[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122273-en":3,"doc-seo-122273-105":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},122273,1099514067415,"Rowan","https://ap-avatar.wpscdn.com/avatar/100002539d78ffe74a7?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779092875211072502",8,"Research & Report","A Study of Machine Learning for Artificial Intelligence-Based Enzyme Classification","Enzyme Commission (EC) number prediction models estimate enzyme function from sequence information by mapping sequences to five EC levels, where level 0 indicates whether a sequence is an enzyme and levels 1–4 correspond to EC digits. Most approaches apply machine learning while keeping a fixed model structure across digits, despite varying data composition. Creating separate optimized pipelines per digit is costly, motivating automated ML.","Ana Patrícia Fernandes Brás da Silva  \nMSc in Integrated Studies of the Oceans  \nA Study of Machine Learning for Artificial Intelligence-Based Enzyme Classification.  \nNov, 2023  \nAna Patrícia Fernandes Brás da Silva  \nGraduated in Integrated Studies of the Oceans  \nA Study of Machine Learning for Artificial Intelligence-Based Enzyme  \nClassification.  \nDissertation to obtain the Master’s Degree in Computational Biology and Bioinformatics  \nSupervisor: Leonardo Vanneschi, Professor , NOVA IMS  \nCo-Supervisor: Isabel Rocha, Professor , ITQB NOVA  \nJury:  \nPresident: Diana Lousa, Principal Researcher, ITQB NOVA  \nOpponent: Nuno Lourenço, Assistant Professor, DEI Coimbra  \nUniversity  \nInstituto de Tecnologia Química e Biológica António Xavier  \nNovember of 2023  \nCopyright  \nO documento A Study of Machine Learning for Artificial Intelligence-Based Enzyme Classification foi redigido por mim, Ana Patrícia Fernandes Brás da Silva, e declaro que são aplicáveis as diretivas de direito de cópia conforme os termos e regulamentos em vigor no Instituto de Tecnologia Química e Biológica António Xavier.  \nO Instituto de Tecnologia Química e Biológica António Xavier e a Universidade Nova de Lisboatêm o direito, perpétuo e sem limites geográficos, de arquivar e publicar esta dissertação através de exemplares impressos reproduzidos em papel ou de forma digital, ou por qualquer outro meioconhecido ou que venha a ser inventado, e de a divulgar através de repositórios científicos e de admitira sua cópia e distribuição com objetivos educacionais ou de investigação, não comerciais, desde que seja dado crédito ao autor e editor.  \nAcknowledgements  \nI would like to first and foremost thank both my supervisors Professor Leonardo Vanneschi and Professor Isabel Rocha for the opportunity to do this thesis and for guiding me throughout the length of the project.  \nI would like to thank Professor Diana and Professor Manuel for helping me at the beginning with the data and code for running in the cluster system. With the end of this project I have now stopped haunting the cluster system with my presence , freeing up several computers. For now at least. I am also grateful to Davide Farinari for taking the time to explain how to run the TPOT algorithm best.  \nFor the people in the SSBio lab , thank you for being such good company and colleagues and showing me the wonder that is Zé Varunca. My weight and wallet have still not recovered.  \nSeveral close friends had to suffer through my excessive talks about this dissertation and my appreciation for their patience and support cannot be measured. Andreia R. , Andreia P. , Querido, Daniela e Leonor, my life would be poorer without knowing you guys. A special shoutout has to be given to a friend I got while doing this masters. Victoria Gil, I am so glad to have met you and your friendship made this masters more enjoyable.  \nFinally, I wish to thank my family. My grandparents who have always been supportive, if a bit confused on what I’m actually doing. My brother, who let me borrow his gaming computer to run a few experiments that my laptop couldn’t handle. My dad for always convincing me to get some fresh air by bribing me with delicious food and restaurants. And finally my mom, who had to deal with her son, daughter and husband discussing algorithms and programming at the dinner table.  \nThank you all.  \nAbstract  \nEnzyme Commission (EC) numbers prediction models allow for the prediction of an enzyme’s function by using only its sequence. They typically have 5 Levels with Level 0 to distinguish if the sequence is an enzyme and the Levels 1 to 4 analogous to each EC number digit. For the most part, these models use machine learning (ML) methods in order to predict the EC numbers, keeping the same structure across the four digits, despite the difference in data composition through the digits. With the hundreds of EC number combinations possible, creating a new ML pipeline for each EC number digit has been impract","cbCaieBbtelc0Cgu","https://ap.wps.com/l/cbCaieBbtelc0Cgu","pdf",2062814,1,83,"English","en",105,"# Acknowledgements\n## Abstract\n## Keywords","[{\"question\":\"How do EC number prediction models use enzyme sequences?\",\"answer\":\"They predict enzyme function from sequence alone by assigning labels across five EC levels, with level 0 indicating enzyme presence and levels 1–4 matching EC number digits.\"},{\"question\":\"Why is it difficult to build an optimized ML pipeline for every EC digit?\",\"answer\":\"With hundreds of possible EC combinations, optimizing a separate pipeline per digit for each class requires substantial time and domain expertise.\"},{\"question\":\"What role does TPOT play in this work?\",\"answer\":\"TPOT is used to automatically create and optimize machine learning pipelines via genetic programming, enabling faster generation of personalized pipelines for EC digit prediction.\"}]","A Study of Machine Learning for Artificial Intelligence-Based Enzyme Classification | PDF",1785809769,209,{"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},"a-study-of-machine-learning-for-artificial-intelligence-based-enzyme-classification","",{"@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/a-study-of-machine-learning-for-artificial-intelligence-based-enzyme-classification/122273/",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},"How do EC number prediction models use enzyme sequences?","Question",{"text":75,"@type":76},"They predict enzyme function from sequence alone by assigning labels across five EC levels, with level 0 indicating enzyme presence and levels 1–4 matching EC number digits.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Why is it difficult to build an optimized ML pipeline for every EC digit?",{"text":80,"@type":76},"With hundreds of possible EC combinations, optimizing a separate pipeline per digit for each class requires substantial time and domain expertise.",{"name":82,"@type":73,"acceptedAnswer":83},"What role does TPOT play in this work?",{"text":84,"@type":76},"TPOT is used to automatically create and optimize machine learning pipelines via genetic programming, enabling faster generation of personalized pipelines for EC digit prediction.","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"]