[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121511-en":3,"doc-seo-121511-105":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":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},121511,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Towards prediction of CML Treatment Outcomes - with Machine Learning and CyTOF Data","Predicting therapy responses for patients with Chronic Myeloid Leukemia (CML) supports more effective, individualized treatment strategies. This thesis trains and compares machine learning models using mass cytometry (CyTOF) samples collected before treatment, at 3 hours, and at 7 days to predict responses to tyrosine kinase inhibitors (TKIs) at 6 and 18 months. A nested cross-validation framework is used for model optimization and evaluation. Model interpretability is explored to highlight key biomarkers, and results also assess performance on new patients, including cell-type prediction using clustered CyTOF representations.","Towards prediction of CML Treatment Outcomes with Machine Learning and CyTOF  \nData  \nMathilde Bergenheim  \nDepartment of Informatics University of Bergen, Norway  \n©Copyright Mathilde Bergenheim  \nThe material in this publication is protected by copyright law.  \nYear: 2024  \nTitle: Towards prediction of CML Treatment Outcomes  \nwith Machine Learning and CyTOF Data Author: Mathilde Bergenheim  \nAcknowledgements  \nI would like to express my sincere gratitude to my supervisor, Inge Jonasson, for his consistent guidance and valuable advice on how to better structure this thesis. Most importantly, I thank him for keeping me on the right track throughout this journey.  \nI also extend my thanks to everyone in the Gjertsen group for providing me with the necessary data and assisting me in understanding it. Special thanks to Bjørn Tore Gjertsen for his clear explanations and for answering all my questions about chronic myeloid leukemia (CML) . His philosophy,”If I can’t explain what I’m doing to anyone, I don’t know it well enough,”was particularly reassuring, as it made me feel comfortable even with my limited background in biology, and is a philosophy I will carry with me.  \nI am grateful to my friends, family, and fellow students for their encouragement, support, and assistance throughout my studies, and for showing genuine interest in my work. A special thanks goes to my boyfriend for his endless support and patience with me.  \nLast but not least, I want to thank Stein Erik Gullaksen, a researcher in the Gjertsen group, for his extensive knowledge about CyTOF and the various tools used to analyze this data. His patience in re-explaining concepts when necessary has been invaluable. He has been the crucial link between data analysis and biology, always available to answer my questions and solve problems, even after moving to the USA.  \nMathilde Bergenheim  \nJune 1st, 2024  \niv Acknowledgements  \nAbstract  \nPredicting responses to therapy for patients with Chronic Myeloid Leukemia (CML) is crucial for optimizing treatment strategies. This study utilizes machine learning models with mass cytometry (CyTOF) data from samples taken before treatment, at 3 hours and 7 days post-treatment, to predict patient responses to tyrosine kinase inhibitors (TKIs) at 6 and 18 months. By comparing the accuracy of various machine learning methods, the research aims to develop tailored treatment strategies for CML patients. The study also explores how well these models can be applied to new patients. A nested cross-validation strategy is employed to optimize and evaluate the models. Additionally, the models are analyzed to identify key biomarkers deemed important for predicting responses at different time points. The findings indicate that integrating machine learning with CyTOF data shows promise in enhancing predictive accuracy, which may help in making early-phase treatment decisions and improving patient outcomes in CML therapy. Furthermore, the study demonstrates promising results in predicting cell types using models trained on clustered CyTOF data, highlighting the potential for these models to accurately classify cell populations.  \nvi Abstract  \nContents  \nAcknowledgements iii  \nAbstract v  \n1 Introduction 1  \n1.1 Problem Statement and Objectives ............. 1  \n2 Background 3  \n2.1 Machine Learning ...................... 3  \n2.1.1 Supervised learning ................. 4  \n2.1.2 Unsupervised learning ............... 11  \n2.1.3 Data Preprocessing ................. 12  \n2.2 Application domain ..................... 14  \n2.2.1 Chronic Myeloid Leukemia ............ 14  \n2.2.2 Mass cytometry/CyTOF .............. 17  \n2.3 Bioinformatics ....................... 18  \n2.3.1 Cancer bioinformatics ............... 18  \n3 Material and Methods 21  \n3.1 Material ........................... 21  \n3.1.1 Patients ....................... 21  \n3.1.2 Materials ...................... 22  \n3.2 Methods ........................... 24  \n3.2.1 Reading and normalizing the","cbCaiuieHtdY2MpK","https://ap.wps.com/l/cbCaiuieHtdY2MpK","pdf",11389999,1,91,"English","en",105,"# Introduction\n## Problem Statement and Objectives\n# Background\n## Machine Learning\n## Application domain\n## Bioinformatics\n# Material and Methods\n## Material\n## Methods\n# Results and discussions\n## Dividing the dataset\n## Batch effects\n## Grouping cells by cell types\n## Predicting patient outcome\n# Conclusions\n# Bibliography\n# Appendix","[{\"question\":\"What data and time points are used to predict CML responses to TKIs?\",\"answer\":\"The study uses CyTOF samples collected before treatment, at 3 hours, and at 7 days post-treatment. These are used to predict patient responses at 6 and 18 months to tyrosine kinase inhibitors (TKIs).\"},{\"question\":\"How are machine learning models optimized and evaluated in this work?\",\"answer\":\"A nested cross-validation strategy is applied to optimize and assess the different machine learning methods, supporting reliable comparison of accuracy and generalization.\"},{\"question\":\"What does the thesis analyze besides predicting patient outcomes?\",\"answer\":\"It investigates key biomarkers associated with responses at different time points and also evaluates model performance for predicting cell types using clustered CyTOF data.\"}]","Towards prediction of CML Treatment Outcomes - with Machine Learning and CyTOF Data | PDF",1785736021,229,{"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},"towards-prediction-of-cml-treatment-outcomes-with-machine-learning-and-cytof-data","",{"@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/towards-prediction-of-cml-treatment-outcomes-with-machine-learning-and-cytof-data/121511/",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","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What data and time points are used to predict CML responses to TKIs?","Question",{"text":75,"@type":76},"The study uses CyTOF samples collected before treatment, at 3 hours, and at 7 days post-treatment. These are used to predict patient responses at 6 and 18 months to tyrosine kinase inhibitors (TKIs).","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How are machine learning models optimized and evaluated in this work?",{"text":80,"@type":76},"A nested cross-validation strategy is applied to optimize and assess the different machine learning methods, supporting reliable comparison of accuracy and generalization.",{"name":82,"@type":73,"acceptedAnswer":83},"What does the thesis analyze besides predicting patient outcomes?",{"text":84,"@type":76},"It investigates key biomarkers associated with responses at different time points and also evaluates model performance for predicting cell types using clustered CyTOF data.","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"]