[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127173-en":3,"doc-seo-127173-105":30,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},127173,3985741905716,"Rowan","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","Integration of multiple machine learning approaches develops a gene mutationbased classifier for accurate immunotherapy outcomes","Immune checkpoint blockade therapies benefit only a minority of cancer patients, and established predictors such as PD-(L)1 expression and tumor mutation burden (TMB) show important limitations from assay heterogeneity and incomplete reflection of immunogenic drivers. This study uses multiple machine learning approaches on nonsynonymous mutations to identify key correlated variants and proposes the Gene mutation-based Predictive Signature (GPS) to classify predicted ICB response and outcomes. GPS outperforms conventional predictors in independent cohorts, with multi-omics and mIHC exploring immunogenicity and the tumor microenvironment across GPS groups, and ex vivo organoid co-culture validation of distinct responses.","npj | precision oncology Article  \n\n| Published in partnership with The Hormel Institute, University of Minnesota |  |  |\n| --- | --- | --- |\n| [https://doi.org/10.1038/s41698-025-00842-8](https://doi.org/10.1038/s41698-025-00842-8) |  |  |\n| Integration of multiple machine learning approaches develops a gene mutationbased classifier for accurate immunotherapy outcomes\u003Cbr> Check for updates |  |  |\n| Run Shi1,9, Jing Sun2,3,9, Zhaokai Zhou4,9, Meiqi Shi5, Xin Wang5, Zhaojia Gao6, Tianyu Zhao7, Minglun Li8 & Yongqian Shu 1  |  |  |\n| In addition to traditional biomarkers like PD-(L)1 expression and tumor mutation burden (TMB), more reliable methods for predicting immune checkpoint blockade (ICB) response in cancer patients are urgently needed. This study utilized multiple machine learning approaches on nonsynonymous mutations to identify key mutations that are most significantly correlated to ICB response. We proposed a classifier, Gene mutation-based Predictive Signature (GPS), to categorize patients based on their predicted response and clinical outcomes post-ICB therapy. GPS outperformed conventional predictors when validated in independent cohorts. Multi-omics analysis and multiplex immunohistochemistry (mIHC) revealed insights into tumor immunogenicity, immune responses, and the tumor microenvironment (TME) in lung adenocarcinoma (LUAD) across different GPS groups. Finally, we validated distinct responses of different GPS samples to ICB in an ex-vivo tumor organoidPBMC co-culture model. Overall, our findings highlight a simple, robust classifier for accurate ICB response prediction, which could reduce costs, shorten testing times, and facilitate clinical implementation. |  |  |\n| In recent years, the advent of immune checkpoint blockade (ICB) targeting programmed death-1 (PD-1), programmed death ligand-1 (PD-L1), and cytotoxic T lymphocyte-associated protein-4 (CTLA-4) has revolutionized cancer therapy and offered tremendous clinical benefits for patients with various types of cancer who had failed from first-line treatments1–3. However, only a small subset (~20–30%) of cancer patients respond to ICB therapy, and the underlying causes of insensitivity to ICB remain elusive4,5.\u003Cbr>In the present clinical practice, PD-(L)1 expression and tumor mutation burden (TMB) serve as two major predictive biomarkers for ICB therapy, but both have obvious shortcomings. PD-(L)1protein expression is mainly evaluated using immunohistochemistry (IHC). However, the staining result is susceptible to both spatial and temporal heterogeneity of | tumor samples and subjective judgment of pathologists, which would induce an inevitable bias ofassessment6. Paradoxically, some cancer patients with high PD-L1 expression unexpectedly show resistance to ICB, yet some patients with negative PD-L1 still respond to ICB therapy7.\u003Cbr>As for TMB, which reflects the somatic mutation burden including synonymous and nonsynonymous variants of a tumor sample, has been proposed as another promising biomarker for ICB therapy over recent years8,9. For example, TMB has been shown as a favorable biomarker for response to frontline treatment with nivolumab together with ipilimumabin patients with advanced non-small cell lung cancer (NSCLC)7. However, the assessment ofTMB still stagnates atthe level of“quantity of mutations”, that is to say, the total number ofall detected mutations10. Actually, different |  |\n\n1Department of Oncology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China. 2Department of Endocrinology, Jiangsu Province Hospital of Chinese Medicine, Affiliated Hospital of Nanjing University of Chinese Medicine, Nanjing, China. 3The First Clinical Medical College of Nanjing University of Chinese Medicine, Nanjing, China. 4Department of Urology, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China. 5Department of Oncology, The Affiliated Cancer Hospital of Nanjing Medical University, Jiangsu Cancer Hospital, Jiangsu Institute of","cbCailYOGyR8jzUj","https://ap.wps.com/l/cbCailYOGyR8jzUj","pdf",6981694,1,16,"English","en",105,"# Background\n## Limitations of PD-(L)1 and TMB\n# Methods\n## Multiple machine learning on nonsynonymous mutations\n## GPS classifier design\n# Results\n## Performance in independent cohorts\n## Multi-omics and multiplex immunohistochemistry insights\n## Ex vivo organoid-PBMC co-culture validation\n# Implications","[{\"question\":\"Why are PD-(L)1 expression and TMB insufficient for predicting ICB response?\",\"answer\":\"PD-(L)1 staining is influenced by spatial/temporal heterogeneity and subjective pathologist judgment, while TMB reflects mutation quantity rather than functional contributions to neoantigen generation and immunogenicity. Some resistant or nonresponsive cases show discordant biomarker status.\"},{\"question\":\"What is the Gene mutation-based Predictive Signature (GPS)?\",\"answer\":\"GPS is a classifier built from key nonsynonymous mutations identified via multiple machine learning approaches. It categorizes patients by predicted ICB response and expected clinical outcomes after immunotherapy.\"},{\"question\":\"How was GPS validated and what biological insights were obtained?\",\"answer\":\"GPS was validated in independent cohorts where it outperformed conventional predictors. Multi-omics and multiplex immunohistochemistry (mIHC) examined tumor immunogenicity, immune responses, and the tumor microenvironment across GPS groups, and an ex vivo tumor organoid–PBMC co-culture model confirmed distinct ICB responses.\"}]","Integration of multiple machine learning approaches develops a gene mutationbased classifier for accurate immunotherapy outcomes | PDF",1785937324,40,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"integration-of-multiple-machine-learning-approaches-develops-a-gene-mutationbased-classifier-for-accurate-immunotherapy-outcomes","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/integration-of-multiple-machine-learning-approaches-develops-a-gene-mutationbased-classifier-for-accurate-immunotherapy-outcomes/127173/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-22","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why are PD-(L)1 expression and TMB insufficient for predicting ICB response?","Question",{"text":76,"@type":77},"PD-(L)1 staining is influenced by spatial/temporal heterogeneity and subjective pathologist judgment, while TMB reflects mutation quantity rather than functional contributions to neoantigen generation and immunogenicity. Some resistant or nonresponsive cases show discordant biomarker status.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What is the Gene mutation-based Predictive Signature (GPS)?",{"text":81,"@type":77},"GPS is a classifier built from key nonsynonymous mutations identified via multiple machine learning approaches. It categorizes patients by predicted ICB response and expected clinical outcomes after immunotherapy.",{"name":83,"@type":74,"acceptedAnswer":84},"How was GPS validated and what biological insights were obtained?",{"text":85,"@type":77},"GPS was validated in independent cohorts where it outperformed conventional predictors. Multi-omics and multiplex immunohistochemistry (mIHC) examined tumor immunogenicity, immune responses, and the tumor microenvironment across GPS groups, and an ex vivo tumor organoid–PBMC co-culture model confirmed distinct ICB responses.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":29,"slug":119},7,"Healthcare","healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":107,"slug":138},19,"General","general"]