{"id":"https://openalex.org/W4366563389","doi":"https://doi.org/10.1093/bioinformatics/btae075","title":"GeneGPT: augmenting large language models with domain tools for improved access to biomedical information","display_name":"GeneGPT: augmenting large language models with domain tools for improved access to biomedical information","publication_year":2024,"publication_date":"2024-02-01","ids":{"openalex":"https://openalex.org/W4366563389","doi":"https://doi.org/10.1093/bioinformatics/btae075","pmid":"https://pubmed.ncbi.nlm.nih.gov/37131884"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btae075","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae075","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btae075/56659521/btae075.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":["arxiv","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/btae075/56659521/btae075.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100611571","display_name":"Qiao Jin","orcid":"https://orcid.org/0000-0002-1268-7239"},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiao Jin","raw_affiliation_strings":["National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health , Bethesda, MD 20894, United States"],"raw_orcid":"https://orcid.org/0000-0002-1268-7239","affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health , Bethesda, MD 20894, United States","institution_ids":["https://openalex.org/I4210109390","https://openalex.org/I1299303238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101623103","display_name":"Yifan Yang","orcid":"https://orcid.org/0000-0003-4414-9176"},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Yang","raw_affiliation_strings":["National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health , Bethesda, MD 20894, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health , Bethesda, MD 20894, United States","institution_ids":["https://openalex.org/I4210109390","https://openalex.org/I1299303238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042874172","display_name":"Qingyu Chen","orcid":"https://orcid.org/0000-0002-6036-1516"},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qingyu Chen","raw_affiliation_strings":["National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health , Bethesda, MD 20894, United States"],"raw_orcid":"https://orcid.org/0000-0002-6036-1516","affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health , Bethesda, MD 20894, United States","institution_ids":["https://openalex.org/I4210109390","https://openalex.org/I1299303238"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083081872","display_name":"Zhiyong Lu","orcid":"https://orcid.org/0000-0001-9998-916X"},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhiyong Lu","raw_affiliation_strings":["National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health , Bethesda, MD 20894, United States"],"raw_orcid":"https://orcid.org/0000-0001-9998-916X","affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health , Bethesda, MD 20894, United States","institution_ids":["https://openalex.org/I4210109390","https://openalex.org/I1299303238"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5083081872"],"corresponding_institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4210109390"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":13.6102,"has_fulltext":true,"cited_by_count":157,"citation_normalized_percentile":{"value":0.99190335,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"40","issue":"2","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.5239999890327454,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.5239999890327454,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11642","display_name":"Genomics and Rare Diseases","score":0.18690000474452972,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T10028","display_name":"Topic Modeling","score":0.07199999690055847,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.782776951789856},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6335194110870361},{"id":"https://openalex.org/keywords/domain-specific-language","display_name":"Domain-specific language","score":0.45208752155303955},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4336296319961548},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.36632007360458374},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.33686792850494385},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06627050042152405}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.782776951789856},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6335194110870361},{"id":"https://openalex.org/C135257023","wikidata":"https://www.wikidata.org/wiki/Q691358","display_name":"Domain-specific language","level":2,"score":0.45208752155303955},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4336296319961548},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.36632007360458374},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.33686792850494385},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06627050042152405},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1093/bioinformatics/btae075","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae075","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btae075/56659521/btae075.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:37131884","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37131884","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":"ArXiv","raw_type":null},{"id":"pmid:38341654","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38341654","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:arXiv.org:2304.09667","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.09667","pdf_url":"https://arxiv.org/pdf/2304.09667","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},{"id":"pmh:oai:pubmedcentral.nih.gov:10153281","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10153281","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10153281/pdf/nihpp-2304.09667v3.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":"ArXiv","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:10904143","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10904143","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10904143/pdf/btae075.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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btae075","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae075","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btae075/56659521/btae075.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4366563389.pdf"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1509844421","https://openalex.org/W2055043387","https://openalex.org/W2067964678","https://openalex.org/W2096525273","https://openalex.org/W2132781587","https://openalex.org/W3027879771","https://openalex.org/W3198080531","https://openalex.org/W4239634997","https://openalex.org/W4292779060","https://openalex.org/W4297253404","https://openalex.org/W4309674289","https://openalex.org/W4324027515","https://openalex.org/W4378783233","https://openalex.org/W4381587418","https://openalex.org/W4384071683","https://openalex.org/W4392359953","https://openalex.org/W6777615688","https://openalex.org/W6778883912","https://openalex.org/W6851355582"],"related_works":["https://openalex.org/W2161550557","https://openalex.org/W2057033141","https://openalex.org/W2148282566","https://openalex.org/W4387796988","https://openalex.org/W2065949834","https://openalex.org/W4252103056","https://openalex.org/W2917823318","https://openalex.org/W2917572814","https://openalex.org/W4242858628","https://openalex.org/W2979406678"],"abstract_inverted_index":{"MOTIVATION:":[0],"While":[1],"large":[2],"language":[3],"models":[4],"(LLMs)":[5],"have":[6,152],"been":[7],"successfully":[8],"applied":[9],"to":[10,35,50,71,169],"various":[11],"tasks,":[12,197],"they":[13],"still":[14],"face":[15],"challenges":[16],"with":[17,21,76,111],"hallucinations.":[18],"Augmenting":[19],"LLMs":[20,49,120,128],"domain-specific":[22],"tools":[23],"such":[24,121,129],"as":[25,122,130,136,138],"database":[26],"utilities":[27],"can":[28,89,167],"facilitate":[29],"easier":[30],"and":[31,83,91,133,141,156,175,210],"more":[32,158],"precise":[33],"access":[34],"specialized":[36],"knowledge.":[37],"In":[38],"this":[39,186],"article,":[40],"we":[41,68],"present":[42],"GeneGPT,":[43],"a":[44,181],"novel":[45,182],"method":[46],"for":[47,59,63,162,201],"teaching":[48],"use":[51],"the":[52,56,73,108,123],"Web":[53,78],"APIs":[54,79],"of":[55,115,172,191],"National":[57],"Center":[58],"Biotechnology":[60],"Information":[61],"(NCBI)":[62],"answering":[64],"genomics":[65],"questions.":[66],"Specifically,":[67],"prompt":[69],"Codex":[70],"solve":[72],"GeneTuring":[74,109],"tests":[75],"NCBI":[77],"by":[80],"in-context":[81,163],"learning":[82],"an":[84,112],"augmented":[85],"decoding":[86],"algorithm":[87],"that":[88,99],"detect":[90],"execute":[92],"API":[93,150,173],"calls.":[94],"RESULTS:":[95],"Experimental":[96],"results":[97],"show":[98],"GeneGPT":[100,166,208],"achieves":[101],"state-of-the-art":[102],"performance":[103],"on":[104],"eight":[105],"tasks":[106],"in":[107,179,185,195],"benchmark":[110],"average":[113],"score":[114],"0.83,":[116],"largely":[117],"surpassing":[118],"retrieval-augmented":[119],"new":[124],"Bing":[125],"(0.44),":[126],"biomedical":[127],"BioMedLM":[131],"(0.08)":[132],"BioGPT":[134],"(0.04),":[135],"well":[137],"GPT-3":[139],"(0.16)":[140],"ChatGPT":[142],"(0.12).":[143],"Our":[144],"further":[145],"analyses":[146],"suggest":[147],"that:":[148],"First,":[149],"demonstrations":[151],"good":[153],"cross-task":[154],"generalizability":[155],"are":[157,193,212],"useful":[159],"than":[160],"documentations":[161],"learning;":[164],"second,":[165],"generalize":[168],"longer":[170],"chains":[171],"calls":[174],"answer":[176],"multi-hop":[177],"questions":[178],"GeneHop,":[180],"dataset":[183],"introduced":[184],"work;":[187],"finally,":[188],"different":[189,196],"types":[190],"errors":[192],"enriched":[194],"providing":[198],"valuable":[199],"insights":[200],"future":[202],"improvements.":[203],"AVAILABILITY":[204],"AND":[205],"IMPLEMENTATION:":[206],"The":[207],"code":[209],"data":[211],"publicly":[213],"available":[214],"at":[215],"https://github.com/ncbi/GeneGPT.":[216]},"counts_by_year":[{"year":2026,"cited_by_count":29},{"year":2025,"cited_by_count":68},{"year":2024,"cited_by_count":47},{"year":2023,"cited_by_count":13}],"updated_date":"2026-07-11T18:08:03.149640","created_date":"2023-04-22T00:00:00"}
