[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-340870-105":59,"doc-detail-340870-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","data-and-text-mining-text-mining-for-contexts-and-relationships-in-cancer-genomics-literature","Data and text mining - Text mining for contexts and relationships in cancer genomics literature","","Motivation: Human genome publication in 2001 triggered a rapid expansion of cancer genomics literature describing context-specific gene functions and interactions. Large-scale text mining is needed to extract reported gene actions under specific experimental contexts and cell states, supporting the design of new therapeutic strategies. Results: A new corpus and methodology extract key details from biomedical text. A named entity recognition model mines PubMed abstracts, and a relation extraction model identifies links between entities. The approach outperforms earlier systems. Availability: Code and data are released on GitHub.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/data-and-text-mining-text-mining-for-contexts-and-relationships-in-cancer-genomics-literature/340870/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/data-and-text-mining-text-mining-for-contexts-and-relationships-in-cancer-genomics-literature/340870.png","ImageObject",300,407,{"name":92,"@type":93},"Logic","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-27","2026-09-22",true,{"@type":102,"interactionType":103,"userInteractionCount":52},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does the study address in cancer genomics literature?","Question",{"text":112,"@type":113},"The study addresses how to extract context-specific gene actions from the vast biomedical literature that researchers cannot analyze manually.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What models are introduced to process biomedical texts?",{"text":117,"@type":113},"It introduces a Named Entity Recognition model to extract important experiment details from PubMed abstracts and a second model to identify relationships between extracted details.",{"name":119,"@type":110,"acceptedAnswer":120},"How does the proposed system support research and therapeutic strategy design?",{"text":121,"@type":113},"By accurately identifying experiment context and gene relationships, it enables analysis of gene function across diverse and dynamically evolving experimental settings, helping inform new therapeutic strategies.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},340870,1790465031,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":52,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":44,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":143,"read_time":144,"preview_page_count":19,"preview_urls":145},1099513958762,"https://ap-avatar.wpscdn.com/avatar/1000023916a998db790?x-image-process=image/resize,m_fixed,w_180,h_180&k=1784791008015729253","Data and text mining  \nText mining for contexts and relationships in cancer genomics literature  \nCharlotte Collins  1, *,†, Simon Baker  1, *,†, Jason Brown 1,†, Huiyuan Zheng2, Adelyne Chan3, Ulla Stenius2, Masashi Narita3, Anna Korhonen 1  \n1 Language Technology Laboratory, Theoretical and Applied Linguistics, Faculty of Modern and Medieval Languages and Linguistics, University of Cambridge, Cambridge CB3 9DA, United Kingdom  \n2 Institute of Environmental Medicine, Karolinska Institutet, 171 77 Stockholm, Sweden  \n3 Cancer Research UK Cambridge Institute, Li Ka Shing Centre, University of Cambridge, Cambridge CB2 0RE, United Kingdom  \n*Corresponding authors. Language Technology Laboratory, Theoretical and Applied Linguistics, University of Cambridge, Cambridge CB3 9DA, United Kingdom. E-mails: [cac74@cam.ac.uk](cac74@cam.ac.uk) (C. C. ); [sb895@cam.ac.uk](sb895@cam.ac.uk) (S. B. )  \n†Equal contribution.  \nAssociate Editor: Zhiyong Lu  \nAbstract  \nMotivation: Scientiﬁc advances build on the ﬁndings of existing research. The 2001 publication of the human genome has led to the production of huge volumes of literature exploring the context-speciﬁc functions and interactions of genes. Technology is needed to perform large-scale text mining of research papers to extract the reported actions of genes in speciﬁc experimental contexts and cell states, such as cancer, thereby facilitating the design of new therapeutic strategies.  \nResults: We present a new corpus and Text Mining methodology that can accurately identify and extract the most important details of cancer genomics experiments from biomedical texts. We build a Named Entity Recognition model that accurately extracts relevant experiment details from PubMed abstract text, and a second model that identiﬁes the relationships between them. This system outperforms earlier models and enables the analysis of gene function in diverse and dynamically evolving experimental contexts.  \nAvailability and implementation: Code and data are available here: [https://github.com/cambridgeltl/functional-genomics-ie](https://github.com/cambridgeltl/functional-genomics-ie).  \n1 Introduction  \nScientific advances depend on collective learning, or the ability to communicate, record, and progressively build on knowledge over time. Since the first publication of the human genome in 2001 (Lander et al. 2001, Venter et al. 2001), the rapid development of new technologies in the biomedical field of genomics has led to the publication of vast numbers of studies seeking to decode the complex relationship between genotype (genetic constitution) and phenotype (the physical and behavioural attributes resulting from a genotype)(Przybyla and Gilbert 2022) . The function of individual genes varies with context such that the same gene may perform variably in different species, tissues, disease states, and experimental approaches. Genomics has the potential to revolutionize our understanding and treatment of human diseases, however, the quantity of literature available is too large for researchers to read and analyse manually. Most biomedical research is stored and accessed through the online biomedical database, PubMed, which already contains more than 34 million citations and is continuing to grow exponentially.  \nText mining (TM) can facilitate information extraction from large volumes of literature by turning unstructured, human-generated language into structured data (Renganathan 2017) . Biomedical TM requires both the means  \nof recognizing biological entities and strategies for identifying contextual details that specify their roles in experiments. TM employs Natural Language Processing (NLP) technology, which trains neural networks of machine-learning algorithmson specialized texts to develop domain-specific language representation models. Recent developments in NLP, such as Transformers (Lee et al. 2020), are used for general biomedical TM tasks. Here, we seek to develop the first TM methodology that is","cbCaiuH0VH8nVT8B","https://ap.wps.com/l/cbCaiuH0VH8nVT8B","pdf",970482,"English","# Abstract\n# 1 Introduction","[{\"question\":\"What problem does the study address in cancer genomics literature?\",\"answer\":\"The study addresses how to extract context-specific gene actions from the vast biomedical literature that researchers cannot analyze manually.\"},{\"question\":\"What models are introduced to process biomedical texts?\",\"answer\":\"It introduces a Named Entity Recognition model to extract important experiment details from PubMed abstracts and a second model to identify relationships between extracted details.\"},{\"question\":\"How does the proposed system support research and therapeutic strategy design?\",\"answer\":\"By accurately identifying experiment context and gene relationships, it enables analysis of gene function across diverse and dynamically evolving experimental settings, helping inform new therapeutic strategies.\"}]","Data and text mining - Text mining for contexts and relationships in cancer genomics literature | PDF",1790039259,23,[146,150,154,158],{"page_no":8,"url":147,"width":148,"height":149},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/23ff40e5caa21b533d83bcafbe266df2.webp",983,1272,{"page_no":14,"url":151,"width":152,"height":153},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/bfda2ba0cba85f315285972884494830.webp",982,1270,{"page_no":81,"url":155,"width":156,"height":157},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/a0d9848ef5bdf7226b994f21ac5dbf91.webp",981,1269,{"page_no":19,"url":159,"width":160,"height":161},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/4e2f380d2ca68eaf53fb7bcade4ea26a.webp",980,1268]