[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118457-en":3,"doc-seo-118457-105":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},118457,2336464648746,"Skyler","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Biophysical Dynamical Priors in Machine Learning - Doctor of Philosophy Dissertation","Biophysical dynamical priors in machine learning address how integrating domain knowledge can enhance modeling for biological systems. The work is motivated by the expansion of high-resolution biological datasets and the limitations of benchmark-style assumptions in real applications. It examines biophysical inductive bias across multiple machine learning models for problems such as genetic regulation. The dissertation uses the latent force paradigm to improve interpretability and representation, proposes scalable predictive methods, and extends RNA velocity for single-cell inference like pseudotime.","Biophysical Dynamical Priors in Machine Learning  \nJacob Daniel Moss  \nDarwin College  \nNov, 2024  \nThis dissertation is submitted for the degree of Doctor of Philosophy  \nDeclaration  \nThis thesis is the result of my own work and includes nothing which is the outcome of work done in collaboration except as declared in the preface and specified in the text. It is not substantially the same as any work that has already been submitted, or is being concurrently submitted, for any degree, diploma or other qualification at the University of Cambridge or any other University or similar institution except as declared in the preface and specified in the text. It does not exceed the prescribed word limit for the relevant Degree Committee  \nJacob Daniel Moss  \nNov, 2024  \n4  \nAbstract  \nBiophysical dynamical priors in machine learning  \nJacob Daniel Moss  \nThe proliferation of machine learning models in biology is due to the great potential of novel discoveries ranging from new medicines to an improved understanding of the development of species. Adding to this, an ever-increasing number of high-resolution biological datasets are providing the fuel for these models to extract meaningful insights. Due to the success of this pairing, machine learning in biology has emerged to be a vital field of research. As with any real-world applications, the scenarios are usually much more complex than the benchmark tasks found in foundational machine learning research. In addition, the standard modelling approaches in biology frequently involve classical techniques such as dimensionality reduction to a 2D plane followed by empirical observations. This motivates a need to construct better modelling techniques that make use of developments in deep learning. The challenge is then to scale these approaches to the vast size and dimensionality of biological datasets.  \nIn this dissertation, I hypothesise that incorporating domain knowledge can not only improve predictive performance but also yield additional insights that cannot be obtained through datadriven methods alone. In order to evaluate this hypothesis, I select a set of important problems in biology, such as genetic regulation, and construct a variety of machine learning models with the aim of evaluating the relative efficacies of different levels of biophysical inductive bias. The approaches I introduce in Chapter 3 traverse from simple, black box dynamical biases to explicit biophysical priors encoded directly in the model. The resulting techniques are studied under the lens of the latent force paradigm, a combination of nonparametric mechanistic and data-driven approaches, leading to improved biological interpretability and a greater representation power. In Chapter 4, I propose and evaluate methods which improve the predictive performance compared with the standard approaches as well as drastically increase the scalability of the paradigm. Chapter 5 extends the popular biological framework, RNA velocity, both to reduce invalid assumptions and to enable the inference of single-cell resolution quantities such as pseudotime. Finally, Chapter 6 presents a conclusion on all the work conducted along with directions for future work.  \n6  \nAcknowledgements  \nThe past five years at Cambridge have been shaped strongly by Professor Pietro Liò . During our first call at the time of my MPhil application, I remember that you opened the world of research to me—everything seemed possible. Despite not winning the string of promised Nobel prizes, I have had an unbelievably special time thanks to your unwavering and ongoing support, kindness, warmth, and humour. Thank you for making this all possible. I owe another great debt of gratitude to Professor Jeremy England for our regular meetings. Thank you for your gentle encouragement and for keeping me on track over the years. At the start of my PhD I thoroughly enjoyed collaborating with Bianca; our shared interests in computational methods in single-cell genomics led to m","cbCaivT1uNhrkQDy","https://ap.wps.com/l/cbCaivT1uNhrkQDy","pdf",17118983,1,134,"English","en",105,"# Introduction\n## Thesis outline & research questions\n## Publications\n# Modelling biophysical data\n## Biological background\n### Gene expression\n### Regulation","[{\"question\":\"Why does the dissertation focus on biophysical dynamical priors in machine learning for biology?\",\"answer\":\"Machine learning in biology is powerful, but real biological scenarios are more complex than standard benchmark tasks. The dissertation targets the need for modeling approaches that incorporate domain knowledge rather than relying only on data-driven methods.\"},{\"question\":\"What hypothesis does the dissertation propose to test?\",\"answer\":\"Incorporating domain knowledge is hypothesized to improve predictive performance and to provide additional insights not obtainable using data-driven methods alone.\"},{\"question\":\"How do the later chapters extend the work beyond basic modeling?\",\"answer\":\"Chapter 4 introduces scalable and predictive-performance-improving methods for the paradigm. Chapter 5 extends RNA velocity to reduce invalid assumptions and enables inference of single-cell quantities such as pseudotime.\"}]","Biophysical Dynamical Priors in Machine Learning - Doctor of Philosophy Dissertation | PDF",1785683707,338,{"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},"biophysical-dynamical-priors-in-machine-learning-doctor-of-philosophy-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/biophysical-dynamical-priors-in-machine-learning-doctor-of-philosophy-dissertation/118457/",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 does the dissertation focus on biophysical dynamical priors in machine learning for biology?","Question",{"text":75,"@type":76},"Machine learning in biology is powerful, but real biological scenarios are more complex than standard benchmark tasks. The dissertation targets the need for modeling approaches that incorporate domain knowledge rather than relying only on data-driven methods.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What hypothesis does the dissertation propose to test?",{"text":80,"@type":76},"Incorporating domain knowledge is hypothesized to improve predictive performance and to provide additional insights not obtainable using data-driven methods alone.",{"name":82,"@type":73,"acceptedAnswer":83},"How do the later chapters extend the work beyond basic modeling?",{"text":84,"@type":76},"Chapter 4 introduces scalable and predictive-performance-improving methods for the paradigm. Chapter 5 extends RNA velocity to reduce invalid assumptions and enables inference of single-cell quantities such as pseudotime.","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"]