[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-371833-105":59,"doc-detail-371833-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","understanding-tcr-t-cell-knockout-behavior-using-interpretable-machine-learning","Understanding TCR T cell knockout behavior using interpretable machine learning","","Genetic perturbation of TCR T cells offers a route to improve immune performance for stronger cancer immunotherapies, yet the behavioral consequences of such edits remain difficult to decipher. Prior work relied on cytokine or metabolic assays, while live-cell imaging provides a practical readout of T cell–cancer interactions. This study uses explainable AI with convolutional neural networks to classify interaction behaviors under CRISPR knockouts of CUL5 and RASA2 and a safe-harbor control, linking behavior differences to interaction coverage and aggregation patterns.",{"@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/understanding-tcr-t-cell-knockout-behavior-using-interpretable-machine-learning/371833/",{"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/understanding-tcr-t-cell-knockout-behavior-using-interpretable-machine-learning/371833.png","ImageObject",300,407,{"name":92,"@type":93},"Kurz","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-02","2026-09-23",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},"Why is understanding TCR T cell knockout behavior important for cancer immunotherapies?","Question",{"text":112,"@type":113},"Genetic perturbations are promising for enhancing TCR T cell performance, but the link between edits and changes in cell behavior is hard to characterize. This understanding is needed to better exploit the resulting therapeutic effects.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What data modality does the study rely on to analyze TCR T cell behavior?",{"text":117,"@type":113},"The study uses live-cell imaging of co-cultures, capturing the dynamics of interactions between TCR T cells and cancer cells across time points.",{"name":119,"@type":110,"acceptedAnswer":120},"How does explainable AI contribute to distinguishing knockout conditions?",{"text":121,"@type":113},"The approach trains convolutional neural networks to distinguish behaviors under specific CRISPR knockouts, then uses explainable AI to identify interaction types that define different knockout conditions, such as differences in coverage and aggregation patterns.","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},371833,1791312503,{"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":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},2336478945635,"https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8","Author Manuscript Author Manuscript Author Manuscript Author Manuscript  \n\n| | HHS Public Access\u003Cbr>Author manuscript\u003Cbr>Pac Symp Biocomput. Author manuscript; available in PMC 2025 September 23. |\n| --- | --- |\n\nPublished in final edited form as:  \nPac Symp Biocomput. 2025 ; 30: 382–393. doi:10.1142/9789819807024_0028.  \nUnderstanding TCR T cell knockout behavior using interpretable machine learning  \nMarcus Blennemann,  \nGladstone Institutes, San Francisco, CA 94158, USA  \nArchit Verma,  \nGladstone Institutes, San Francisco, CA 94158, USA  \nStefanie Bachl,  \nUniversity of California, San Francisco, San Francisco, CA 94143, USA  \nJulia Carnevale,  \nUniversity of California, San Francisco, San Francisco, CA 94143, USA  \nBarbara E. Engelhardt  \nGladstone Institutes, San Francisco, CA 94158, USA, Biomedical Data Science, Stanford University Stanford, CA 94305, USA  \nAbstract  \nGenetic perturbation ofT cell receptor (TCR) T cells is a promising method to unlock better TCR T cell performance to create more powerful cancer immunotherapies, but understanding the changes to T cell behavior induced by genetic perturbations remains a challenge. Prior studies have evaluated the effect of different genetic modifications with cytokine production and metabolic activity assays. Live-cell imaging is an inexpensive and robust approach to capture TCRT cell responses to cancer. Most methods to quantify T cell responses in live-cell imaging data use simple approaches to count T cells and cancer cells across time, effectively quantifying how much space in the 2D well each cell type covers, leaving actionable information unexplored. In this study, we characterize changes in TCR T cell’s interactions with cancer cells from live-cell imaging data using explainable artificial intelligence (AI) . We train convolutional neural networks to distinguish behaviors in TCR T cell with CRISPR knock outs of CUL5, RASA2, and a safe harbor control knockout. We use explainable AI to identify specific interaction types that define different knock-out conditions. We find that T cell and cancer cell coverage is a strong marker ofTCR T cell modification when comparing similar experimental time points, but differences in cell aggregation characterize CUL5KO and RASA2KO behavior across all time points. Our pipeline for discovery in live-cell imaging data can be used for characterizing complex behaviorsin arbitrary live-cell imaging datasets, and we describe best practices for this goal.  \nOpen Access chapter published by World Scientific Publishing Company and distributed under the terms of the Creative Commons Attribution Non-Commercial (CC BY-NC) 4.0 License.  \n[marcus.blennemann@gladstone.ucsf.edu](marcus.blennemann@gladstone.ucsf.edu) .  \nAuthor Manuscript Author Manuscript Author Manuscript Author Manuscript  \nBlennemann et al. Page 2  \nKeywords  \nExplainable AI; Grad-CAM; machine learning; live cell imaging  \n1. Introduction  \nSince FDA approval in 2017, chimeric antigen receptor (CAR) T cell immunotherapies have proven effective at treating advanced leukemias and lymphomas.1,2 CAR T cell therapy uses ex vivo modification of native patient T cells to express a chimeric antigen receptor (CAR), capable of binding to surface markers of cancerous cells, to enhance T cell immunological response. T-cell receptor (TCR) therapy is a related method of treatment that uses naturally existing TCRs, protein complexes that bind to a cell’s major histocompatibility complex (MHC), as an alternative to CAR proteins. TCR therapy targets various cancers by recognizing a specific antigen presented by a human leukocyte antigen (HLA) on cancer cell surfaces. This reduces the risk of toxicity associated with CAR T cell therapy, which currently struggles to distinguish between solid cancer cells and normal tissues.1 TCR therapy, in contrast, has demonstrated effective responses against multiple solid cancer types such as melanoma and lung carcinoma with reduced off-target effects.3  \nGe","cbCaieBaRPNqeh51","https://ap.wps.com/l/cbCaieBaRPNqeh51","pdf",1205960,18,"English","# 1. Introduction\n# 2. Methods and Explainable AI Approach\n# 3. Results: Interaction Behaviors by Knockout Condition\n# 4. Pipeline and Best Practices for Live-Cell Imaging Discovery","[{\"question\":\"Why is understanding TCR T cell knockout behavior important for cancer immunotherapies?\",\"answer\":\"Genetic perturbations are promising for enhancing TCR T cell performance, but the link between edits and changes in cell behavior is hard to characterize. This understanding is needed to better exploit the resulting therapeutic effects.\"},{\"question\":\"What data modality does the study rely on to analyze TCR T cell behavior?\",\"answer\":\"The study uses live-cell imaging of co-cultures, capturing the dynamics of interactions between TCR T cells and cancer cells across time points.\"},{\"question\":\"How does explainable AI contribute to distinguishing knockout conditions?\",\"answer\":\"The approach trains convolutional neural networks to distinguish behaviors under specific CRISPR knockouts, then uses explainable AI to identify interaction types that define different knockout conditions, such as differences in coverage and aggregation patterns.\"}]","Understanding TCR T cell knockout behavior using interpretable machine learning | PDF",1790192978,45,[147,151,155,159],{"page_no":8,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/18511f11b6498af913d43415f30fe9b7.webp",983,1272,{"page_no":14,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/118bfbe47ba95b7c04d63e5cb4ec2d88.webp",982,1270,{"page_no":81,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/a458030369a670664cadb8d0fe94784e.webp",981,1269,{"page_no":19,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/f2432ab7d761a6c00227ac86753b47ec.webp",980,1268]