[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117180-en":3,"doc-seo-117180-105":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},117180,4398048950312,"Violet","https://ap-avatar.wpscdn.com/avatar/400002538284de19e3c?_k=1778320343897328908",8,"Research & Report","Machine learning models for the discovery of new plastics degradation enzymes - Thesis","Plastic pollution has emerged as a global environmental challenge, requiring innovative strategies to curb the accumulation of plastic waste. This thesis investigates PET degradation via microbial action by searching for microbial enzymes able to break down plastics, with special focus on polyethylene terephthalate (PET). It develops machine learning models that identify PET-degrading enzymes from a pool of available proteins. Protein sequence and structure are converted into numerical representations, then used to train semi-supervised classification models distinguishing PET degraders from others. Experimental validations on a representative protein set show strong performance, especially for sequence-based approaches. The results indicate these models can detect key molecular markers of PET degradation and predict unknown PET-degrading enzymes from microorganisms adapted to heavily plastic-polluted environments.","University of Padova  \nDepartment of Mathematics  \nMaster Thesis in Data science  \nMachine learning models for the  \ndiscovery of new plastics degradation  \nenzymes  \nSupervisor Master Candidate  \nGuido Zampieri Stefano Minto  \nUniversity of Padova  \nCo-supervisor  \nAcademic Year  \n2023-2024  \nii  \nDedication.  \nKhoya andiamo avanti  \niv  \nAbstract  \nPlastic pollution has emerged as a global environmental challenge, prompting the need for innovative strategies to address the mounting accumulation of plastic waste, such as bioremediation through living organisms like bacteria, fungi, or plants to break down or neutralize pollutants in the environment. This thesis explores the promising avenue of plastic degradation through microbial action, focusing on the search for microbial enzymes capable of breaking down plastics, with a particular emphasis on polyethylene terephthalate (PET) . The goal of this work is to develop machine learning models able to identify enzymes for PET degradation in a pool of available proteins. Protein sequence and structure serve as complementary sources of information for creating numerical representations for each protein under analysis. These numerical representations are then used to train semi-supervised classi昀椀cation models capable of distinguishing PET-degrading proteins from others. Experimental validations on a representative protein set yield high performances for all the tested models, particularly those that incorporate sequence information. The results suggest that these methods can detect crucial molecular markers associated with the ability to degrade PET in both information sources, allowing the prediction of unknown PET-degrading enzymes coming from microorganisms adapted in heavily plastic-polluted environments.  \nvi  \nContents  \nAbstract v  \nList of figures ix  \nList of tables xi  \nListing of acronyms xiii  \n1 Introduction 1  \n1.1 Plastic degradation .............................. 2  \n1.2 Biodegradation of plastic ........................... 3  \n1.3 PET and its possible biodegradation ..................... 4  \n1.3.1 Identi昀椀cation of PET-degrading enzymes ............... 5  \n1.3.2 Engineering of hydrolase for PET depolymerization ......... 6  \n1.4 Aim of the work ................................ 6  \n2 Data and Methods 9  \n2. 1 Data . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11  \n2.2 AlphaFold2 .................................. 13  \n2.3 From sequence to vector ............................ 17  \n2.3.1 BERT ................................. 18  \n2.3.2 ESM1b : a BERT-based model .................... 23  \n2.4 From graph to vector ............................. 24  \n2.4.1 Graph2vec .............................. 24  \n2.4. 2 GL2vec   26  \n2.4.3 FeatherGraph ............................. 27  \n2.4.4 Wavelets-Based graph embedding ................... 29  \n2.5 Semi-supervised learning : label propagation ................. 30  \n2.6 Dimensionality reduction : t-SNE ....................... 33  \n2.7 Metrics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 33  \n2.8 Software .................................... 35  \n3 Results 37  \n3.1 Sequence embedding approach ........................ 39  \n3.2 Graph embedding approach .......................... 43  \n3.3 Combined sequence and graph embedding approach ............. 49  \n4 Conclusion 51  \nReferences 53  \nAcknowledgments 57  \nListing of昀椀gures  \n1.1 Although a portion of plastic is e昀케ciently recycled an important of it reach the environment where it can be degraded by both biotioc and abiotic factors. 2  \n2.1 model structure ................................ 10  \n2.2 Diagram of AlphaFold2 published in the o昀케cial Nature paper[1] ....... 14  \n2.3 Schematic of how co-evolution extract information about protein structure from a MSA. Image taken from Marks DS et al. [2] .............. 15  \n2.4 Protein structures of human myoglobin (top left), african elephant myoglobin (top right, 80% sequence identity","cbCairFOqtXp7ooy","https://ap.wps.com/l/cbCairFOqtXp7ooy","pdf",2056914,1,71,"English","en",105,"# Abstract\n# Introduction\n## Plastic degradation\n## Biodegradation of plastic\n## PET and its possible biodegradation\n## Aim of the work\n# Data and Methods\n## Data\n## AlphaFold2\n## From sequence to vector\n## From graph to vector\n## Semi-supervised learning: label propagation\n## Dimensionality reduction: t-SNE\n## Metrics\n## Software\n# Results\n## Sequence embedding approach\n## Graph embedding approach\n## Combined sequence and graph embedding approach\n# Conclusion\n# References\n# Acknowledgments","[{\"question\":\"What environmental problem motivates this thesis?\",\"answer\":\"The work is motivated by plastic pollution and the growing accumulation of plastic waste in the environment.\"},{\"question\":\"How does the thesis approach discovering PET-degrading enzymes?\",\"answer\":\"It builds machine learning models that learn from numerical representations derived from protein sequence and structure, then classifies proteins as PET-degrading or not using semi-supervised learning.\"},{\"question\":\"What do the experimental results show about model performance?\",\"answer\":\"Validations on a representative protein set achieve high performance across tested models, with particularly strong results for methods incorporating sequence information.\"}]","Machine learning models for the discovery of new plastics degradation enzymes - Thesis | PDF",1785674247,179,{"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},"machine-learning-models-for-the-discovery-of-new-plastics-degradation-enzymes-thesis","",{"@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/machine-learning-models-for-the-discovery-of-new-plastics-degradation-enzymes-thesis/117180/",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},"What environmental problem motivates this thesis?","Question",{"text":75,"@type":76},"The work is motivated by plastic pollution and the growing accumulation of plastic waste in the environment.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the thesis approach discovering PET-degrading enzymes?",{"text":80,"@type":76},"It builds machine learning models that learn from numerical representations derived from protein sequence and structure, then classifies proteins as PET-degrading or not using semi-supervised learning.",{"name":82,"@type":73,"acceptedAnswer":83},"What do the experimental results show about model performance?",{"text":84,"@type":76},"Validations on a representative protein set achieve high performance across tested models, with particularly strong results for methods incorporating sequence information.","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"]