[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128606-en":3,"doc-seo-128606-105":31,"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},128606,962084925502,"Lucas Martin","https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8",8,"Research & Report","Machine learning-based anti-cancer drug treatment optimization - Dissertation","Machine learning systems are expanding into healthcare, making trustworthiness a central scientific and societal challenge. This dissertation introduces novel ML-based decision support tools for cancer therapy by predicting anti-cancer drug responses from personalized multi-omics data. The work addresses data-related imbalance, improves model interpretability, and increases reliability. MERIDA outputs Boolean rules and leverages pharmacogenomic knowledge; SAURON-RF combines classification and regression to better handle underrepresented drug-sensitive samples; reliable SAURON-RF adds conformal prediction with certainty guarantees. A new drug sensitivity measure corrects limitations of existing metrics.","Machine learning-based anti-cancer drug treatment optimization  \nDissertation  \nzur Erlangung des Grades  \nder Doktorin der Naturwissenschaften (Dr. rer. nat) der Fakultät für Mathematik und Informatik der Universität des Saarlandes  \nvon  \nKerstin Lenhof  \nSaarbrücken  \nTag des Kolloquiums: 22.7.2024  \nDekan der Fakultät: Univ.-Prof. Dr. Roland Speicher  \nPrüfungsausschuss  \nVorsitzende des Prüfungsausschusses: Prof. Dr. Olga Kalinina  \nBerichterstatter: Prof. Dr. Hans-Peter Lenhof, Prof. Dr. Sven Rahmann, Prof. Dr. Gunnar W. Klau  \nWissenschaftlicher Mitarbeiter: Dr. Michael Backenköhler  \nAbstract  \nElves seldom give unguarded advice, for advice is a dangerous gift, even from the wise to the wise.  \n(Gildor, LotR)  \nMachine learning (ML) systems are about to expand into every area of our lives, including human healthcare. Thus, ensuring their trustworthiness represents one of today's most pressuring scientific and societal issues.  \nIn this thesis, we present novel ML-based decision support tools for one of the most complex, prevalent, and mortal diseases of our time: cancer. In particular, we focus on developing trustworthy ML methods for predicting anti-cancer drug responses from personalized multi-omics data. Our methods encompass strategies to minimize the effect of data-related issues such as class or regression imbalance, to achieve the interpretability of the models, and to increase the reliability of the models. Our first approach, MERIDA, is dedicated to interpretability: it delivers Boolean rules as output and considers a priori pharmacogenomic knowledge to a previously unconsidered extent. With SAURON-RF, we devised a simultaneous classification and regression method that improved the statistical performance for the underrepresented yet essential group of drug-sensitive samples, whose performance has mainly been neglected in the scientific literature. Its successor, reliable SAURONRF, provides a conformal prediction framework, which, for the first time, ensures the reliability of classification and regression with certainty guarantees. Moreover, we propose a novel drug sensitivity measure that addresses the shortcomings of the commonly used measures.  \nKurzfassung  \nElves seldom give unguarded advice, for advice is a dangerous gift, even from the wise to the wise.  \n(Gildor, LotR)  \nSysteme des machinellen Lernens (ML) sind im Begriff, in jeden Bereich unseres Lebens vorzudringen, inklusive der Gesundheitsversorgung. Dementsprechendist die Sicherstellung der Vertrauenswürdigkeit dieser Systeme eine der größten gesellschaftlichen und wissenschaftlichen Herausforderungen unserer Zeit.  \nDiese Dissertation stellt ML-basierte Entscheidungshilfeverfahren für eine der komplexesten und am weitesten verbreiteten Krankheiten der Welt vor: Krebs. Der Fokus dieser Arbeit liegt hierbei auf der Entwicklung vertrauenswürdiger Vorhersagemodelle für die Wirksamkeit von Krebsmedikamenten basierend auf personalisierten omics Daten. Unsere Methoden umfassen dabei Strategien zur Minimierung der Auswirkungen datenbezogener Probleme wie Klassen- oder Regressionsungleichgewicht, zur Verbesserung der Interpretierbarkeit der Modelle und zur Erhöhung der Zuverlässigkeit der Modelle.  \nUnser erster Ansatz, MERIDA, ist der Interpretierbarkeit gewidmet: MERIDA liefert logische Regeln als Ausgabe und berücksichtigt dabei pharmakogenomisches a priori Wissen in bisher nicht betrachtetem Umfang. Mit unserem zweiten Ansatz, SAURON-RF, haben wir eine Methode zur gleichzeitigen Regression und Klassifikation entwickelt. SAURON-RF verbessert die Vorhersagekraft für die unterrepräsentierten Gruppe der arzneimittelempfindlichen Proben, deren Wichtigkeitbisher vernachlässigt wurde. Der Nachfolger, reliable SAURON-RF, nutzt konforme Vorhersage (conformal prediction), um die Verlässlichkeit der Klassifikation und Regression zu gewährleisten. Darüber hinaus schlagen wir ein neuartiges Maß für die Medikamentenwirksamkeit vor, welches Unzulänglichkeiten üblicher Maße b","cbCaibVU0fqtrtui","https://ap.wps.com/l/cbCaibVU0fqtrtui","pdf",17911079,2,1,408,"English","en",105,"# Abstract\n## MERIDA: interpretability with Boolean rules\n## SAURON-RF and reliable SAURON-RF: joint prediction and reliability guarantees\n## Novel drug sensitivity measure\n# Acknowledgement","[{\"question\":\"What problem does the dissertation address in cancer treatment?\",\"answer\":\"It addresses how to develop trustworthy machine learning methods that predict anti-cancer drug responses from personalized multi-omics data.\"},{\"question\":\"How does MERIDA improve interpretability?\",\"answer\":\"MERIDA focuses on interpretability by producing Boolean rules and incorporating pharmacogenomic knowledge to a greater extent than previously considered.\"},{\"question\":\"What makes reliable SAURON-RF trustworthy?\",\"answer\":\"It uses a conformal prediction framework to provide reliability for both classification and regression with certainty guarantees.\"}]","Machine learning-based anti-cancer drug treatment optimization - Dissertation | PDF",1786002065,1028,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"machine-learning-based-anti-cancer-drug-treatment-optimization-dissertation","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,48,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":20},"https://docshare.wps.com/document/","Document",{"item":49,"name":12,"@type":44,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/machine-learning-based-anti-cancer-drug-treatment-optimization-dissertation/128606/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-25","2026-08-06",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},"What problem does the dissertation address in cancer treatment?","Question",{"text":76,"@type":77},"It addresses how to develop trustworthy machine learning methods that predict anti-cancer drug responses from personalized multi-omics data.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does MERIDA improve interpretability?",{"text":81,"@type":77},"MERIDA focuses on interpretability by producing Boolean rules and incorporating pharmacogenomic knowledge to a greater extent than previously considered.",{"name":83,"@type":74,"acceptedAnswer":84},"What makes reliable SAURON-RF trustworthy?",{"text":85,"@type":77},"It uses a conformal prediction framework to provide reliability for both classification and regression with certainty guarantees.","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":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]