[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117115-en":3,"doc-seo-117115-105":30,"detail-sidebar-cat-0-en-105":91},{"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":4,"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},117115,4398048949847,"Eliana","https://ap-avatar.wpscdn.com/avatar/400002536579ef2da7f?_k=1778318612642679267",8,"Research & Report","Safety quantification in gene editing experiments using machine learning on rationally designed feature spaces","With ongoing development of the CRISPR/Cas programmable nuclease system, applications in in vivo therapeutic gene editing are increasingly within reach. Nonnegligible off-target effects remain a major barrier for clinical use, despite many off-target cleavage datasets. This thesis develops a comprehensive and transparent overview tool via crisprSQL, then presents modelling strategies that quantify safety using machine learning on rationally designed feature spaces, integrating data processing, physical insight, and evaluation.","Safety quantification in gene editing experiments using machine learning on rationally designed feature spaces  \nFlorian M. Strtz Linacre College University of Oxford  \nA thesis submitted for the degree of Doctor of Philosophy  \nHilary Term 2023  \nTh’ infinite Creator can dwell in it, and may not man?  \n—Joseph Beaumont (1616-1699), The House of the Mind  \nContents  \nAbstract . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . iv  \n[Acknowledgements ..................................... vi](Acknowledgements ..................................... vi)  \n[List of publications arising from this work ........................ viii](List of publications arising from this work ........................ viii)  \n[List of Figures ........................................ ix](List of Figures ........................................ ix)  \nList of Tables . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . xiv  \nList of Abbreviations . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . xvi  \n1 Background 1  \n1.1 Biological background ................................ 1  \n1.1.1 Clinical gene therapy ............................. 1  \n1.1.2 CRISPR . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3  \n1.1.3 Cleavage repair ................................ 8  \n1.1.4 DNA structure & energetics ......................... 9  \n1.2 Computational background ............................. 11  \n1.2. 1 Gradient boosted decision trees . . . . . . . . . . . . . . . . . . . . . . . 12  \n1.2.2 Neural Networks . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13  \n1.2.3 Convolutional Neural Network . . . . . . . . . . . . . . . . . . . . . . . 14  \n1.2.4 Recurrent Neural Network . . . . . . . . . . . . . . . . . . . . . . . . . 15  \n1.2.5 MOSAICS . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18  \n1.3 Existing CRISPR modelling efforts ......................... 18  \n1.3.1 Cleavage data repositories .......................... 18  \n1.3.2 sgRNA specificity modelling efforts .................... 18  \n1.3.3 Existing editing outcome prediction algorithms ............. 21  \n1.3.4 Industry review ................................ 22  \n1.3.5 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23  \n2 Database platform for CRISPR/Cas9 off-target cleavage assays 24  \n2. 1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24  \n2.2 Materials and Methods . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26  \n2.2.1 Data Acquisition ............................... 26  \n2.2.2 Data storage .................................. 32  \n2.2.3 Website interface . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 32  \n2.3 Results and Discussion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 34  \n2.3.1 Future Developments ............................ 37  \n3 Physically informed modelling of CRISPR/Cas9 cleavage efficiency 40  \n3. 1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 41  \n3.2 Exploratory modelling . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 41  \n3.2. 1 Data Source . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 42  \n3.2.2 Data Augmentation ............................. 46  \n3.2.3 Feature Encoding ............................... 48  \n3.2.4 Model Architectures . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 49  \n3.2.5 Model Training & Evaluation . . . . . . . . . . . . . . . . . . . . . . . . 51  \n3.2.6 Results & Discussion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 56  \n3.2.7 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 63  \n3.3 Optimised selection of architectures, feature sets and encodings ........ 68  \n3.3.1 Model Training & Evaluation ........................ 69  \n3.3.2 Results & Discussion . . . . . ","cbCainmvrdBrnj9B","https://ap.wps.com/l/cbCainmvrdBrnj9B","pdf",16051539,1,169,"English","en",105,"# Background\n## Biological background\n## Computational background\n## Existing CRISPR modelling efforts\n# Database platform for CRISPR/Cas9 off-target cleavage assays\n## Introduction\n## Materials and Methods\n## Results and Discussion\n## Future Developments\n# Physically informed modelling of CRISPR/Cas9 cleavage efficiency\n## Introduction\n## Exploratory modelling\n## Optimised selection of architectures, feature sets and encodings\n# CRISPR repair outcome prediction using structural calculations\n## Introduction\n## Preliminary considerations\n## CasTER repair steps modelling\n# Conclusion & Further Developments","[{\"question\":\"What main problem does the thesis address in CRISPR gene editing?\",\"answer\":\"Nonnegligible off-target effects that limit safe clinical application, despite the existence of many datasets.\"},{\"question\":\"What tool is developed to support off-target analysis?\",\"answer\":\"The thesis presents the creation of crisprSQL, described as a comprehensive and transparent overview tool for off-target cleavage data.\"},{\"question\":\"How does the thesis approach safety quantification beyond data repositories?\",\"answer\":\"It uses machine learning on rationally designed feature spaces, including both data-driven modelling and physically informed or structural calculation based strategies to quantify outcomes.\"}]","Safety quantification in gene editing experiments using machine learning on rationally designed feature spaces | PDF",1785673955,426,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"safety-quantification-in-gene-editing-experiments-using-machine-learning-on-rationally-designed-feature-spaces","",{"@graph":36,"@context":85},[37,54,68],{"@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/safety-quantification-in-gene-editing-experiments-using-machine-learning-on-rationally-designed-feature-spaces/117115/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What main problem does the thesis address in CRISPR gene editing?","Question",{"text":75,"@type":76},"Nonnegligible off-target effects that limit safe clinical application, despite the existence of many datasets.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What tool is developed to support off-target analysis?",{"text":80,"@type":76},"The thesis presents the creation of crisprSQL, described as a comprehensive and transparent overview tool for off-target cleavage data.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the thesis approach safety quantification beyond data repositories?",{"text":84,"@type":76},"It uses machine learning on rationally designed feature spaces, including both data-driven modelling and physically informed or structural calculation based strategies to quantify outcomes.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"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":106,"slug":138},19,"General","general"]