openalex.org/I12708293"]},{"raw_affiliation_string":"Biozentrum, University of Basel, Basel, 4056, Switzerland","institution_ids":["https://openalex.org/I1850255"]},{"raw_affiliation_string":"SIB: Swiss Institute of Bioinformatics, Basel, 4056, Switzerland","institution_ids":["https://openalex.org/I12708293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053683682","display_name":"Gabriel Studer","orcid":"https://orcid.org/0000-0003-0462-1456"},"institutions":[{"id":"https://openalex.org/I12708293","display_name":"SIB Swiss Institute of Bioinformatics","ror":"https://ror.org/002n09z45","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I12708293"]},{"id":"https://openalex.org/I1850255","display_name":"University of Basel","ror":"https://ror.org/02s6k3f65","country_code":"CH","type":"education","lineage":["https://openalex.org/I1850255"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Gabriel Studer","raw_affiliation_strings":["Biozentrum, University of Basel , Basel 4056, Switzerland","SIB Swiss Institute of Bioinformatics , Basel 4056, Switzerland","SIB: Swiss Institute of Bioinformatics, Basel, 4056, Switzerland","Biozentrum, University of Basel, Basel, 4056, Switzerland"],"raw_orcid":"https://orcid.org/0000-0003-0462-1456","affiliations":[{"raw_affiliation_string":"Biozentrum, University of Basel , Basel 4056, Switzerland","institution_ids":["https://openalex.org/I1850255"]},{"raw_affiliation_string":"SIB Swiss Institute of Bioinformatics , Basel 4056, Switzerland","institution_ids":["https://openalex.org/I12708293"]},{"raw_affiliation_string":"SIB: Swiss Institute of Bioinformatics, Basel, 4056, Switzerland","institution_ids":["https://openalex.org/I12708293"]},{"raw_affiliation_string":"Biozentrum, University of Basel, Basel, 4056, Switzerland","institution_ids":["https://openalex.org/I1850255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041584450","display_name":"Joana Pereira","orcid":"https://orcid.org/0000-0002-5588-6588"},"institutions":[{"id":"https://openalex.org/I12708293","display_name":"SIB Swiss Institute of Bioinformatics","ror":"https://ror.org/002n09z45","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I12708293"]},{"id":"https://openalex.org/I1850255","display_name":"University of Basel","ror":"https://ror.org/02s6k3f65","country_code":"CH","type":"education","lineage":["https://openalex.org/I1850255"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Joana Pereira","raw_affiliation_strings":["Biozentrum, University of Basel , Basel 4056, Switzerland","SIB Swiss Institute of Bioinformatics , Basel 4056, Switzerland","SIB: Swiss Institute of Bioinformatics, Basel, 4056, Switzerland","Biozentrum, University of Basel, Basel, 4056, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-5588-6588","affiliations":[{"raw_affiliation_string":"Biozentrum, University of Basel , Basel 4056, Switzerland","institution_ids":["https://openalex.org/I1850255"]},{"raw_affiliation_string":"SIB Swiss Institute of Bioinformatics , Basel 4056, Switzerland","institution_ids":["https://openalex.org/I12708293"]},{"raw_affiliation_string":"SIB: Swiss Institute of Bioinformatics, Basel, 4056, Switzerland","institution_ids":["https://openalex.org/I12708293"]},{"raw_affiliation_string":"Biozentrum, University of Basel, Basel, 4056, Switzerland","institution_ids":["https://openalex.org/I1850255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040003101","display_name":"Janani Durairaj","orcid":"https://orcid.org/0000-0002-1698-4556"},"institutions":[{"id":"https://openalex.org/I12708293","display_name":"SIB Swiss Institute of Bioinformatics","ror":"https://ror.org/002n09z45","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I12708293"]},{"id":"https://openalex.org/I1850255","display_name":"University of Basel","ror":"https://ror.org/02s6k3f65","country_code":"CH","type":"education","lineage":["https://openalex.org/I1850255"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Janani Durairaj","raw_affiliation_strings":["Biozentrum, University of Basel , Basel 4056, Switzerland","SIB Swiss Institute of Bioinformatics , Basel 4056, Switzerland","SIB: Swiss Institute of Bioinformatics, Basel, 4056, Switzerland","Biozentrum, University of Basel, Basel, 4056, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-1698-4556","affiliations":[{"raw_affiliation_string":"Biozentrum, University of Basel , Basel 4056, Switzerland","institution_ids":["https://openalex.org/I1850255"]},{"raw_affiliation_string":"SIB Swiss Institute of Bioinformatics , Basel 4056, Switzerland","institution_ids":["https://openalex.org/I12708293"]},{"raw_affiliation_string":"SIB: Swiss Institute of Bioinformatics, Basel, 4056, Switzerland","institution_ids":["https://openalex.org/I12708293"]},{"raw_affiliation_string":"Biozentrum, University of Basel, Basel, 4056, Switzerland","institution_ids":["https://openalex.org/I1850255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090117521","display_name":"Gerardo Tauriello","orcid":"https://orcid.org/0000-0002-5921-7007"},"institutions":[{"id":"https://openalex.org/I12708293","display_name":"SIB Swiss Institute of Bioinformatics","ror":"https://ror.org/002n09z45","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I12708293"]},{"id":"https://openalex.org/I1850255","display_name":"University of Basel","ror":"https://ror.org/02s6k3f65","country_code":"CH","type":"education","lineage":["https://openalex.org/I1850255"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Gerardo Tauriello","raw_affiliation_strings":["Biozentrum, University of Basel , Basel 4056, Switzerland","SIB Swiss Institute of Bioinformatics , Basel 4056, Switzerland","Biozentrum, University of Basel, Basel, 4056, Switzerland","SIB: Swiss Institute of Bioinformatics, Basel, 4056, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-5921-7007","affiliations":[{"raw_affiliation_string":"Biozentrum, University of Basel , Basel 4056, Switzerland","institution_ids":["https://openalex.org/I1850255"]},{"raw_affiliation_string":"SIB Swiss Institute of Bioinformatics , Basel 4056, Switzerland","institution_ids":["https://openalex.org/I12708293"]},{"raw_affiliation_string":"Biozentrum, University of Basel, Basel, 4056, Switzerland","institution_ids":["https://openalex.org/I1850255"]},{"raw_affiliation_string":"SIB: Swiss Institute of Bioinformatics, Basel, 4056, Switzerland","institution_ids":["https://openalex.org/I12708293"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049569891","display_name":"Torsten Schwede","orcid":"https://orcid.org/0000-0003-2715-335X"},"institutions":[{"id":"https://openalex.org/I12708293","display_name":"SIB Swiss Institute of Bioinformatics","ror":"https://ror.org/002n09z45","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I12708293"]},{"id":"https://openalex.org/I1850255","display_name":"University of Basel","ror":"https://ror.org/02s6k3f65","country_code":"CH","type":"education","lineage":["https://openalex.org/I1850255"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Torsten Schwede","raw_affiliation_strings":["Biozentrum, University of Basel , Basel 4056, Switzerland","SIB Swiss Institute of Bioinformatics , Basel 4056, Switzerland","Biozentrum, University of Basel, Basel, 4056, Switzerland","SIB: Swiss Institute of Bioinformatics, Basel, 4056, Switzerland"],"raw_orcid":"https://orcid.org/0000-0003-2715-335X","affiliations":[{"raw_affiliation_string":"Biozentrum, University of Basel , Basel 4056, Switzerland","institution_ids":["https://openalex.org/I1850255"]},{"raw_affiliation_string":"SIB Swiss Institute of Bioinformatics , Basel 4056, Switzerland","institution_ids":["https://openalex.org/I12708293"]},{"raw_affiliation_string":"Biozentrum, University of Basel, Basel, 4056, Switzerland","institution_ids":["https://openalex.org/I1850255"]},{"raw_affiliation_string":"SIB: Swiss Institute of Bioinformatics, Basel, 4056, Switzerland","institution_ids":["https://openalex.org/I12708293"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5049569891"],"corresponding_institution_ids":["https://openalex.org/I12708293","https://openalex.org/I1850255"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":6.8661,"has_fulltext":true,"cited_by_count":51,"citation_normalized_percentile":{"value":0.97606339,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"40","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.2935999929904938,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.2935999929904938,"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":0.28700000047683716,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.21070000529289246,"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/embedding","display_name":"Embedding","score":0.7990362048149109},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7210502624511719},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.6453449726104736},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.438036173582077},{"id":"https://openalex.org/keywords/structural-alignment","display_name":"Structural alignment","score":0.4198923110961914},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3753408193588257},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.36966145038604736},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.35922694206237793},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34679466485977173},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.08116954565048218}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7990362048149109},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7210502624511719},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.6453449726104736},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.438036173582077},{"id":"https://openalex.org/C4668613","wikidata":"https://www.wikidata.org/wiki/Q4116110","display_name":"Structural alignment","level":5,"score":0.4198923110961914},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3753408193588257},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.36966145038604736},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.35922694206237793},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34679466485977173},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.08116954565048218},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btad786","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad786","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad786/55024500/btad786.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:38175775","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38175775","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:10792726","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10792726","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10792726/pdf/btad786.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/btad786","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad786","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad786/55024500/btad786.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","score":0.8299999833106995,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310466","display_name":"Universit\u00e4t Basel","ror":"https://ror.org/02s6k3f65"},{"id":"https://openalex.org/F4320331322","display_name":"Swiss Institute of Bioinformatics","ror":"https://ror.org/002n09z45"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4390590489.pdf"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W2004178884","https://openalex.org/W2022058405","https://openalex.org/W2101220662","https://openalex.org/W2102245393","https://openalex.org/W2102461176","https://openalex.org/W2108361377","https://openalex.org/W2143210482","https://openalex.org/W2148311769","https://openalex.org/W2153153865","https://openalex.org/W2161151688","https://openalex.org/W2918063357","https://openalex.org/W2950954328","https://openalex.org/W2972411752","https://openalex.org/W2984761660","https://openalex.org/W3106745904","https://openalex.org/W3146944767","https://openalex.org/W3166142427","https://openalex.org/W3177500196","https://openalex.org/W3177828909","https://openalex.org/W3211795435","https://openalex.org/W4210494137","https://openalex.org/W4282984452","https://openalex.org/W4309485183","https://openalex.org/W4309609816","https://openalex.org/W4327550249","https://openalex.org/W4375858802","https://openalex.org/W4383313853","https://openalex.org/W4385245566","https://openalex.org/W4386496033","https://openalex.org/W4386860638","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W2029514038","https://openalex.org/W2088487249","https://openalex.org/W2111937814","https://openalex.org/W1985408726","https://openalex.org/W2051969447","https://openalex.org/W2061567716","https://openalex.org/W1482324242","https://openalex.org/W2084367350","https://openalex.org/W2130940308","https://openalex.org/W1981307089"],"abstract_inverted_index":{"MOTIVATION:":[0],"Language":[1],"models":[2,31],"are":[3],"routinely":[4],"used":[5,62],"for":[6,67,74,148],"text":[7],"classification":[8],"and":[9,40,97,131,166,178],"generative":[10],"tasks.":[11],"Recently,":[12],"the":[13,26,51,54,106,127,137,149,156,168],"same":[14],"architectures":[15],"were":[16],"applied":[17],"to":[18,163],"protein":[19,56,93],"sequences,":[20],"unlocking":[21],"powerful":[22],"new":[23,88],"approaches":[24,117],"in":[25,50,105,155,171],"bioinformatics":[27],"field.":[28],"Protein":[29],"language":[30],"(pLMs)":[32],"generate":[33],"high-dimensional":[34],"embeddings":[35],"on":[36,119],"a":[37,42,64,87,145],"per-residue":[38],"level":[39],"encode":[41],"\"semantic":[43],"meaning\"":[44],"of":[45,53,129,139,151],"each":[46],"individual":[47],"amino":[48],"acid":[49],"context":[52],"full":[55],"sequence.":[57],"These":[58],"representations":[59],"have":[60],"been":[61],"as":[63,113,115],"starting":[65],"point":[66],"downstream":[68],"learning":[69],"tasks":[70],"and,":[71],"more":[72],"recently,":[73],"identifying":[75],"distant":[76],"homologous":[77],"relationships":[78,152],"between":[79,153],"proteins.":[80],"RESULTS:":[81],"In":[82],"this":[83,172],"work,":[84],"we":[85],"introduce":[86],"method":[89,122],"that":[90,136],"generates":[91],"embedding-based":[92],"sequence":[94],"alignments":[95],"(EBA)":[96],"show":[98],"how":[99],"these":[100],"capture":[101],"structural":[102],"similarities":[103],"even":[104],"twilight":[107],"zone,":[108],"outperforming":[109],"both":[110],"classical":[111],"methods":[112,143],"well":[114],"other":[116],"based":[118],"pLMs.":[120],"The":[121,161],"shows":[123],"excellent":[124],"accuracy":[125],"despite":[126],"absence":[128],"training":[130],"parameter":[132],"optimization.":[133],"We":[134],"demonstrate":[135],"combination":[138],"pLMs":[140],"with":[141],"alignment":[142],"is":[144,174],"valuable":[146],"approach":[147],"detection":[150],"proteins":[154],"twilight-zone.":[157],"AVAILABILITY":[158],"AND":[159],"IMPLEMENTATION:":[160],"code":[162],"run":[164],"EBA":[165],"reproduce":[167],"analysis":[169],"described":[170],"article":[173],"available":[175],"at:":[176],"https://git.scicore.unibas.ch/schwede/EBA":[177],"https://git.scicore.unibas.ch/schwede/eba_benchmark.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":22},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-11T18:08:03.149640","created_date":"2025-10-10T00:00:00"}
