[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128148-en":3,"doc-seo-128148-105":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},128148,549768072016,"River Wang","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Machine Learning for Protein Engineering Using Molecular Dynamics Simulation Data - dissertation","Protein therapies and enzymes have transformed pharmaceutical and biotechnology industries, yet protein engineering with evolutionary methods remains labor-intensive and difficult to scale. Molecular Dynamics (MD) simulations provide rich insights into protein properties, but MD data interpretation is sensitive and subjective. Machine Learning (ML) can infer cause-and-effect patterns, though performance depends on data quality and volume. This thesis builds a pipeline that uses MD-generated variant structures as ML training data. More than 1600 trajectories from 312 enterokinase variants support dataset construction and validation, enabling testing of over 40 supervised ML algorithms.","Machine Learning for Protein Engineering Using Molecular Dynamics Simulation Data  \nNiccolò Alberto Elia Venanzi  \nA dissertation submitted in partial fulfillment of the requirements for the degree of  \nDoctor of Philosophy  \nof  \nUniversity College London.  \nDepartment of Biochemical Engineering University College London  \nFebruary 23, 2024  \n2  \nI, Niccolò Alberto Elia Venanzi, confirm that the work presented in this thesis is my own. Where information has been derived from other sources, I  \nconfirm that this has been indicated in the work.  \nAbstract  \nProtein therapies and enzymes have revolutionised the pharmaceutical and biotechnology industries. However, the scalability and labour intensity of evolutionary methods for protein engineering impede progress and still present ongoing challenges. Molecular Dynamics (MD) simulations are invaluable in researching protein properties; however, MD data require careful and subjective interpretation. Concurrently, Machine Learning (ML) algorithms have successfully elucidated cause-and-effect relationships in data, but their performances are bound by data quality and volume. This thesis delves into developing a pipeline that leverages the synergistic potential of MD simulations as a data source for ML algorithms. For this purpose, variant structures were generated, validated, and used to produce more than 1600 trajectories of 312 enterokinase variants to serve as data for ML algorithms. MD simulations were shown to be sensitive to mutations and provided comparable information across diverse simulation lengths. After selecting and validating optimal simulation parameters, datasets were constructed using MD simulation-derived data, sequence information, and structural features. These datasets were then used to test and refine over 40 supervised ML algorithms. An iterative process revealed that incorporating MD simulations enhanced the predictive capabilities of supervised ML. Interpretability techniques allowed for the identification of important features, paving the way for more targeted experimental rounds in protein engineering and setting a new standard in protein development research. As the final step, the MD data were used to build graph neural networks, and the performances of these deep learning algorithms were compared  \nAbstract 4  \nwith the previously constructed ML models. Overall, the pipeline presented here, constructed by combining the strengths of MD simulations and ML techniques, served to predict protein functions. These findings present valuable insights with the potential to reduce costs and time in protein engineering campaigns, thereby exemplifying the immense potential of ML leveraged with  \ninformation-rich data such as those derived from MD simulations.  \nAcknowledgements  \nInitially, I wrote this section without names, addressing only the groups of people who supported me through some of the most challenging years of my life. While a general acknowledgement might not offend anyone, it also would not give due credit to the specific individuals who played pivotal roles in my journey. I apologise if I have accidentally forgotten someone. Before I begin, I must emphasise that everyone mentioned here has shaped me in profound ways.  \nLao-Tze once said:  \n”Watch your thoughts; they become words.  \nWatch your words; they become actions.  \nWatch your actions; they become habits.  \nWatch your habits; they become character.  \nWatch your character; it becomes your destiny.”  \nIn light of this wisdom, I want to express my gratitude to you all. You have not only influenced my thoughts, but also guided my words and actions. Through your support, you have helped mould my habits and, in turn, my character. In essence, you have played a role in shaping my destiny.  \nIt has been a long journey, but let us unpack everything from the beginning (names are presented in no particular order) . Thanks to Alex for trusting a chemist to undertake such a challenging computational proje","cbCaihLZDVnRYo2B","https://ap.wps.com/l/cbCaihLZDVnRYo2B","pdf",29435626,2,1,261,"English","en",105,"# Abstract\n## Aims and motivation\n## MD-to-ML pipeline and dataset construction\n## Supervised ML evaluation and interpretability\n## Deep learning with graph neural networks\n# Acknowledgements","[{\"question\":\"What problem does the thesis address in protein engineering?\",\"answer\":\"It targets the scalability and labor burden of evolutionary protein-engineering approaches, alongside the challenge of interpreting MD simulation data for actionable models.\"},{\"question\":\"How is molecular dynamics simulation used in the proposed pipeline?\",\"answer\":\"MD simulations generate and validate variant structures, producing trajectories used as an information-rich data source for ML model training and refinement.\"},{\"question\":\"What machine learning approach is used and how is performance validated?\",\"answer\":\"The work tests and iteratively refines more than 40 supervised ML algorithms using datasets built from MD-derived data, sequence information, and structural features, and then compares graph neural network models built on MD data.\"}]","Machine Learning for Protein Engineering Using Molecular Dynamics Simulation Data - dissertation | PDF",1785945099,658,{"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-protein-engineering-using-molecular-dynamics-simulation-data-dissertation","",{"@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-protein-engineering-using-molecular-dynamics-simulation-data-dissertation/128148/",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","2026-08-26","2026-08-05",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 problem does the thesis address in protein engineering?","Question",{"text":76,"@type":77},"It targets the scalability and labor burden of evolutionary protein-engineering approaches, alongside the challenge of interpreting MD simulation data for actionable models.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How is molecular dynamics simulation used in the proposed pipeline?",{"text":81,"@type":77},"MD simulations generate and validate variant structures, producing trajectories used as an information-rich data source for ML model training and refinement.",{"name":83,"@type":74,"acceptedAnswer":84},"What machine learning approach is used and how is performance validated?",{"text":85,"@type":77},"The work tests and iteratively refines more than 40 supervised ML algorithms using datasets built from MD-derived data, sequence information, and structural features, and then compares graph neural network models built on MD data.","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"]