[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122034-en":3,"doc-seo-122034-105":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},122034,2336464648322,"Aria","https://ap-avatar.wpscdn.com/avatar/2200025388227c56fec?_k=1778556882303663488",8,"Research & Report","De Novo Protein Design using Generative Machine Learning","This thesis develops computational methods for designing novel protein sequences and structures using deep generative machine learning. It covers six chapters ranging from an introduction to de novo protein design and generative learning, to studies on variational autoencoders for sequence design, and evaluations of AlphaFold on previously generated proteins. It further develops protein sequence language models trained on synthetic data, tests AlphaFold-guided fixed-backbone design via greedy optimization, and concludes with contributions and future implications for design methodology.","De Novo Protein Design using Generative Machine Learning  \nLewis Iain Moffat  \nA dissertation submitted in partial fulfillment of the requirements for the degree of  \nDoctor of Philosophy  \nof  \nUCL  \nDepartment of Computer Science University College London  \nJune 14, 2023  \n2  \nI, Lewis Iain Moffat, confirm that the work presented in this thesis is my own. Where information has been derived from other sources, I confirm that this has been indicated in the thesis.  \nAbstract  \nIn this thesis, methods are developed for computationally designing novel protein sequences and structures using deep generative machine learning algorithms. It is divided into six chapters.  \nChapter 1 provides an introduction to contemporary protein design, generative machine learning, and the nascent field emerging from the intersection of the two. This particularly focuses on the challenge of de novo protein design and the demonstrated uses of generative deep learning methods.  \nChapter 2 describes the first study performed for this thesis. It explores the use of variational autoencoders for protein sequence design with two separate in silico design tasks, one functional and one structural, respectively. Being one of the earliest works on this topic, it provided evidence that generative approaches had merit as a focus for further design investigations.  \nChapter 3 encompasses an analysis of the performance of state-of-the-art deep protein structure prediction algorithms, primarily the AlphaFold method, on previously de novo designed protein sequences. As expected, it finds AlphaFold is able to accurately and confidently predict the structures of these proteins, supporting its use as a tool in the development of future design methods.  \nChapter 4 explores the development of protein sequence language models trained on synthetic sequences to avoid the detriments of training with natural sequences. It also describes the evaluation of generated sequences with state-of-the-art structure predictor AlphaFold.  \nChapter 5 describes a technique for fixed-backbone protein design using greedy sequence optimization of AlphaFold structure predictions that leverages the models developed in the previous chapter. Initial in vitro validation of a small number of designed sequences provides optimistic signs of success.  \nAbstract 4  \nThe final chapter highlights the key contributions of this thesis to the field of computational protein design and concludes with implications for future design method development.  \nImpact Statement  \nThe research undertaken for this thesis may impact the academic Protein Design community, and the community within that, that focuses on protein design with machine learning methods. Across the spread of this thesis, research has been performed that demonstrates the viability of deep generative modelling as a means of performing protein design in several different contexts. This ranges from some of the earliest published examples of such work to more modern applications.  \nGiven the recent huge rise in popularity of such approaches, both in academia and industrially, my work has potentially had an impact in being among the many similar pieces of work disseminated publicly constituting that rise. This is also true of any impact going forward, following the submission of this thesis. Protein design, having huge promise in the development of novel biomaterials and biopharmaceuticals, inter alia, has a far reaching potential for different impacts. As such, this provides a wide scope for the potential impact my work, and the many others in the field, may have.  \nThe work in this thesis is primarily disseminated through the publication of articles in academic journals, and the release of articles on preprint servers. So far two articles have been published, and two preprints articles have been released. A further article is also being worked towards. In addition, several different talks and conference posters have been presented covering the work presented i","cbCaidieC9J6zyah","https://ap.wps.com/l/cbCaidieC9J6zyah","pdf",25956711,1,214,"English","en",105,"# Introduction\n# Variational Autoencoders for Protein Sequence Design\n# AlphaFold Performance on De Novo Designed Sequences\n# Protein Sequence Language Models on Synthetic Sequences\n# Fixed-Backbone Design with AlphaFold-Guided Optimization\n# Contributions and Conclusions","[{\"question\":\"What is the main goal of this thesis?\",\"answer\":\"To develop deep generative machine learning methods that computationally design novel protein sequences and structures for de novo protein design tasks.\"},{\"question\":\"How does the thesis assess the structures of generated proteins?\",\"answer\":\"It analyzes performance of state-of-the-art protein structure prediction algorithms, with primary focus on AlphaFold, on previously de novo designed sequences.\"},{\"question\":\"What design strategy is explored for fixed-backbone protein design?\",\"answer\":\"It uses greedy sequence optimization of AlphaFold structure predictions for fixed-backbone protein design, leveraging models trained in earlier chapters and includes initial in vitro validation of designed sequences.\"}]","De Novo Protein Design using Generative Machine Learning | PDF",1785808419,539,{"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},"de-novo-protein-design-using-generative-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/de-novo-protein-design-using-generative-machine-learning/122034/",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","2026-08-04",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},"What is the main goal of this thesis?","Question",{"text":75,"@type":76},"To develop deep generative machine learning methods that computationally design novel protein sequences and structures for de novo protein design tasks.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the thesis assess the structures of generated proteins?",{"text":80,"@type":76},"It analyzes performance of state-of-the-art protein structure prediction algorithms, with primary focus on AlphaFold, on previously de novo designed sequences.",{"name":82,"@type":73,"acceptedAnswer":83},"What design strategy is explored for fixed-backbone protein design?",{"text":84,"@type":76},"It uses greedy sequence optimization of AlphaFold structure predictions for fixed-backbone protein design, leveraging models trained in earlier chapters and includes initial in vitro validation of designed sequences.","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"]