{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T16:01:10Z","timestamp":1785254470223,"version":"3.55.0"},"reference-count":51,"publisher":"Oxford University Press (OUP)","license":[{"start":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T00:00:00Z","timestamp":1785196800000},"content-version":"vor","delay-in-days":208,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001807","name":"FAPESP","doi-asserted-by":"publisher","award":["2025\/23708-6"],"award-info":[{"award-number":["2025\/23708-6"]}],"id":[{"id":"10.13039\/501100001807","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001807","name":"FAPESP","doi-asserted-by":"publisher","award":["2023\/02691-2"],"award-info":[{"award-number":["2023\/02691-2"]}],"id":[{"id":"10.13039\/501100001807","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001807","name":"FAPESP","doi-asserted-by":"publisher","award":["2020\/08615-8"],"award-info":[{"award-number":["2020\/08615-8"]}],"id":[{"id":"10.13039\/501100001807","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Motivation: Protein exosites are secondary binding sites that recruit macromolecular partners and control molecular recognition across protein families. Despite their therapeutic potential demonstrated by approved drugs such as bivalirudin, systematic characterization remains limited by fragmented literature and inconsistent reporting. Existing databases lack exosite-specific curation, residue-level contact mapping, and structure\u2013function integration. Results: We present ExositeDB, a curated database of protein exosites built through AI-assisted curation combining large language model extraction with expert validation. Our three-pass pipeline acquires papers from multiple databases, extracts data using GPT-4o with confidence scoring, validates findings against PDB structures, and links all claims to source text. The current release contains 525 expert-validated exosite records spanning 280 unique proteins, each annotated with residue-level positions, partner types, and functional roles. Quality is maintained through multi-tier confidence scoring integrating experimental methodology (35% weight), structural validation (25%), literature consistency (20%), and terminology precision (20%). The database follows FAIR principles through structured metadata, versioned releases, persistent identifiers, and an open REST API. Structural coverage includes 395 unique PDB structures supporting structure\u2013function validation. ExositeDB provides training data for AI-driven exosite prediction, supports rational design of selective modulators, and enables analysis of exosite-mediated regulatory networks.<\/jats:p>","DOI":"10.1093\/database\/baag031","type":"journal-article","created":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T11:52:18Z","timestamp":1784807538000},"source":"Crossref","is-referenced-by-count":0,"title":["STING-ExositeDB: An AI-assisted curated database of protein exosites for drug discovery"],"prefix":"10.1093","volume":"2026","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9750-5034","authenticated-orcid":false,"given":"Folorunsho Bright","family":"Omage","sequence":"first","affiliation":[{"name":"Computational Biology Research Group, Embrapa Digital Agriculture , Av. Andr\u00e9 Tosello, 209, Bar\u00e3o Geraldo, CEP 13083-886 Campinas, SP ,","place":["Brazil"]},{"name":"Biological Chemistry Laboratory, Department of Organic Chemistry, Institute of Chemistry, University of Campinas (UNICAMP) , Rua Josu\u00e9 de Castro, s\/n, Bar\u00e3o Geraldo, CEP 13083-861 Campinas, SP ,","place":["Brazil"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3763-1071","authenticated-orcid":false,"given":"Ivan","family":"Mazoni","sequence":"additional","affiliation":[{"name":"Computational Biology Research Group, Embrapa Digital Agriculture , Av. Andr\u00e9 Tosello, 209, Bar\u00e3o Geraldo, CEP 13083-886 Campinas, SP ,","place":["Brazil"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"In\u00e1cio Henrique","family":"Yano","sequence":"additional","affiliation":[{"name":"Computational Biology Research Group, Embrapa Digital Agriculture , Av. Andr\u00e9 Tosello, 209, Bar\u00e3o Geraldo, CEP 13083-886 Campinas, SP ,","place":["Brazil"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4982-0416","authenticated-orcid":false,"given":"Goran","family":"Neshich","sequence":"additional","affiliation":[{"name":"Computational Biology Research Group, Embrapa Digital Agriculture , Av. Andr\u00e9 Tosello, 209, Bar\u00e3o Geraldo, CEP 13083-886 Campinas, SP ,","place":["Brazil"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,7,28]]},"reference":[{"key":"2026072811295781800_bib1","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1016\/j.tibtech.2011.06.001","article-title":"Allostery in trypsin-like proteases suggests new therapeutic strategies","volume":"29","author":"Gohara","year":"2011","journal-title":"Trends Biotechnol"},{"key":"2026072811295781800_bib2","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1016\/j.cell.2013.03.034","article-title":"Allostery in disease and in drug discovery","volume":"153","author":"Nussinov","year":"2013","journal-title":"Cell"},{"key":"2026072811295781800_bib3","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1016\/S1367-5931(02)00341-1","article-title":"Protein exosites: A new frontier for drug discovery","volume":"6","author":"Carlson","year":"2002","journal-title":"Curr Opin Chem Biol"},{"key":"2026072811295781800_bib4","first-page":"648","article-title":"Substrate recognition by thrombin","volume":"15","author":"Huntington","year":"2005","journal-title":"Curr Opin Struct Biol"},{"key":"2026072811295781800_bib5","first-page":"458","article-title":"Allostery and cooperativity revisited","volume":"32","author":"Changeux","year":"2007","journal-title":"Trends Biochem Sci"},{"key":"2026072811295781800_bib6","first-page":"809","article-title":"Kinase regulation by pseudokinases","volume":"177","author":"Reiterer","year":"2019","journal-title":"Cell"},{"key":"2026072811295781800_bib7","first-page":"83","article-title":"Allosteric regulation of protein function","volume":"43","author":"Motlagh","year":"2014","journal-title":"Annu Rev Biophys"},{"key":"2026072811295781800_bib8","doi-asserted-by":"publisher","first-page":"6351","DOI":"10.1021\/acs.chemrev.5b00590","article-title":"Protein allostery and conformational dynamics","volume":"116","author":"Tsai","year":"2016","journal-title":"Chem Rev"},{"key":"2026072811295781800_bib9","first-page":"613","article-title":"Thrombin exosite interactions","volume":"4","author":"Bode","year":"1993","journal-title":"Blood Coagul Fibrinolysis"},{"key":"2026072811295781800_bib10","first-page":"113","article-title":"Molecular recognition in thrombin","volume":"21","author":"Stubbs","year":"1995","journal-title":"Semin Thromb Hemost"},{"key":"2026072811295781800_bib11","first-page":"5747","article-title":"Exosite-mediated regulation of factor viia by tissue factor pathway inhibitor","volume":"36","author":"Wood","year":"1997","journal-title":"Biochemistry"},{"key":"2026072811295781800_bib12","first-page":"9188","article-title":"Allosteric mechanisms in ace regulation by c-domain selective inhibitors","volume":"47","author":"Rushworth","year":"2008","journal-title":"Biochemistry"},{"key":"2026072811295781800_bib13","doi-asserted-by":"publisher","first-page":"104662","DOI":"10.1016\/j.drudis.2026.104662","article-title":"Protein exosites as drug targets: from structural topology to therapeutic modality","volume":"31","author":"Omage","year":"2026","journal-title":"Drug Discov Today"},{"key":"2026072811295781800_bib14","first-page":"2468","article-title":"Allosteric drug discovery: From theory to practice","volume":"39","author":"Lu","year":"2019","journal-title":"Med Res Rev"},{"key":"2026072811295781800_bib15","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1146\/annurev-pharmtox-010611-134525","article-title":"Drugs for allosteric sites on receptors","volume":"54","author":"Wenthur","year":"2014","journal-title":"Annu Rev Pharmacol Toxicol"},{"key":"2026072811295781800_bib16","first-page":"10","article-title":"Nu172 aptamer in acute coronary syndrome","volume":"30","author":"Becker","year":"2010","journal-title":"J Thromb Thrombolysis"},{"key":"2026072811295781800_bib17","first-page":"2081","article-title":"Phase ii trial of nu172","volume":"121","author":"Cohen","year":"2010","journal-title":"Circulation"},{"key":"2026072811295781800_bib18","doi-asserted-by":"crossref","first-page":"2361","DOI":"10.1002\/j.1460-2075.1990.tb07410.x","article-title":"Structure of the hirudin-thrombin complex","volume":"9","author":"Grutter","year":"1990","journal-title":"EMBO J"},{"key":"2026072811295781800_bib19","first-page":"4403","article-title":"Crystal structure of bivalirudin-thrombin complex","volume":"278","author":"Huntington","year":"2003","journal-title":"J Biol Chem"},{"key":"2026072811295781800_bib20","first-page":"1381","article-title":"Lepirudin: A review of its pharmacology and clinical use","volume":"5","author":"Warkentin","year":"2004","journal-title":"Expert Pharmacother"},{"key":"2026072811295781800_bib21","first-page":"1484","article-title":"Desirudin: A comprehensive review","volume":"23","author":"Weitz","year":"2002","journal-title":"Eur Heart J"},{"key":"2026072811295781800_bib22","doi-asserted-by":"crossref","first-page":"706","DOI":"10.1016\/j.sbi.2004.10.009","article-title":"Searching for new allosteric sites in enzymes","volume":"14","author":"Hardy","year":"2004","journal-title":"Curr Opin Struct Biol"},{"key":"2026072811295781800_bib23","doi-asserted-by":"crossref","first-page":"4501","DOI":"10.1021\/cr000033x","article-title":"Serine protease mechanism and specificity","volume":"102","author":"Hedstrom","year":"2002","journal-title":"Chem Rev"},{"key":"2026072811295781800_bib24","doi-asserted-by":"crossref","first-page":"1220","DOI":"10.1007\/s00018-008-7565-9","article-title":"Serine peptidases: classification, structure and function","volume":"65","author":"Page","year":"2008","journal-title":"Cell Mol Life Sci"},{"key":"2026072811295781800_bib25","first-page":"884","article-title":"Semi-automated data curation from biomedical literature","volume":"2022","author":"Rahman","year":"2023","journal-title":"AMIA Annu Symp Proc"},{"key":"2026072811295781800_bib26","doi-asserted-by":"publisher","first-page":"bbad493","DOI":"10.1093\/bib\/bbad493","article-title":"Opportunities and challenges for chatgpt and large language models in biomedicine and health","volume":"25","author":"Tian","year":"2024","journal-title":"Brief Bioinform"},{"key":"2026072811295781800_bib27","first-page":"1284","article-title":"Gpt-4 for biomedical knowledge extraction","volume":"39","author":"Wei","year":"2023","journal-title":"Bioinformatics"},{"key":"2026072811295781800_bib28","doi-asserted-by":"crossref","first-page":"160018","DOI":"10.1038\/sdata.2016.18","article-title":"The FAIR Guiding Principles for scientific data management and stewardship","volume":"3","author":"Wilkinson","year":"2016","journal-title":"Sci Data"},{"key":"2026072811295781800_bib29","first-page":"50","article-title":"Evaluation frameworks for automated curation","volume":"10","author":"Kim","year":"2018","journal-title":"J Cheminform"},{"key":"2026072811295781800_bib30","doi-asserted-by":"crossref","first-page":"D520","DOI":"10.1093\/nar\/gky949","article-title":"Protein data bank: the single global archive for 3d macromolecular structure data","volume":"47","author":"Burley","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2026072811295781800_bib31","doi-asserted-by":"crossref","first-page":"D1045","DOI":"10.1093\/nar\/gkv1072","article-title":"Bindingdb in 2015: A public database for medicinal chemistry","volume":"44","author":"Gilson","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2026072811295781800_bib32","doi-asserted-by":"crossref","first-page":"D480","DOI":"10.1093\/nar\/gkaa1100","article-title":"Uniprot: the universal protein knowledgebase in 2021","volume":"49","author":"Consortium","year":"2021","journal-title":"Nucleic Acids Res"},{"key":"2026072811295781800_bib33","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1038\/nmeth.2340","article-title":"A large-scale evaluation of computational protein function prediction","volume":"10","author":"Radivojac","year":"2013","journal-title":"Nat Methods"},{"key":"2026072811295781800_bib34","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.sbi.2017.10.002","article-title":"Computational prediction of allosteric sites","volume":"50","author":"Greener","year":"2018","journal-title":"Curr Opin Struct Biol"},{"key":"2026072811295781800_bib35","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1016\/j.sbi.2019.12.016","article-title":"Machine learning approaches for analyzing and enhancing molecular dynamics simulations","volume":"61","author":"Wang","year":"2020","journal-title":"Curr Opin Struct Biol"},{"key":"2026072811295781800_bib36","doi-asserted-by":"publisher","first-page":"100166","DOI":"10.1016\/j.ailsci.2026.100166","article-title":"Protein family membership governs exosite predictability across the structural proteome","volume":"9","author":"Omage","year":"2026","journal-title":"Artif Intell Life Sci"},{"key":"2026072811295781800_bib37","article-title":"Fastapi: Modern, fast (high-performance), web framework for building apis with python 3.8+","author":"Ram\u00edrez","year":"2024"},{"key":"2026072811295781800_bib38","article-title":"React: A javascript library for building user interfaces","author":"Meta Platforms","year":"2024"},{"key":"2026072811295781800_bib39","doi-asserted-by":"publisher","first-page":"3755","DOI":"10.1093\/bioinformatics\/bty419","article-title":"NGL viewer: web-based molecular graphics for large complexes","volume":"34","author":"Rose","year":"2018","journal-title":"Bioinformatics"},{"key":"2026072811295781800_bib40","article-title":"E-utilities quick start","volume-title":"Entrez Programming Utilities Help","author":"Sayers","year":"2018"},{"key":"2026072811295781800_bib41","doi-asserted-by":"publisher","first-page":"D609","DOI":"10.1093\/nar\/gkae1010","article-title":"Uniprot: the universal protein knowledgebase in 2025","volume":"53","author":"UniProt Consortium","year":"2025","journal-title":"Nucleic Acids Res"},{"key":"2026072811295781800_bib42","doi-asserted-by":"publisher","first-page":"D564","DOI":"10.1093\/nar\/gkae1091","article-title":"Updated resources for exploring experimentally-determined pdb structures and computed structure models at the rcsb protein data bank","volume":"53","author":"Burley","year":"2025","journal-title":"Nucleic Acids Res"},{"key":"2026072811295781800_bib43","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1038\/s41586-020-2649-2","article-title":"Array programming with numpy","volume":"585","author":"Harris","year":"2020","journal-title":"Nature"},{"key":"2026072811295781800_bib44","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","article-title":"Scipy 1.0: fundamental algorithms for scientific computing in python","volume":"17","author":"Virtanen","year":"2020","journal-title":"Nat Methods"},{"key":"2026072811295781800_bib45","doi-asserted-by":"publisher","first-page":"51","DOI":"10.25080\/majora-92bf1922-00a","article-title":"Data structures for statistical computing in python","author":"McKinney","year":"2010"},{"key":"2026072811295781800_bib46","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1109\/mcse.2007.55","article-title":"Matplotlib: A 2d graphics environment","volume":"9","author":"Hunter","year":"2007","journal-title":"Comput Sci Eng"},{"key":"2026072811295781800_bib47","doi-asserted-by":"publisher","first-page":"3021","DOI":"10.21105\/joss.03021","article-title":"seaborn: statistical data visualization","volume":"6","author":"Waskom","year":"2021","journal-title":"J Open Source Softw"},{"key":"2026072811295781800_bib48","doi-asserted-by":"publisher","first-page":"3907","DOI":"10.1016\/j.csbj.2024.10.023","article-title":"Protein allosteric site identification using machine learning and per amino acid residue reported internal protein nanoenvironment descriptors","volume":"23","author":"Omage","year":"2024","journal-title":"Comput Struct Biotechnol J"},{"key":"2026072811295781800_bib49","doi-asserted-by":"publisher","first-page":"bbaf424","DOI":"10.1093\/bib\/bbaf424","article-title":"Stingallo: a web server for high-throughput prediction of allosteric site-forming residues using internal protein nanoenvironment descriptors","volume":"26","author":"Omage","year":"2025","journal-title":"Brief Bioinform"},{"key":"2026072811295781800_bib50","doi-asserted-by":"publisher","first-page":"2977","DOI":"10.1021\/jm030580l","article-title":"The PDBbind database: collection of binding affinities for protein-ligand complexes with known three-dimensional structures","volume":"47","author":"Wang","year":"2004","journal-title":"J Med Chem"},{"key":"2026072811295781800_bib51","doi-asserted-by":"publisher","first-page":"D1096","DOI":"10.1093\/nar\/gks966","article-title":"BioLIP: a semi-manually curated database for biologically relevant ligand-protein interactions","volume":"41","author":"Yang","year":"2013","journal-title":"Nucleic Acids Res"}],"container-title":["Database"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/database\/article-pdf\/doi\/10.1093\/database\/baag031\/70268523\/baag031.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/database\/article-pdf\/doi\/10.1093\/database\/baag031\/70268523\/baag031.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T15:30:09Z","timestamp":1785252609000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/database\/article\/doi\/10.1093\/database\/baag031\/8744159"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1093\/database\/baag031","relation":{},"ISSN":["1758-0463"],"issn-type":[{"value":"1758-0463","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026]]},"published":{"date-parts":[[2026]]},"article-number":"baag031"}}