[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125832-en":3,"doc-seo-125832-105":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},125832,549758252649,"Ivy","https://ap-avatar.wpscdn.com/avatar/8000253669c5317157?_k=1778319167496531819",8,"Research & Report","Metabolic Profiling on 2D NMR TOCSY Spectra Using Machine Learning","Metabolomics is a fast-growing area of medical diagnostics driven by disease-related metabolic reprogramming, enabling study of molecular mechanisms and cellular pathways. Biological dynamics alter the chemical and biochemical characteristics of structural profiles in biofluids and tissues, making metabolic profiling essential for mapping disease fingerprints and their evolution. Two-dimensional NMR, specifically 2D 1H-1H TOCSY, improves spectral overlap but faces severe challenges such as peak shifts, overlap, crowding, and matrix effects, motivating automated ML-based deconvolution, assignment, and novelty detection.","Metabolic profiling on 2D NMR TOCSY Spectra Using Machine Learning  \nVon der Fakultät Elektrotechnik und Informationstechnik der Technischen Universität Dortmund genehmigte  \nDissertation  \nzur Erlangung des akademischen Grades  \nDoktor der Naturwissenschaft (Dr. rer. nat.) eingereicht von  \nLubaba Yousef Hazza Migdadi, M.Sc.  \nDortmund, 2023  \nTag der mündlichen Prüfung: 02.06.2023  \nHauptreferent: Prof. Dr. rer. nat. habil. Christian Wöhler, TU Dortmund Korreferent Prof. Dr.-Ing. habil. Franz Kummert, Bielefeld University  \nArbeitsgebiet Bildsignalverarbeitung Technische Universität Dortmund  \nAbstract  \nMetabolomics is an expanding field of medical diagnostics due to metabolic reprogramming alteration caused through diseases. Additionally, studying metabolomics offers an insight into the molecular mechanisms of diseases. The dynamicity of biological cells causes alteration in the chemical and biochemical characteristics of structural profiles of biological fluids and tissues. Therefore, the role of metabolic profiling in discovering biological fingerprints of diseases, and their evolution, as well as the cellular pathway of different biological or chemical stimuli is most significant.  \nTwo-dimensional nuclear magnetic resonance (2D NMR) is one of the fundamental and strong analytical instruments for metabolic profiling. Though, total correlation spectroscopy (2D NMR 1H-1H TOCSY) can be used to improve spectral overlap of 1D NMR, strong peak shift, signal overlap, spectral crowding and matrix effects in complex biological mixtures are extremely challenging in 2D NMR analysis. Thus, in this work, we introduce an automated metabolic deconvolution and assignment based on TOCSY of real breast cancer tissue and of adipose tissue-derived human Mesenchymal Stem cells. A major alternative to the common approaches in NMR based machine learning where images of the spectra are used as an input. In the new suggested approach, metabolic assignment is based only on the vertical and horizontal frequencies of the metabolites in the 1H-1H TOCSY.  \nA set of 27 metabolites were deduced from the TOCSY ofa breast cancer sample and the classifiers: Kernel Null Foley–Sammon Transform, support vector machines, and third- and fourth-degree polynomial classifiers have been customized and extended under the semi-supervised learning scheme. The classifiers’performance was evaluated by comparing the conventional humanbased methodology and automatic assignments under different initial training sizes settings.  \nMost metabolic profiling approaches focus only on identifying pre-known metabolites on 1H-1H TOCSY spectrum using configured parameters. However, there is a lack of research dealing with automating the detection of new metabolites that might appear during the dynamic evolution of biological cells. Novelty detection is a category of machine learning that is used to identify data that emerge during the test phase and were not considered during the training phase. We propose a novelty detection system for detecting novel metabolites in the 2D NMR 1H-1H TOCSY spectrum of a breast cancer-tissue sample. We build one-and multi-class recognition systems using different classifiers such as Kernel Null Foley-Sammon Transform, Kernel Density Estimation, and Support Vector Data Description. The training models were constructed based on different sizes of training data and are used in the novelty detection procedure. Multiple  \nevaluation measures were applied to test the performance of the novelty detection methods. The results of our novel metabolic profiling method demonstrate its suitability, robustness, and speed in automated metabolic research.  \nFurthermore, machine learning is applied on real-time 2D 1H-1H TOCSY to monitor the dynamic evolution of adipose tissue-derived human Mesenchymal Stem cells (AT-derived hMSCs) cultivated in basal culture media or in the presence of adipogenic or osteogenic differentiation media for a duration of fourteen days. ","cbCaijC2fzjgyGtL","https://ap.wps.com/l/cbCaijC2fzjgyGtL","pdf",9033914,1,126,"English","en",105,"# Introduction\n## Motivation\n## Contributions\n## Thesis Outline\n# Machine Learning","[{\"question\":\"Why is metabolic profiling important in metabolomics and disease research?\",\"answer\":\"Metabolic profiling helps discover biological fingerprints of diseases and track how these fingerprints evolve, while also supporting understanding of cellular pathways affected by biological or chemical stimuli.\"},{\"question\":\"What makes 2D NMR 1H-1H TOCSY useful and challenging for metabolic profiling?\",\"answer\":\"TOCSY improves spectral overlap compared with 1D NMR, but 2D analysis is difficult due to strong peak shifts, signal overlap, spectral crowding, and matrix effects in complex mixtures.\"},{\"question\":\"How does the proposed machine-learning approach differ from common NMR ML methods?\",\"answer\":\"Instead of using spectrum images as input, metabolic assignment is derived only from vertical and horizontal frequencies in the 1H-1H TOCSY data, paired with customized semi-supervised classifiers.\"}]","Metabolic Profiling on 2D NMR TOCSY Spectra Using Machine Learning | PDF",1785901469,318,{"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},"metabolic-profiling-on-2d-nmr-tocsy-spectra-using-machine-learning","",{"@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/metabolic-profiling-on-2d-nmr-tocsy-spectra-using-machine-learning/125832/",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","2026-08-05",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 is metabolic profiling important in metabolomics and disease research?","Question",{"text":75,"@type":76},"Metabolic profiling helps discover biological fingerprints of diseases and track how these fingerprints evolve, while also supporting understanding of cellular pathways affected by biological or chemical stimuli.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What makes 2D NMR 1H-1H TOCSY useful and challenging for metabolic profiling?",{"text":80,"@type":76},"TOCSY improves spectral overlap compared with 1D NMR, but 2D analysis is difficult due to strong peak shifts, signal overlap, spectral crowding, and matrix effects in complex mixtures.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the proposed machine-learning approach differ from common NMR ML methods?",{"text":84,"@type":76},"Instead of using spectrum images as input, metabolic assignment is derived only from vertical and horizontal frequencies in the 1H-1H TOCSY data, paired with customized semi-supervised classifiers.","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"]