[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-363620-105":59,"doc-detail-363620-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","decoding-immunotherapy-response-through-computational-modeling-review-article","Decoding immunotherapy response through computational modeling - Review article","","Immunotherapy has achieved major success in treating cancer, yet patient responses vary widely, creating a strong need for reliable stratification and individualized therapy planning. This review synthesizes four computational paradigms—classical and deep machine learning, graph and network modeling, and mechanistic systems biology—showing how approaches evolve from correlational features toward representation learning, relational inference, and causal simulation. Emphasis is placed on multi-modal fusion and interpretable, clinically deployable models, especially to enable robust predictive biomarkers for precision immuno-oncology.",{"@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/decoding-immunotherapy-response-through-computational-modeling-review-article/363620/",{"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/decoding-immunotherapy-response-through-computational-modeling-review-article/363620.png","ImageObject",300,407,{"name":92,"@type":93},"Franzy","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-24","2026-09-23",true,{"@type":102,"interactionType":103,"userInteractionCount":44},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"Why is patient stratification needed in cancer immunotherapy?","Question",{"text":112,"@type":113},"Immunotherapy shows success, but responses vary due to profound heterogeneity and non-uniform benefit. This variability also increases exposure to immune-related adverse events and other costs, making robust stratification essential.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What computational paradigms does the review cover?",{"text":117,"@type":113},"The review analyzes four converging paradigms: classical machine learning, deep learning, graph and network modeling, and mechanistic systems biology. It highlights the shift from correlational features toward representation learning, relational inference, and causal simulation.",{"name":119,"@type":110,"acceptedAnswer":120},"What are key biological bottlenecks for building predictive models?",{"text":121,"@type":113},"The tumor microenvironment is dynamic and heterogeneous, including intratumor heterogeneity that can make biopsies unrepresentative and baseline sampling that may miss later tumor-immune trajectories. Additional host factors and intrinsically resistant tumor contexts further complicate prediction.","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},363620,1790992293,{"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":44,"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,"preview_page_count":19,"preview_urls":146},2336478945519,"https://ap-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45","Review article [https://doi.org/10.1038/s41467-026-71364-5](https://doi.org/10.1038/s41467-026-71364-5)  \nDecoding immunotherapy response through computational modeling  \nReceived: 7 February 2025  \n\n| Accepted: 21 March 2026 |\n| --- |\n| |\n| Check for updates |\n\nBingrui Li1,2,6, Ruihan Luo 2,3,4,6, Kexin Huang2,3,4,6, Jiajia Liu2, Weiling Zhao2 & Xiaobo Zhou 2,5   \nImmunotherapy has seen success in treating patients with cancer, but variable responses underscore the need for effective patient stratiﬁcation and therapy planning. Computational tools integrating multi-omics, imaging and machine learning have advanced, yet reliable personalized predictions remain challenging. This review analyzes the ﬁeld through four converging paradigms:  \nclassical machine learning, deep learning, graph and network modeling, and mechanistic systems biology. We examine the evolution from correlational features to representation learning, relational inference, and causal simulation of tumor-immune dynamics, highlighting the shift towards multi-modal fusion and interpretable, clinically deployable models. By providing an integrated review of these computational tools, we hope to bring the community closer to achieving precision immuno-oncology for personalized cancer treatments.  \nThe clinical imperative for predictive biomarkers  \nCancer immunotherapy, particularly immune checkpoint inhibitors (ICI), has fundamentally changed the landscape of oncology, offering the prospect of durable, long-term remission for patients with advanced malignancies1. Therapies targeting the programmed cell death protein 1 (PD-1)/programmed death-ligand 1 (PD-L1) and cytotoxic T-lymphocyte antigen-4 (CTLA-4) have demonstrated unprecedented success in various cancers, including melanoma2,3, non-small-cell lung cancer (NSCLC)4 and renal cell carcinoma5. However, the transformative potential of these agents is tempered by the profound heterogeneity inpatient response2,6. Even within responsive cancer types, a substantial proportion of patients fail to derive clinical beneﬁt, while others may experience severe, and occasionally life-threatening, immune-related adverse events (irAE)7. This variability not only exposes non-responding patients to toxicity and substantial ﬁnancial cost but also underscoresan urgent, unmet need for robust predictive biomarkers8.  \nThe development of such biomarkers is a vital clinical imperative for advancing precision immuno-oncology. An ideal biomarker would accurately stratify patients before treatment, identifying likely  \nresponders, candidates for combination strategies, and those better served by alternatives. Achieving these goals often requires computational models that integrate tumor-, host-, and treatment-level factors to help translate biomarker signals into actionable decisions, but the core bottleneck remains in capturing the complex interactions among cancer, immune system and existing therapy, an inherently high-dimensional task well suited to computational tools.  \nAn overview of biological and data-related bottlenecks Developing reliable predictive models is obstructed by biological complexity and data limitations, which help explain why early biomarkers often proved insufﬁcient (Table 1) and why more sophisticated computational approaches may be necessary.  \nThe primary biological bottleneck is the dynamic and heterogeneous nature of the tumor microenvironment (TME) . Intratumor heterogeneity (ITH) creates spatial and genetic diversity, so a single biopsy may not represent the full tumor and can confound spot sampling-based prediction9. In addition, the TME is dynamic; a baseline biopsy may miss the subsequent tumor-immune trajectory10. Host-  \n1Department of Cancer Biology, University of Texas MD Anderson Cancer Center, Houston, TX, USA. 2Center for Computational Systems Medicine, School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX, USA. 3West China Biomedical Big Data Ce","cbCaisgmmG6n4aIF","https://ap.wps.com/l/cbCaisgmmG6n4aIF","pdf",3051292,21,"English","# Clinical imperative for predictive biomarkers\n# An overview of biological and data-related bottlenecks\n## Tumor microenvironment complexity and data limitations\n# Review scope: computational paradigms and modeling evolution\n## From correlational features to causal simulation","[{\"question\":\"Why is patient stratification needed in cancer immunotherapy?\",\"answer\":\"Immunotherapy shows success, but responses vary due to profound heterogeneity and non-uniform benefit. This variability also increases exposure to immune-related adverse events and other costs, making robust stratification essential.\"},{\"question\":\"What computational paradigms does the review cover?\",\"answer\":\"The review analyzes four converging paradigms: classical machine learning, deep learning, graph and network modeling, and mechanistic systems biology. It highlights the shift from correlational features toward representation learning, relational inference, and causal simulation.\"},{\"question\":\"What are key biological bottlenecks for building predictive models?\",\"answer\":\"The tumor microenvironment is dynamic and heterogeneous, including intratumor heterogeneity that can make biopsies unrepresentative and baseline sampling that may miss later tumor-immune trajectories. Additional host factors and intrinsically resistant tumor contexts further complicate prediction.\"}]","Decoding immunotherapy response through computational modeling - Review article | PDF",1790152206,53,[147,151,155,159],{"page_no":8,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/b0b1b4b06d9ad22c1ec12fea5016a636.webp",983,1305,{"page_no":14,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/db8a65241e9b292ed7d8f40c75f0b3a9.webp",982,1304,{"page_no":81,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/427500383cd72a3729b75047e98ca807.webp",981,1303,{"page_no":19,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/3e251e318e3c53685c90195721cd414a.webp",980,1301]