{"id":"https://openalex.org/W4406259803","doi":"https://doi.org/10.1109/bibm62325.2024.10822432","title":"Gene function prediction using an AnnoTree-based genomic language model","display_name":"Gene function prediction using an AnnoTree-based genomic language model","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406259803","doi":"https://doi.org/10.1109/bibm62325.2024.10822432"},"language":"en","primary_location":{"id":"doi:10.1109/bibm62325.2024.10822432","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm62325.2024.10822432","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052356216","display_name":"Huagang Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Huagang Tan","raw_affiliation_strings":["University of Waterloo,Department of Biology,Waterloo,ON,Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo,Department of Biology,Waterloo,ON,Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057232313","display_name":"Gabriel Moreno\u2010Hagelsieb","orcid":"https://orcid.org/0000-0002-2457-4450"},"institutions":[{"id":"https://openalex.org/I75381157","display_name":"Wilfrid Laurier University","ror":"https://ror.org/00fn7gb05","country_code":"CA","type":"education","lineage":["https://openalex.org/I75381157"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Gabriel Moreno-Hagelsieb","raw_affiliation_strings":["Wilfrid Laurier University,Department of Biology,Waterloo,ON,Canada"],"affiliations":[{"raw_affiliation_string":"Wilfrid Laurier University,Department of Biology,Waterloo,ON,Canada","institution_ids":["https://openalex.org/I75381157"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032187526","display_name":"Andrew C. Doxey","orcid":"https://orcid.org/0000-0003-2015-099X"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Andrew C. Doxey","raw_affiliation_strings":["University of Waterloo,Cheriton School of Computer Science,Department of Biology,Waterloo,ON,Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo,Cheriton School of Computer Science,Department of Biology,Waterloo,ON,Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5052356216"],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":0.2494,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.61140585,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"5120","last_page":"5126"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9624000191688538,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9624000191688538,"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/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.9348999857902527,"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":0.6806454658508301},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.504438042640686},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4706408679485321},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44825148582458496},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4482076168060303},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3876335024833679},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.17082074284553528},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.15401294827461243}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6806454658508301},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.504438042640686},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4706408679485321},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44825148582458496},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4482076168060303},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3876335024833679},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.17082074284553528},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.15401294827461243}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm62325.2024.10822432","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm62325.2024.10822432","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/2","score":0.47999998927116394,"display_name":"Zero hunger"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1976848573","https://openalex.org/W2112364185","https://openalex.org/W2173732482","https://openalex.org/W2889019390","https://openalex.org/W3118845805","https://openalex.org/W4236865533","https://openalex.org/W6632938290","https://openalex.org/W6636510571","https://openalex.org/W6640596903","https://openalex.org/W6656840875","https://openalex.org/W6663419805","https://openalex.org/W6674960978","https://openalex.org/W6679542025","https://openalex.org/W6681765588","https://openalex.org/W6715686946","https://openalex.org/W6755865722","https://openalex.org/W6761256464","https://openalex.org/W6766574342","https://openalex.org/W6766620035","https://openalex.org/W6767676818","https://openalex.org/W6768434673","https://openalex.org/W6769376386","https://openalex.org/W6774695153","https://openalex.org/W6778025009","https://openalex.org/W6784443386","https://openalex.org/W6785944886","https://openalex.org/W6786915954","https://openalex.org/W6793118399","https://openalex.org/W6798407072","https://openalex.org/W6842933097","https://openalex.org/W6843109041","https://openalex.org/W6846811755","https://openalex.org/W6851447165","https://openalex.org/W6861119088","https://openalex.org/W6874177246"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W3188962172","https://openalex.org/W2772917594","https://openalex.org/W4312825515","https://openalex.org/W4306742369","https://openalex.org/W4303457083","https://openalex.org/W2131146434","https://openalex.org/W2951359407","https://openalex.org/W4376623224","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Large":[0],"tree-of-life":[1],"(ToL)":[2],"scale":[3],"databases":[4],"of":[5,25,39,49,71,88,144],"microbial":[6,145],"genomes":[7],"are":[8],"powerful":[9,134],"resources":[10],"for":[11,62,90,137],"exploring":[12],"genome":[13,29],"structure":[14],"and":[15,84,93,142],"function":[16,52,89,123],"from":[17],"a":[18,33,36,60,64,108,133],"phylogenomic":[19],"context.":[20],"Despite":[21],"the":[22,47,76,86,116,129],"growing":[23],"availability":[24],"genomic":[26,66,72],"data,":[27],"large-scale":[28],"annotation":[30],"is":[31],"still":[32],"challenge,":[34],"with":[35,115],"considerable":[37],"fraction":[38],"genes":[40,83],"remaining":[41],"as":[42,59,95,132],"unannotated.":[43],"Here,":[44],"to":[45,110,113],"expand":[46],"capabilities":[48],"database-wide":[50],"gene":[51,122,146],"prediction,":[53],"we":[54,96,106],"used":[55],"our":[56,126],"AnnoTree":[57,77,117],"platform":[58],"corpus":[61],"training":[63,135],"Word2vec-based":[65],"language":[67],"model":[68],"(gLM).":[69],"Machine-learning":[70],"grammar":[73],"patterns":[74],"across":[75],"database":[78,131,136],"revealed":[79],"functional":[80],"associations":[81],"between":[82],"enabled":[85],"inference":[87],"hypothetical":[91],"proteins":[92],"domains,":[94],"demonstrated":[97],"by":[98],"predicting":[99],"novel":[100],"type":[101],"VI":[102],"secretion":[103],"proteins.":[104],"Finally,":[105],"implemented":[107],"web-server":[109],"allow":[111],"users":[112],"interact":[114],"Word2vec":[118],"model,":[119],"thus":[120],"facilitating":[121],"prediction.":[124],"Ultimately,":[125],"work":[127],"highlighted":[128],"GTDB/AnnoTree":[130],"gLMs":[138],"focused":[139],"on":[140],"prediction":[141],"discovery":[143],"functions.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}
