[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-334278-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-334278-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","combining-evolution-and-protein-language-models-for-an-interpretable-cancer-driver-mutation-prediction-with-d2deep","Combining evolution and protein language models for an interpretable cancer driver mutation prediction with D2Deep","","Cancer-causing driver mutations can be hard to distinguish from random passenger mutations using tumor-specific genomic data. State-of-the-art homology-based predictors often embed biases and are poorly aligned with cancer’s biological complexity. Protein language models have not yet been validated at large scale for this task and typically lack interpretability. The D2Deep framework combines a general protein language model with protein-specific evolutionary signals to predict driver mutations from sequence only.",{"@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/combining-evolution-and-protein-language-models-for-an-interpretable-cancer-driver-mutation-prediction-with-d2deep/334278/",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/combining-evolution-and-protein-language-models-for-an-interpretable-cancer-driver-mutation-prediction-with-d2deep/334278.png","ImageObject",300,407,{"name":42,"@type":43},"Genevieve","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-11","2026-09-21",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",8,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"Why is cancer driver mutation prediction challenging?","Question",{"text":63,"@type":64},"Driver mutations must be separated from passenger mutations using tumor-specific genomic data, but homology-based predictors can carry biases and do not fully capture cancer biology’s complexity.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How does D2Deep combine language and evolutionary signals?",{"text":68,"@type":64},"D2Deep integrates a nonspecialized protein language model capturing information from protein sequences with protein-specific evolutionary information reflecting functional requirements.",{"name":70,"@type":61,"acceptedAnswer":71},"How are D2Deep predictions meant to support clinical interpretation?",{"text":72,"@type":64},"D2Deep produces confidence scores and predictions that can be accessed through TumorScope to help prioritize mutations and interpret results in clinical settings.","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},334278,1790218901,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,114,119,122,126],{"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":55,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":112,"slug":113},30,"research-report",{"id":115,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"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":55,"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":4},1374391974585,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","Briefings in Bioinformatics, 2025, 26(1), bbae664  \n[https://doi.org/10.1093/bib/bbae664](https://doi.org/10.1093/bib/bbae664)  \nProblem Solving Protocol  \nCombining evolution and protein language models for an interpretable cancer driver mutation prediction with D2Deep  \nKonstantina Tzavella 1 , Adrian Diaz1 , Catharina Olsen1 , 2 , 3 ,‡, Wim Vranken1 ,4 , 5 , 6 , 7 ,‡, *  \n1 Interuniversity Institute of Bioinformatics (IB2), Université Libre de Bruxelles, Vrije Universiteit Brussel (ULB-VUB), Triomflaan, Brussels 1050, Belgium  \n2 Brussels Interuniversity Genomics High Throughput Core (BRIGHTcore), Vrije Universiteit Brussel (VUB), Université Libre de Bruxelles (ULB), Laarbeeklaan 101, Brussels 1090, Belgium  \n3 Clinical Sciences, Research Group Genetics, Reproduction and Development (GRAD), Vrije Universiteit Brussel (VUB), Universitair Ziekenhuis Brussel (UZ Brussel), Laarbeeklaan 101, Brussels 1090, Belgium  \n4 Structural Biology Brussels, Vrije Universiteit Brussel (VUB), Pleinlaan 2, Brussels 1050, Belgium  \n5 Chemistry Department, Vrije Universiteit Brussel, Pleinlaan 2, Brussels 1050, Belgium  \n6AI Lab, Vrije Universtiteit Brussel, Pleinlaan 2, Brussels 1050, Belgium  \n7 Biomedical sciences, Vrije Universiteit Brussel, Laarbeeklaan 101, Brussels 1090, Belgium  \n*Corresponding author. Interuniversity Institute of Bioinformatics (IB2), ULB-VUB, Triomflaan, Brussels 1050, [Belgium. E-mail:](Belgium. E-mail: wim.vranken@vub.be)[ wim.vranken@vub.be](Belgium. E-mail: wim.vranken@vub.be)[ ](Belgium. E-mail: wim.vranken@vub.be)‡Catharina Olsen and Wim Vranken contributed equally to this work.  \nAbstract  \nThe mutations driving cancer are being increasingly exposed through tumor-specific genomic data. However, differentiating between cancer-causing driver mutations and random passenger mutations remains challenging. State-of-the-art homology-based predictors contain built-in biases and are often ill-suited to the intricacies of cancer biology. Protein language models have successfully addressed various biological problems but have not yet been tested on the challenging task of cancer driver mutation prediction at a large scale. Additionally, they often fail to offer result interpretation, hindering their effective use in clinical settings. The AI-based D2Deep method we introduce here addresses these challenges by combining two powerful elements: (i) a nonspecialized protein language model that captures the makeup of all protein sequences and (ii) protein-specific evolutionary information that encompasses functional requirements for a particular protein. D2Deep relies exclusively on sequence information, outperforms state-of-the-art predictors, and captures intricate epistatic changes throughout the protein caused by mutations. These epistatic changes correlate with known mutations in the clinical setting and can be used for the interpretation of results. The model is trained on a balanced, somatic training set and so effectively mitigates biases related to hotspot mutations compared to state-of-the-art techniques. The versatility of D2Deep is illustrated by its performance on non-cancer mutation prediction, where most variants still lack known consequences. D2Deep predictions and confidence scores are available via [https://tumorscope.be/d2deep](https://tumorscope.be/d2deep) to help with clinical interpretation and mutation prioritization.  \nReceived: June 21, 2024 . Revised: September 15, 2024 . Accepted: December 7, 2024  \n© The Author(s) 2024 . Published by Oxford University Press.  \nThis is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License ([https://creativecommons.org/](https://creativecommons.org/)[ ](https://creativecommons.org/)[licenses/by-nc/4.0/](licenses/by-nc/4.0/)), which permits non-commercial re-use, distribution, and reproduction in any medium, provided the original work is properly cited. For commercial re-use, please [contact journals.permissions@ou","cbCaisqkTLvSGUTs","https://ap.wps.com/l/cbCaisqkTLvSGUTs","pdf",2999243,13,"English","# Abstract\n## Problem framing\n## D2Deep approach\n## Training strategy and bias mitigation\n## Clinical interpretation via TumorScope\n# Keywords\n# Introduction","[{\"question\":\"Why is cancer driver mutation prediction challenging?\",\"answer\":\"Driver mutations must be separated from passenger mutations using tumor-specific genomic data, but homology-based predictors can carry biases and do not fully capture cancer biology’s complexity.\"},{\"question\":\"How does D2Deep combine language and evolutionary signals?\",\"answer\":\"D2Deep integrates a nonspecialized protein language model capturing information from protein sequences with protein-specific evolutionary information reflecting functional requirements.\"},{\"question\":\"How are D2Deep predictions meant to support clinical interpretation?\",\"answer\":\"D2Deep produces confidence scores and predictions that can be accessed through TumorScope to help prioritize mutations and interpret results in clinical settings.\"}]","Combining evolution and protein language models for an interpretable cancer driver mutation prediction with D2Deep | PDF",1790006095,33]