[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-371806-105":59,"doc-detail-371806-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","neural-interaction-explainable-ai-predicts-drug-response-across-cancers","Neural interaction explainable AI predicts drug response across cancers","","Personalized treatment selection is crucial for cancer patients due to the high variability in drug response. While actionable mutations can inform decisions, many therapies still rely on population-based approaches. NeurixAI is an explainable, scalable deep learning framework that models drug–gene interactions and finds transcriptomic patterns linked to drug response. Trained on 546,646 drug perturbation experiments across 1135 drugs and 476 tumors, it predicts unseen responses and identifies repurposed drug anticancer potential using xAI mechanisms.",{"@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":35,"@type":76,"position":81},"https://docshare.wps.com/document/healthcare/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/neural-interaction-explainable-ai-predicts-drug-response-across-cancers/371806/",{"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/neural-interaction-explainable-ai-predicts-drug-response-across-cancers/371806.png","ImageObject",300,407,{"name":92,"@type":93},"Elsa","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-24","2026-09-23",true,{"@type":102,"interactionType":103,"userInteractionCount":34},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"Why is personalized treatment selection important in cancer therapy?","Question",{"text":112,"@type":113},"Cancer patients show high variability in drug response. Personalized selection helps address differences in how tumors react to the same therapy.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What is NeurixAI and what does it model?",{"text":117,"@type":113},"NeurixAI is an explainable, scalable deep learning framework that models drug–gene interactions and links transcriptomic patterns to drug response.",{"name":119,"@type":110,"acceptedAnswer":120},"How was NeurixAI trained and validated?",{"text":121,"@type":113},"It was trained using 546,646 drug perturbation experiments across 1135 drugs and molecular profiles from 476 tumors, achieving strong performance on unseen tumor samples and an external validation set.","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},371806,1790839222,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":34,"category_name":35,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":34,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":145},137455077381,"https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d","NAR Cancer, 2025, 7, zcaf029  \n[https://doi.org/10.1093/narcan/zcaf029](https://doi.org/10.1093/narcan/zcaf029)  \nCancer Computational Biology  \nNeural interaction explainable AI predicts drug response across cancers  \nPhilipp Keyl 1 ,2 ,3 ,4 , *, Julius Keyl 5 , 6 , Andreas Mock2 , 7 , Gabriel Dernbach8 ,9 ,  \nLiliana H. Mochmann2 , Niklas Kiermeyer2 , 7 , Philipp Jurmeister2 , 7 , Michael Bockmayr 1 , 10 , 11 , Roland F. Schwarz3 ,4 , Grégoire Montavon 3 ,8 , 12 ,†, Klaus-Robert Müller 3 ,8 , 13 , 14 ,†, Frederick Klauschen 1 ,2 ,3 , 7 ,†  \n1 Institute of Pathology, Charité—Universitätsmedizin Berlin, 10117 Berlin, Germany  \n2 Institute of Pathology, Faculty of Medicine, LMU Munich, 80337 Munich, Germany  \n3 BIFOLD—Berlin Institute for the Foundations of Learning and Data, 10587 Berlin, Germany  \n4 Institute for Computational Cancer Biology (ICCB), Center for Integrated Oncology (CIO), Cancer Research Center Cologne Essen (CCCE), Faculty of Medicine and University Hospital Cologne, University of Cologne, 50931 Cologne, Germany  \n5 Institute for Artificial Intelligence in Medicine, University Hospital Essen (AöR), Essen, Germany  \n6 Institute of Pathology, University Hospital Essen (AöR), 45147 Essen, Germany  \n7 German Cancer Consortium (DKTK), German Cancer Research Center (DKFZ), Munich partner site, 80336 Munich, Germany  \n8 Machine Learning Group, Technical University of Berlin, 10587 Berlin, Germany  \n9Aignostics GmbH, 10555 Berlin, Germany  \n10 Department of Pediatric Hematology and Oncology, University Medical Center Hamburg-Eppendorf, 20246 Hamburg, Germany  \n11 bAIome—Center for Biomedical AI, University Medical Center Hamburg-Eppendorf, 20246 Hamburg, Germany  \n12 Department of Mathematics and Computer Science, Freie Universität Berlin, 14195 Berlin, Germany  \n13 Department of Artificial Intelligence, Korea University, Seoul 136-713, South Korea  \n14 MPI for Informatics, 66123 Saarbrücken, Germany  \n* To whom correspondence should be addressed. Email: [philippgerrit.keyl@med.uni-muenchen.de](philippgerrit.keyl@med.uni-muenchen.de)[ ](philippgerrit.keyl@med.uni-muenchen.de)†The last three authors should be regarded as Joint Last Authors.  \nAbstract  \nPersonalized treatment selection is crucial for cancer patients due to the high variability in drug response. While actionable mutations can increasingly inform treatment decisions, most therapies still rely on population-based approaches. Here, we introduce neural interaction explainable AI (NeurixAI), an explainable and highly scalable deep learning framework that models drug–gene interactions and identifies transcriptomic patterns linked with drug response. Trained on data from 546 646 drug perturbation experiments involving 1135 drugs and molecular profiles from 476 tumors, NeurixAI accurately predicted treatment responses for 272 targeted and 30 chemotherapeutic drugs in unseen tumor samples (Spearman’s rho >0.2), maintaining high performance on an external validation set. Additionally, NeurixAI identified the anticancer potential of 160 repurposed non-cancer drugs. Using explainable artificial intelligence (xAI), our framework uncovered key genes influencing drug response at the individual tumor level and revealed both known and novel mechanisms of drug resistance. These findings demonstrate the potential of integrating transcriptomics with xAI to optimize cancer treatment, enable drug repurposing, and identify new therapeutic targets.  \nReceived: February 26, 2025. Revised: July 23, 2025. Editorial Decision: July 26, 2025. Accepted: August 11, 2025  \n© The Author(s) 2025. Published by Oxford University Press.  \nThis is an Open Access article distributed under the terms of the Creative Commons Attribution-NonCommercial License  \n([https:](https://creativecommons.org/licenses/by-nc/4.0/)[//](https://creativecommons.org/licenses/by-nc/4.0/)[creativecommons.org](https://creativecommons.org/licenses/by-nc/4.0/)[/](https://creativecommons.org/licenses/by-nc/4.0/)[licen","cbCaisPfplray3Hu","https://ap.wps.com/l/cbCaisPfplray3Hu","pdf",1950887,13,"English","# Abstract\n## Introduction\n## Graphical abstract","[{\"question\":\"Why is personalized treatment selection important in cancer therapy?\",\"answer\":\"Cancer patients show high variability in drug response. Personalized selection helps address differences in how tumors react to the same therapy.\"},{\"question\":\"What is NeurixAI and what does it model?\",\"answer\":\"NeurixAI is an explainable, scalable deep learning framework that models drug–gene interactions and links transcriptomic patterns to drug response.\"},{\"question\":\"How was NeurixAI trained and validated?\",\"answer\":\"It was trained using 546,646 drug perturbation experiments across 1135 drugs and molecular profiles from 476 tumors, achieving strong performance on unseen tumor samples and an external validation set.\"}]","Neural interaction explainable AI predicts drug response across cancers | PDF",1790192910,33]