{"id":"https://openalex.org/W4395451981","doi":"https://doi.org/10.1186/s12859-024-05779-6","title":"Improvements in viral gene annotation using large language models and soft alignments","display_name":"Improvements in viral gene annotation using large language models and soft alignments","publication_year":2024,"publication_date":"2024-04-25","ids":{"openalex":"https://openalex.org/W4395451981","doi":"https://doi.org/10.1186/s12859-024-05779-6","pmid":"https://pubmed.ncbi.nlm.nih.gov/38664627"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-024-05779-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-024-05779-6","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-024-05779-6","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-024-05779-6","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5095888935","display_name":"William Harrigan","orcid":"https://orcid.org/0000-0003-2935-6863"},"institutions":[{"id":"https://openalex.org/I117965899","display_name":"University of Hawai\u02bbi at M\u0101noa","ror":"https://ror.org/01wspgy28","country_code":"US","type":"education","lineage":["https://openalex.org/I117965899"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William L. Harrigan","raw_affiliation_strings":["Hawai'i Institute of Marine Biology, University of Hawai'i at M\u0101noa, Honolulu, HI, 96822, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hawai'i Institute of Marine Biology, University of Hawai'i at M\u0101noa, Honolulu, HI, 96822, USA","institution_ids":["https://openalex.org/I117965899"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029560442","display_name":"Barbra D. Ferrell","orcid":"https://orcid.org/0000-0003-3057-3478"},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Barbra D. Ferrell","raw_affiliation_strings":["Department of Plant & Soil Sciences, University of Delaware, Newark, DE, 19713, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Plant & Soil Sciences, University of Delaware, Newark, DE, 19713, USA","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073203401","display_name":"K. Eric Wommack","orcid":"https://orcid.org/0000-0001-5797-7128"},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"K. Eric Wommack","raw_affiliation_strings":["Department of Plant & Soil Sciences, University of Delaware, Newark, DE, 19713, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Plant & Soil Sciences, University of Delaware, Newark, DE, 19713, USA","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082160609","display_name":"Shawn W. Polson","orcid":"https://orcid.org/0000-0002-3398-6932"},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shawn W. Polson","raw_affiliation_strings":["Department of Computer and Information Sciences, University of Delaware, Newark, DE, 19713, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Sciences, University of Delaware, Newark, DE, 19713, USA","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5095888936","display_name":"Zachary D. Schreiber","orcid":null},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zachary D. Schreiber","raw_affiliation_strings":["Department of Plant & Soil Sciences, University of Delaware, Newark, DE, 19713, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Plant & Soil Sciences, University of Delaware, Newark, DE, 19713, USA","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035080938","display_name":"Mahdi Belcaid","orcid":"https://orcid.org/0009-0004-5185-0643"},"institutions":[{"id":"https://openalex.org/I117965899","display_name":"University of Hawai\u02bbi at M\u0101noa","ror":"https://ror.org/01wspgy28","country_code":"US","type":"education","lineage":["https://openalex.org/I117965899"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mahdi Belcaid","raw_affiliation_strings":["Department of Computer Science, University of Hawai'i at M\u0101noa, Honolulu, HI, 96822, USA. mahdi@hawaii.edu","Department of Computer Science, University of Hawai'i at M\u0101noa, Honolulu, HI, 96822, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Hawai'i at M\u0101noa, Honolulu, HI, 96822, USA. mahdi@hawaii.edu","institution_ids":["https://openalex.org/I117965899"]},{"raw_affiliation_string":"Department of Computer Science, University of Hawai'i at M\u0101noa, Honolulu, HI, 96822, USA","institution_ids":["https://openalex.org/I117965899"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5035080938"],"corresponding_institution_ids":["https://openalex.org/I117965899"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":3.7212,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.9242312,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"25","issue":"1","first_page":"165","last_page":"165"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11048","display_name":"Bacteriophages and microbial interactions","score":0.29269999265670776,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11048","display_name":"Bacteriophages and microbial interactions","score":0.29269999265670776,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.12229999899864197,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.11479999870061874,"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/annotation","display_name":"Annotation","score":0.7472569346427917},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.6436008214950562},{"id":"https://openalex.org/keywords/dna-microarray","display_name":"DNA microarray","score":0.5832805633544922},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5167738199234009},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.450982928276062},{"id":"https://openalex.org/keywords/gene-annotation","display_name":"Gene Annotation","score":0.4260697066783905},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.4218555688858032},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.3252643346786499},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.3249366581439972},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.3006102442741394},{"id":"https://openalex.org/keywords/gene-expression","display_name":"Gene expression","score":0.1637411117553711}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7472569346427917},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6436008214950562},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.5832805633544922},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5167738199234009},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.450982928276062},{"id":"https://openalex.org/C2908923196","wikidata":"https://www.wikidata.org/wiki/Q5205742","display_name":"Gene Annotation","level":4,"score":0.4260697066783905},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.4218555688858032},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.3252643346786499},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.3249366581439972},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.3006102442741394},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.1637411117553711}],"mesh":[{"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":"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":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D005814","descriptor_name":"Genes, Viral","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005814","descriptor_name":"Genes, Viral","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005814","descriptor_name":"Genes, Viral","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005814","descriptor_name":"Genes, Viral","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005814","descriptor_name":"Genes, Viral","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014764","descriptor_name":"Viral Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D014764","descriptor_name":"Viral Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D014764","descriptor_name":"Viral Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D014764","descriptor_name":"Viral Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D014764","descriptor_name":"Viral Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D014764","descriptor_name":"Viral Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D014764","descriptor_name":"Viral Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D014764","descriptor_name":"Viral Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D014764","descriptor_name":"Viral Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D014764","descriptor_name":"Viral Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","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":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12859-024-05779-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-024-05779-6","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-024-05779-6","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:38664627","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38664627","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11046836","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11046836","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11046836/pdf/12859_2024_Article_5779.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:11da29dbb5db42a19a182a6b11c4be02","is_oa":false,"landing_page_url":"https://doaj.org/article/11da29dbb5db42a19a182a6b11c4be02","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 25, Iss 1, Pp 1-19 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s12859-024-05779-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-024-05779-6","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-024-05779-6","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G7065548098","display_name":null,"funder_award_id":"2149133","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320338283","display_name":"Office of Experimental Program to Stimulate Competitive Research","ror":"https://ror.org/04k9mqs78"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4395451981.pdf"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W634418684","https://openalex.org/W1486817521","https://openalex.org/W1505893511","https://openalex.org/W1966912927","https://openalex.org/W1967320885","https://openalex.org/W1999200033","https://openalex.org/W2001668098","https://openalex.org/W2046892081","https://openalex.org/W2055043387","https://openalex.org/W2060797027","https://openalex.org/W2076048958","https://openalex.org/W2117486996","https://openalex.org/W2141885858","https://openalex.org/W2148495628","https://openalex.org/W2158714788","https://openalex.org/W2163922914","https://openalex.org/W2252523470","https://openalex.org/W2781086737","https://openalex.org/W2945297971","https://openalex.org/W2951765074","https://openalex.org/W2998702515","https://openalex.org/W3007807538","https://openalex.org/W3023746197","https://openalex.org/W3045012301","https://openalex.org/W3111174583","https://openalex.org/W3118936575","https://openalex.org/W3155977246","https://openalex.org/W3166142427","https://openalex.org/W3175996595","https://openalex.org/W3177500196","https://openalex.org/W3177828909","https://openalex.org/W3202237470","https://openalex.org/W4210400672","https://openalex.org/W4280592348","https://openalex.org/W4290989027","https://openalex.org/W4306404289","https://openalex.org/W4313430582","https://openalex.org/W4315641887","https://openalex.org/W4318071656","https://openalex.org/W4382246105","https://openalex.org/W4388024559","https://openalex.org/W4392686654","https://openalex.org/W6601298480","https://openalex.org/W6729835178"],"related_works":["https://openalex.org/W2059565715","https://openalex.org/W2901823680","https://openalex.org/W2009940763","https://openalex.org/W4386637333","https://openalex.org/W2946410450","https://openalex.org/W4361192415","https://openalex.org/W2126804125","https://openalex.org/W2162782320","https://openalex.org/W2137318037","https://openalex.org/W1760213857"],"abstract_inverted_index":{"BACKGROUND:":[0],"The":[1,188],"annotation":[2,143],"of":[3,195],"protein":[4,55,73,142,158,199,217],"sequences":[5,56,170],"in":[6,14,100,104,203,220],"public":[7],"databases":[8,159],"has":[9],"long":[10],"posed":[11],"a":[12,123,209],"challenge":[13,52],"molecular":[15,221],"biology.":[16,222],"This":[17,92],"issue":[18],"is":[19,65],"particularly":[20],"acute":[21],"for":[22,88,181,197,212],"viral":[23,204],"proteins,":[24],"which":[25,177],"demonstrate":[26],"limited":[27],"homology":[28,38],"to":[29,62,84,108,140,185],"known":[30],"proteins":[31],"when":[32],"using":[33,151],"alignment,":[34],"k-mer,":[35],"or":[36],"profile-based":[37],"search":[39],"approaches.":[40],"A":[41],"novel":[42,163],"methodology":[43],"employing":[44],"Large":[45],"Language":[46],"Models":[47],"(LLMs)":[48],"addresses":[49],"this":[50],"methodological":[51],"by":[53],"annotating":[54],"based":[57],"on":[58],"embeddings.":[59],"RESULTS:":[60],"Central":[61],"our":[63,126],"contribution":[64],"the":[66,80,86,118,152,162,192],"soft":[67,164],"alignment":[68,74,131,165],"algorithm,":[69],"drawing":[70],"from":[71,121],"traditional":[72,134],"but":[75,102],"leveraging":[76],"embedding":[77],"similarity":[78],"at":[79],"amino":[81,112],"acid":[82],"level":[83],"bypass":[85],"need":[87],"conventional":[89],"scoring":[90],"matrices.":[91],"method":[93],"not":[94],"only":[95],"surpasses":[96],"pooled":[97],"embedding-based":[98,145],"models":[99],"efficiency":[101],"also":[103],"interpretability,":[105],"enabling":[106],"users":[107],"easily":[109],"trace":[110],"homologous":[111],"acids":[113],"and":[114,156,168,174,215],"delve":[115],"deeper":[116],"into":[117],"alignments.":[119],"Far":[120],"being":[122],"black":[124],"box,":[125],"approach":[127,166,190],"provides":[128],"transparent,":[129],"BLAST-like":[130],"visualizations,":[132],"combining":[133],"biological":[135],"research":[136],"with":[137],"AI":[138],"advancements":[139],"elevate":[141],"through":[144],"analysis":[146],"while":[147],"ensuring":[148],"interpretability.":[149],"Tests":[150],"Virus":[153],"Orthologous":[154],"Groups":[155],"ViralZone":[157],"indicated":[160],"that":[161,171],"recognized":[167],"annotated":[169],"both":[172],"blastp":[173],"pooling-based":[175],"methods,":[176],"are":[178],"commonly":[179],"used":[180],"sequence":[182,200],"annotation,":[183,201],"failed":[184],"detect.":[186],"CONCLUSION:":[187],"embeddings":[189],"shows":[191],"great":[193],"potential":[194],"LLMs":[196],"enhancing":[198],"especially":[202],"genomics.":[205],"These":[206],"findings":[207],"present":[208],"promising":[210],"avenue":[211],"more":[213],"efficient":[214],"accurate":[216],"function":[218],"inference":[219]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-07T08:38:57.713557","created_date":"2025-10-10T00:00:00"}
