{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T08:59:18Z","timestamp":1778057958357,"version":"3.51.4"},"reference-count":13,"publisher":"Oxford University Press (OUP)","issue":"11","license":[{"start":{"date-parts":[[2023,11,9]],"date-time":"2023-11-09T00:00:00Z","timestamp":1699488000000},"content-version":"vor","delay-in-days":8,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100004807","name":"DFG","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004807","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100002014","name":"CRC","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100002014","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Helmholtz Einstein International Berlin Research School in Data Science"},{"name":"e:Med program of the German Ministry of Education and Research","award":["031L0189D"],"award-info":[{"award-number":["031L0189D"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,11,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Summary<\/jats:title>\n                  <jats:p>Relation extraction (RE) from large text collections is an important tool for database curation, pathway reconstruction, or functional omics data analysis. In practice, RE often is part of a complex data analysis pipeline requiring specific adaptations like restricting the types of relations or the set of proteins to be considered. However, current systems are either non-programmable web sites or research code with fixed functionality. We present PEDL+, a user-friendly tool for extracting protein\u2013protein and protein\u2013chemical associations from PubMed articles. PEDL+ combines state-of-the-art NLP technology with adaptable ranking and filtering options and can easily be integrated into analysis pipelines. We evaluated PEDL+ in two pathway curation projects and found that 59% to 80% of its extractions were helpful.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>PEDL+ is freely available at https:\/\/github.com\/leonweber\/pedl.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btad603","type":"journal-article","created":{"date-parts":[[2023,11,11]],"date-time":"2023-11-11T08:31:58Z","timestamp":1699691518000},"source":"Crossref","is-referenced-by-count":5,"title":["PEDL+: protein-centered relation extraction from PubMed at your fingertip"],"prefix":"10.1093","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2499-472X","authenticated-orcid":false,"given":"Leon","family":"Weber","sequence":"first","affiliation":[{"name":"Center for Information and Language Processing, Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen , Geschwister-Scholl-Platz 1 , M\u00fcnchen 80539, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fabio","family":"Barth","sequence":"additional","affiliation":[{"name":"Computer Science Department, Humboldt-Universit\u00e4t zu Berlin , Unter den Linden 6 , Berlin 10099, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leonie","family":"Lorenz","sequence":"additional","affiliation":[{"name":"Pathogen Informatics and Modelling, EMBL-EBI , Hinxton, Cambridgeshire CB10 1SD, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fabian","family":"Konrath","sequence":"additional","affiliation":[{"name":"Mathematical Modelling of Cellular Processes, Max Delbr\u00fcck Center for Molecular Medicine , Robert-R\u00f6ssle-Str. 10 , Berlin 13125, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kirsten","family":"Huska","sequence":"additional","affiliation":[{"name":"Mathematical Modelling of Cellular Processes, Max Delbr\u00fcck Center for Molecular Medicine , Robert-R\u00f6ssle-Str. 10 , Berlin 13125, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jana","family":"Wolf","sequence":"additional","affiliation":[{"name":"Mathematical Modelling of Cellular Processes, Max Delbr\u00fcck Center for Molecular Medicine , Robert-R\u00f6ssle-Str. 10 , Berlin 13125, Germany"},{"name":"Department of Mathematics and Computer Science, Free University Berlin , Berlin, 14195, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ulf","family":"Leser","sequence":"additional","affiliation":[{"name":"Computer Science Department, Humboldt-Universit\u00e4t zu Berlin , Unter den Linden 6 , Berlin 10099, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2023,11,9]]},"reference":[{"key":"2023112107154467100_btad603-B1","first-page":"3613","author":"Beltagy","year":"2019"},{"key":"2023112107154467100_btad603-B2","first-page":"3533","article-title":"PMC text mining subset in BioC: about three million full-text articles and growing","volume":"35","author":"Comeau","year":"2019","journal-title":"Bioinformatics (Oxford, England)"},{"key":"2023112107154467100_btad603-B3","first-page":"4171","author":"Devlin","year":"2019"},{"key":"2023112107154467100_btad603-B4","doi-asserted-by":"crossref","first-page":"954","DOI":"10.15252\/msb.20177651","article-title":"From word models to executable models of signaling networks using automated assembly","volume":"13","author":"Gyori","year":"2017","journal-title":"Mol Syst Biol"},{"key":"2023112107154467100_btad603-B5","doi-asserted-by":"crossref","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","article-title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","volume":"36","author":"Lee","year":"2020","journal-title":"Bioinformatics"},{"key":"2023112107154467100_btad603-B6","author":"Miranda","year":"2021"},{"key":"2023112107154467100_btad603-B7","doi-asserted-by":"crossref","first-page":"1655","DOI":"10.3390\/biomedicines9111655","article-title":"Patient-specific modeling of diffuse large B-cell lymphoma","volume":"9","author":"Thobe","year":"2021","journal-title":"Biomedicines"},{"key":"2023112107154467100_btad603-B8","doi-asserted-by":"crossref","first-page":"e55814","DOI":"10.1371\/journal.pone.0055814","article-title":"Large-scale event extraction from literature with multi-level gene normalization","volume":"8","author":"Van Landeghem","year":"2013","journal-title":"PLoS One"},{"key":"2023112107154467100_btad603-B9","doi-asserted-by":"crossref","first-page":"i490","DOI":"10.1093\/bioinformatics\/btaa430","article-title":"PEDL: extracting protein\u2013protein associations using deep language models and distant supervision","volume":"36","author":"Weber","year":"2020","journal-title":"Bioinformatics"},{"key":"2023112107154467100_btad603-B10","first-page":"4","author":"Weber","year":"2021"},{"key":"2023112107154467100_btad603-B11","doi-asserted-by":"crossref","first-page":"baac098","DOI":"10.1093\/database\/baac098","article-title":"Chemical\u2013protein relation extraction with ensembles of carefully tuned pretrained language models","volume":"2022","author":"Weber","year":"2022","journal-title":"Database"},{"key":"2023112107154467100_btad603-B12","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":"2023112107154467100_btad603-B13","first-page":"8003","author":"Yasunaga","year":"2022"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btad603\/53180165\/btad603.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/11\/btad603\/53604239\/btad603.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/11\/btad603\/53604239\/btad603.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T14:48:08Z","timestamp":1700578088000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btad603\/7394936"}},"subtitle":[],"editor":[{"given":"Zhiyong","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2023,11,1]]},"references-count":13,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2023,11,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btad603","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,11,1]]},"published":{"date-parts":[[2023,11,1]]},"article-number":"btad603"}}