[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117443-en":3,"doc-seo-117443-105":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},117443,13056703019404,"Miles","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Advanced Applications of Machine Learning in Bioinformatics - Dissertation","Machine learning has evolved continuously since its first appearance, driving progress in science and technology while increasingly attracting interdisciplinary attention beyond traditional computer science. Studies applying machine learning to bioinformatics demonstrate feasibility for solving biological problems, yet challenges stem from differences in data and tasks between the two fields. Training learning-based models requires a systematic pipeline, with data- and task-related factors jointly determining performance. This thesis develops advanced methods tailored to epigenomics, metagenomics, and infectious diseases to improve practical use of machine learning in bioinformatics.","Advanced Applications of Machine Learning in  \nBioinformatics  \nDissertation  \nder Mathematisch-Naturwissenschaftlichen Fakultät der Eberhard Karls Universität Tübingen zur Erlangung des Grades eines Doktors der Naturwissenschaften  \n(Dr. rer. nat.)  \nvorgelegt von  \nM. Sc. Wenhuan Zeng  \naus Hongkong, China  \nTübingen  \nGedruckt mit Genehmigung der Mathematisch-Naturwissenschaftlichen Fakultät der Eberhard Karls Universität Tübingen.  \nTag der mündlichen Qualifikation: 27.03.2025  \nDekan: Prof. Dr. Thilo Stehle  \n1. Berichterstatter/-in: Prof. Dr. Daniel H. Huson  \n2. Berichterstatter/-in: Prof. Dr. Nico Pfeifer  \nAbstract  \nMachine learning has evolved continuously since its first appearance, driving progress in science and technology while increasingly attracting interdisciplinary attention beyond the scope of traditional computer science. A number of studies have applied machine learning to bioinformatics, obtaining valuable findings and validating the feasibility of using machine learning algorithms to solve biological problems. The difficulties and challenges in using machine learning techniques for biological problem-solving arise from the differences in data and tasks between computer science and biology. Training a sophisticated learning-based model is a systematic task that involves a series of steps. These steps can be broadly categorized into data and task aspects, each influencing the overall performance of the model. Appropriately adjusting the model based on the specific task during training is essential for effectively adapting machine learning algorithms to domain-specific challenges, which motivates us to develop advanced methods tailored to the biological field, allowing machine learning to be more successfully applied to problems that were initially solved using traditional computational methods in bioinformatics. This thesis presents our studies addressing biological problems across three topics: epigenomics, metagenomics, and infectious diseases. Solving problems in each area, we developed advanced machine learning frameworks based on considering corresponding biological characteristics, thereby improving machine learning algorithms for better performance. First, we address DNA methylation status identification within epigenomics by developing two new frameworks inspired by natural language processing techniques. These frameworks implement the detection of DNA methylation sites and provide biological insights through model interpretation. Second, regarding problems in metagenomics, we present a study that predicts the source of microbiome samples among ten different origins by training a sophisticated ensemble model on taxonomic and functional profiles generated by whole-genome shotgun metagenomics sequencing. Finally, we introduce a study on an infectious disease problem in the context of the COVID- 19 pandemic, focusing on predicting patients mortality and exploring factors associated  \nwith disease severity. This study consists of multiple models trained on different types of datasets. These models jointly demonstrated the feasibility of predicting patients’ status based on their diverse features and provided valuable insights during the early stages of a new infectious disease. In summary, this cumulative thesis assembles studies across multiple topics of biological problems, advancing current machine learning algorithms for more practical applications in bioinformatics.  \nKurzfassung  \nMaschinelles Lernen hat sich seit seiner Entstehung kontinuierlich weiterentwickelt und treibt den Fortschritt in Wissenschaft und Technologie voran, während es zunehmend interdisziplinäre Aufmerksamkeit über den Bereich der traditionellen Informatik hinaus auf sich zieht. Zahlreiche Studien haben maschinelles Lernen in der Bioinformatik verwendet, um wertvolle Erkenntnisse zu gewinnen, was den Nutzen dieser Methoden zur Lösung biologischer Probleme unterstreicht. Die Schwierigkeiten und Herausforderungen bei der Anwen","cbCaiqzFUYB04E4G","https://ap.wps.com/l/cbCaiqzFUYB04E4G","pdf",8519217,1,121,"English","en",105,"# Abstract\n## Epigenomics: DNA methylation\n## Metagenomics: microbiome source prediction\n## Infectious diseases: COVID-19 severity and mortality","[{\"question\":\"Why are machine-learning methods challenging to apply directly in bioinformatics?\",\"answer\":\"Difficulties arise from differences in data and tasks between computer science and biology, which affect training and model performance.\"},{\"question\":\"What does the thesis cover besides general methodological discussion?\",\"answer\":\"It addresses biological problems in three areas: epigenomics, metagenomics, and infectious diseases, with tailored advanced machine-learning frameworks for each.\"},{\"question\":\"How are models used for the COVID-19 infectious disease study?\",\"answer\":\"The study trains multiple models on different dataset types to predict patients’ status, including mortality, and to explore factors linked to disease severity.\"}]","Advanced Applications of Machine Learning in Bioinformatics - Dissertation | PDF",1785675897,305,{"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},"advanced-applications-of-machine-learning-in-bioinformatics-dissertation","",{"@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/advanced-applications-of-machine-learning-in-bioinformatics-dissertation/117443/",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},"Why are machine-learning methods challenging to apply directly in bioinformatics?","Question",{"text":75,"@type":76},"Difficulties arise from differences in data and tasks between computer science and biology, which affect training and model performance.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What does the thesis cover besides general methodological discussion?",{"text":80,"@type":76},"It addresses biological problems in three areas: epigenomics, metagenomics, and infectious diseases, with tailored advanced machine-learning frameworks for each.",{"name":82,"@type":73,"acceptedAnswer":83},"How are models used for the COVID-19 infectious disease study?",{"text":84,"@type":76},"The study trains multiple models on different dataset types to predict patients’ status, including mortality, and to explore factors linked to disease severity.","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"]