[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128594-en":3,"doc-seo-128594-105":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},128594,962084925502,"Lucas Martin","https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8",8,"Research & Report","Machine Learning for Predictable Design of Yeast Promoters","Synthetic Biology treats living systems as an engineerable technology, enabling engineered organisms to sense and respond dynamically and to support biomanufacturing and therapeutics. Predictable design applies a workflow inspired by electronic design automation: start from functional specifications, model genetic components, and design gene circuits controlling transcription. This thesis presents gene circuit design automation to produce promoter function specifications, then uses sequence-to-function deep learning to identify suitable yeast promoters and infer promoter strength from DNA sequence.","This thesis has been submitted in fulfilment of the requirements for a postgraduate degree (e. g. PhD, MPhil, DClinPsychol) at the University of Edinburgh. Please note the following terms and conditions of use:  \n• This work is protected by copyright and other intellectual property rights, which are retained by the thesis author, unless otherwise stated.  \n• A copy can be downloaded for personal non-commercial research or study, without prior permission or charge.  \n• This thesis cannot be reproduced or quoted extensively from without first obtaining permission in writing from the author.  \n• The content must not be changed in any way or sold commercially in any format or medium without the formal permission of the author.  \n• When referring to this work, full bibliographic details including the author, title, awarding institution and date of the thesis must be given.  \nMachine Learning for Predictable Design of Yeast Promoters  \nFrederick Starkey  \nO  \nF  \nI N B  \nU  \nR  \nG  \nH  \nE  \nD  \nDoctor of Philosophy  \nTHE UNIVERSITY OF EDINBURGH  \n2023  \nAbstract  \nSynthetic Biology approaches living systems as an engineerable technology. Engineered organisms with the ability to reproduce, self-repair and evolve can sense and respond to their environment far more dynamically than machines. The efficiency with which engineered organisms can carry out chemical processes and the ease of interfacing with other biological systems opens new avenues in biomanufacturing and therapeutics as well as a new sandpit for scientific investigation.  \nPredictable Design in Synthetic Biology applies an analogous workflow to Electronic Design Automation beginning with a functional specification and identifying the arrangement and identity of components to fulfil a target function. A core aim of Synthetic Biology is to engineer gene circuits of interacting transcriptional units that control gene expression. Gene Circuit Design Automation can provide a design specification detailing the functionality of the genetic components we need to build a gene circuit. Promoters are genetic components that control transcription initiation, their function is encoded in their sequence by a genetic grammar. The possible number of Yeast promoters is enormous yet there is large variation in the comparatively tiny number of natural promoters. By utilising synthetic promoters we can greatly expand the range and specificity of gene regulatory control available for engineering applications.  \nOur Predictable Design workflow begins with a functional specification for a gene circuit consisting of time series for input signals and output protein expression. We apply Gene Circuit Design Automation to label a network graph which encodes a mathematical model for our target circuit. The output is a design specification which details the required function of the promoter components.  \nOur task now becomes the identification of appropriate Yeast promoters, using sequence-tofunction models. Firstly we delineate promoters from other sequences. We train a deep twin neural network, improving on the state-of-the-art accuracy in Yeast promoter classification. Secondly we determine the ‘strength’ of a promoter by learning a discrete probability mass function of RNA quantity from the DNA sequence.  \nBy using sequence-to-function models to score candidate promoters versus the design specification provided by Gene Circuit Design Automation, we can generate novel Yeast promoters bespoke to a gene circuit. We interrogate this process to explain how target promoter function is achieved with reference to motifs in the Yeast promoter grammar.  \nOur results demonstrate a new AI powered workflow for Synthetic Biology. Gene Circuit Design Automation produces a design specification describing the arrangement and function of the required promoters. Machine Learning models elucidate the DNA sequences of these promoters. Coupled with further work in constructing these systems using robotic biofoundries w","cbCailI9fQVohEi0","https://ap.wps.com/l/cbCailI9fQVohEi0","pdf",4236468,2,1,96,"English","en",105,"# Abstract\n## Lay Summary\n## Acknowledgements\n## Declaration","[{\"question\":\"What goal does predictable design target in synthetic biology?\",\"answer\":\"It aims to engineer gene circuits by starting from a functional specification and determining the arrangement and identity of genetic components—especially promoters—that satisfy a target function.\"},{\"question\":\"How does the workflow design promoter components for a gene circuit?\",\"answer\":\"Gene circuit design automation produces a design specification describing the required promoter function, and sequence-to-function machine learning models score candidate yeast promoters against that specification.\"},{\"question\":\"How are yeast promoter strength and function learned in this approach?\",\"answer\":\"The thesis first distinguishes promoters from other sequences using a deep twin neural network, then determines promoter “strength” by learning a discrete probability mass function of RNA quantity from the DNA sequence.\"}]","Machine Learning for Predictable Design of Yeast Promoters | PDF",1786001983,242,{"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-for-predictable-design-of-yeast-promoters","",{"@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-for-predictable-design-of-yeast-promoters/128594/",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","2026-08-23","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 goal does predictable design target in synthetic biology?","Question",{"text":76,"@type":77},"It aims to engineer gene circuits by starting from a functional specification and determining the arrangement and identity of genetic components—especially promoters—that satisfy a target function.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the workflow design promoter components for a gene circuit?",{"text":81,"@type":77},"Gene circuit design automation produces a design specification describing the required promoter function, and sequence-to-function machine learning models score candidate yeast promoters against that specification.",{"name":83,"@type":74,"acceptedAnswer":84},"How are yeast promoter strength and function learned in this approach?",{"text":85,"@type":77},"The thesis first distinguishes promoters from other sequences using a deep twin neural network, then determines promoter “strength” by learning a discrete probability mass function of RNA quantity from the DNA sequence.","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"]