[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-364150-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-364150-en":130},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","a-fair-gold-standard-benchmark-for-geographic-entity-recognition-in-cancer-genomics-literature-for-biomedical-nlp","A FAIR gold-standard benchmark for geographic entity recognition in cancer genomics literature for biomedical NLP","","Geographic biases in cancer genomics research restrict the global applicability of precision oncology. Existing consortia cover only a limited set of countries and leave most of the PubMed literature unrepresented, partly because standardized, machine-readable geographic and molecular metadata are missing and extraction models lack domain-specific benchmark datasets. The work introduces a FAIR-compliant gold-standard benchmark with 129 curated studies across 46 countries. The benchmark supports systematic evaluation of document-level extraction and enables training and comparison of domain-specific NLP models.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/a-fair-gold-standard-benchmark-for-geographic-entity-recognition-in-cancer-genomics-literature-for-biomedical-nlp/364150/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/a-fair-gold-standard-benchmark-for-geographic-entity-recognition-in-cancer-genomics-literature-for-biomedical-nlp/364150.png","ImageObject",300,407,{"name":42,"@type":43},"pixelkiddo","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-14","2026-09-23",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",10,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"Why is geographic bias a problem in cancer genomics literature mining?","Question",{"text":63,"@type":64},"Geographic biases limit the global applicability of precision oncology, because major consortia represent only a small fraction of countries and the broader publication record lacks standardized, machine-readable geographic and molecular metadata.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"What does the proposed benchmark provide?",{"text":68,"@type":64},"It provides a FAIR-compliant gold-standard benchmark including 129 manually curated cancer genomics studies across 46 countries, enabling evaluation of automated geographic information and molecular data extraction approaches.",{"name":70,"@type":61,"acceptedAnswer":71},"How do molecular data coverage and misattribution issues affect the benchmark’s significance?",{"text":72,"@type":64},"Many studies include author affiliations from countries unrelated to patient cohorts, which causes systematic misattribution when using metadata proxies. The benchmark also includes molecular data for 263,472 patients, highlighting substantial literature-derived resources not present in major consortia.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},364150,1790241047,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,120,123,126],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":112,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":113,"slug":114},8,30,"research-report",{"id":116,"doc_module":4,"doc_module_name":25,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":25,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":55,"slug":125},"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":112,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":139,"language":140,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":12,"update_tm":144,"read_time":145,"preview_page_count":33,"preview_urls":146},962090883892,"https://ap-avatar.wpscdn.com/avatar/e00115db34f3e0f11b?x-image-process=image/resize,m_fixed,w_180,h_180&k=1790152879550218658","A FAIR gold-standard benchmark for geographic entity recognition in cancer genomics literature for biomedical NLP  \nMaricel G. Kann1,*, , Karen O’Connor2, , Petra Tembei1, Samuel Rosner3, Graciela Gonzalez Hernandez4,*  \n1 Biological Sciences Department, University of Maryland, Baltimore County, Baltimore, MD 21250, United States  \n2 Department of Biostatistics, Epidemiology, and Informatics, University of Pennsylvania, Philadelphia, PA 19104, United States  \n3 Division of Oncology, University of Maryland Marlene & Stewart Greenebaum Comprehensive Cancer Center, Baltimore, MD 21201, United States 4 Department of Computational Biomedicine, Cedars Sinai Medical Center, Los Angeles, CA 90069, United States  \n*Corresponding authors. Maricel G. Kann, Department of Biological Sciences, University of Maryland, Baltimore County, 1000 Hilltop Circle, Baltimore, MD, 21250, United [States. E-mail: mkann@umbc.edu](States. E-mail: mkann@umbc.edu); Graciela Gonzalez Hernandez, Department of Computational Biomedicine, Cedars Sinai Medical Center, 700 N. San Vicente Blvd. Pacific Design Center Suite G549F, West Hollywood, CA 90069, United States. E-mail: [Graciela.GonzalezHernandez@csmc.edu](Graciela.GonzalezHernandez@csmc.edu).  \nAssociate Editor: Scott Hazelhurst  \nAbstract  \nMotivation: Geographic biases in cancer genomics research limit precision oncology’s global applicability. Major consortia represent only 16 countries and sample less than 1% of 1.4 million publications worldwide. While automated literature mining could address these biases, the lack of benchmark datasets prevents rigorous development and validation of extraction models. We present a FAIR-compliant gold-standard benchmark of 129 manually curated cancer genomics studies spanning 46 countries, tripling geographic representation versus existing consortia. This dataset enables systematic evaluation of automated geographic information and molecular data extraction approaches and establishes a reference task for document-level geographic information extraction models.  \nResults: Our benchmark highlights critical challenges for AI-powered literature mining. GeoBoost2 achieves 55% macro-F1 and 46% micro-F1 for patient-origin extraction across 129 articles, exposing precision–recall tradeoffs requiring domain adaptation. Seventy percent of studies include author affiliations from countries unrelated to patient cohorts, showing that metadata-based approaches systematically misattribute geographic provenance. Of 129 studies, 96 provide molecular data for 263 472 cancer patients, revealing substantial untapped literature-derived resources absent from major consortia and supporting training and comparison of domain-specific NLP models.  \nAvailability and implementation: The complete benchmark dataset, including manual annotations, automated extraction outputs, evaluation scripts, and supplementary documentation, is available at Zenodo with DOI 10.5281/zenodo. 18259159.  \n1 Introduction  \nThe biomedical literature represents a vast, underutilized data resource. PubMed indexes over 1.4 million cancer genomics publications spanning 188 countries, yet major consortia such as The Cancer Genome Atlas (TCGA) (The Cancer Genome Atlas Research Network et al. 2013), cBioPortal (Cerami et al. 2012), and the International Cancer Genome Consortium (ICGC) (The International Cancer Genome Consortium 2010) have systematically incorporated data from only 16 nations. This 99% underutilization reflects not just access barriers, but fundamental challenges in automated information extraction: published studies lack standardized, machine-readable geographic and molecular metadata, and existing natural language processing (NLP)  \ntools lack domain-specific validation benchmarks. Without rigorously curated training datasets, developing robust extraction models remains intractable, a challenge generalizable across biomedical literature mining applications.  \nMajor international consortia datasets predomina","cbCairT78XhLD0df","https://ap.wps.com/l/cbCairT78XhLD0df","pdf",1694127,13,"English","# Abstract\n## Motivation\n## Results\n## Availability and implementation\n# Introduction","[{\"question\":\"Why is geographic bias a problem in cancer genomics literature mining?\",\"answer\":\"Geographic biases limit the global applicability of precision oncology, because major consortia represent only a small fraction of countries and the broader publication record lacks standardized, machine-readable geographic and molecular metadata.\"},{\"question\":\"What does the proposed benchmark provide?\",\"answer\":\"It provides a FAIR-compliant gold-standard benchmark including 129 manually curated cancer genomics studies across 46 countries, enabling evaluation of automated geographic information and molecular data extraction approaches.\"},{\"question\":\"How do molecular data coverage and misattribution issues affect the benchmark’s significance?\",\"answer\":\"Many studies include author affiliations from countries unrelated to patient cohorts, which causes systematic misattribution when using metadata proxies. The benchmark also includes molecular data for 263,472 patients, highlighting substantial literature-derived resources not present in major consortia.\"}]","A FAIR gold-standard benchmark for geographic entity recognition in cancer genomics literature for biomedical NLP | PDF",1790156070,33,[147,151,155,159],{"page_no":22,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/6cc472f910566cda28f4825ae421e77e.webp",983,1291,{"page_no":26,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/f7962aeea1ef6e5b10de235332832943.webp",982,1290,{"page_no":30,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/5cc4673403e623156ea2031e64630086.webp",981,1289,{"page_no":33,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/58cce1b08257e5acb4ef2130fa06bc8a.webp",980,1287]