{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T18:54:03Z","timestamp":1773687243812,"version":"3.50.1"},"reference-count":18,"publisher":"Oxford University Press (OUP)","issue":"10","funder":[{"DOI":"10.13039\/100000092","name":"National Library of Medicine","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000092","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["DUT23RC(3)014"],"award-info":[{"award-number":["DUT23RC(3)014"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Gene name normalization is an important yet highly complex task in biomedical text mining research, as gene names can be highly ambiguous and may refer to different genes in different species or share similar names with other bioconcepts. This poses a challenge for accurately identifying and linking gene mentions to their corresponding entries in databases such as NCBI Gene or UniProt. While there has been a body of literature on the gene normalization task, few have addressed all of these challenges or make their solutions publicly available to the scientific community.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>Building on the success of GNormPlus, we have created GNorm2: a more advanced tool with optimized functions and improved performance. GNorm2 integrates a range of advanced deep learning-based methods, resulting in the highest levels of accuracy and efficiency for gene recognition and normalization to date. Our tool is freely available for download.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>https:\/\/github.com\/ncbi\/GNorm2.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btad599","type":"journal-article","created":{"date-parts":[[2023,10,25]],"date-time":"2023-10-25T19:02:24Z","timestamp":1698260544000},"source":"Crossref","is-referenced-by-count":19,"title":["GNorm2: an improved gene name recognition and normalization system"],"prefix":"10.1093","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5094-7321","authenticated-orcid":false,"given":"Chih-Hsuan","family":"Wei","sequence":"first","affiliation":[{"name":"National Center for Biotechnology Information (NCBI), National Library of Medicine (NLM), National Institutes of Health (NIH) , Bethesda, MD 20894, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5141-0259","authenticated-orcid":false,"given":"Ling","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Dalian University of Technology , Dalian 116024, China"}]},{"given":"Rezarta","family":"Islamaj","sequence":"additional","affiliation":[{"name":"National Center for Biotechnology Information (NCBI), National Library of Medicine (NLM), National Institutes of Health (NIH) , Bethesda, MD 20894, United States"}]},{"given":"Po-Ting","family":"Lai","sequence":"additional","affiliation":[{"name":"National Center for Biotechnology Information (NCBI), National Library of Medicine (NLM), National Institutes of Health (NIH) , Bethesda, MD 20894, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9998-916X","authenticated-orcid":false,"given":"Zhiyong","family":"Lu","sequence":"additional","affiliation":[{"name":"National Center for Biotechnology Information (NCBI), National Library of Medicine (NLM), National Institutes of Health (NIH) , Bethesda, MD 20894, United States"}]}],"member":"286","published-online":{"date-parts":[[2023,10,25]]},"reference":[{"key":"2023102913434839000_btad599-B1","doi-asserted-by":"crossref","first-page":"D36","DOI":"10.1093\/nar\/gku1055","article-title":"Gene: a gene-centered information resource at NCBI","volume":"43","author":"Brown","year":"2015","journal-title":"Nucleic Acids Res"},{"key":"2023102913434839000_btad599-B2","doi-asserted-by":"crossref","first-page":"D506","DOI":"10.1093\/nar\/gky1049","article-title":"UniProt: a worldwide hub of protein knowledge","volume":"47","author":"Consortium","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2023102913434839000_btad599-B3","first-page":"4171","author":"Devlin"},{"key":"2023102913434839000_btad599-B4","author":"Fang","year":"2023"},{"key":"2023102913434839000_btad599-B5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3458754","article-title":"Domain-specific language model pretraining for biomedical natural language processing","volume":"3","author":"Gu","year":"2022","journal-title":"ACM Trans Comput Healthcare"},{"key":"2023102913434839000_btad599-B6","doi-asserted-by":"crossref","first-page":"2769","DOI":"10.1093\/bioinformatics\/btr455","article-title":"The GNAT library for local and remote gene mention normalization","volume":"27","author":"Hakenberg","year":"2011","journal-title":"Bioinformatics"},{"key":"2023102913434839000_btad599-B7","doi-asserted-by":"crossref","first-page":"1032","DOI":"10.1093\/bioinformatics\/btr042","article-title":"GeneTUKit: a software for document-level gene normalization","volume":"27","author":"Huang","year":"2011","journal-title":"Bioinformatics"},{"key":"2023102913434839000_btad599-B8","doi-asserted-by":"crossref","first-page":"bap018","DOI":"10.1093\/database\/bap018","article-title":"Understanding PubMed\u00ae user search behavior through log analysis","volume":"2009","author":"Islamaj Dogan","year":"2009","journal-title":"Database (Oxford)"},{"key":"2023102913434839000_btad599-B9","doi-asserted-by":"crossref","first-page":"103779","DOI":"10.1016\/j.jbi.2021.103779","article-title":"NLM-Gene, a richly annotated gold standard dataset for gene entities that addresses ambiguity and multi-species gene recognition","volume":"118","author":"Islamaj","year":"2021","journal-title":"J Biomed Inf"},{"key":"2023102913434839000_btad599-B10","first-page":"282","author":"Lafferty"},{"key":"2023102913434839000_btad599-B11","first-page":"baac090","article-title":"Assigning species information to corresponding genes by a sequence labeling framework","volume":"2022","author":"Luo","year":"2022","journal-title":"Database J Biol Databases Curation"},{"key":"2023102913434839000_btad599-B12","doi-asserted-by":"crossref","first-page":"D23","DOI":"10.1093\/nar\/gky1069","article-title":"Database resources of the national center for biotechnology information","volume":"47","author":"Sayers","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2023102913434839000_btad599-B13","doi-asserted-by":"crossref","first-page":"402","DOI":"10.1186\/1471-2105-9-402","article-title":"Abbreviation definition identification based on automatic precision estimates","volume":"9","author":"Sohn","year":"2008","journal-title":"BMC Bioinformatics"},{"key":"2023102913434839000_btad599-B14","doi-asserted-by":"crossref","first-page":"4837","DOI":"10.1093\/bioinformatics\/btac598","article-title":"BERN2: an advanced neural biomedical named entity recognition and normalization tool","volume":"38","author":"Sung","year":"2022","journal-title":"Bioinformatics"},{"key":"2023102913434839000_btad599-B15","doi-asserted-by":"crossref","first-page":"2792","DOI":"10.1093\/bioinformatics\/btab042","article-title":"HunFlair: an easy-to-use tool for state-of-the-art biomedical named entity recognition","volume":"37","author":"Weber","year":"2021","journal-title":"Bioinformatics"},{"key":"2023102913434839000_btad599-B16","doi-asserted-by":"crossref","first-page":"S5","DOI":"10.1186\/1471-2105-12-S8-S5","article-title":"Cross-species gene normalization by species inference","volume":"12","author":"Wei","year":"2011","journal-title":"BMC Bioinformatics"},{"key":"2023102913434839000_btad599-B17","doi-asserted-by":"crossref","first-page":"W587","DOI":"10.1093\/nar\/gkz389","article-title":"PubTator Central: automated concept annotation for biomedical full text articles","volume":"47","author":"Wei","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2023102913434839000_btad599-B18","doi-asserted-by":"crossref","first-page":"918710","DOI":"10.1155\/2015\/918710","article-title":"GNormPlus: an integrative approach for tagging genes, gene families, and protein domains","volume":"2015","author":"Wei","year":"2015","journal-title":"Biomed Res Int"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btad599\/52543835\/btad599.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/10\/btad599\/52673505\/btad599.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/10\/btad599\/52673505\/btad599.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,29]],"date-time":"2023-10-29T14:10:02Z","timestamp":1698588602000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btad599\/7329714"}},"subtitle":[],"editor":[{"given":"Jonathan","family":"Wren","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":18,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2023,10,3]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btad599","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,10,1]]},"published":{"date-parts":[[2023,10,1]]},"article-number":"btad599"}}