[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126035-en":3,"doc-seo-126035-105":31,"detail-sidebar-cat-0-en-105":84},{"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},126035,2336474466412,"Ezra","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Machine learning for the design of protein–protein interactions","Protein–protein interactions are critical for biological processes, and specific interaction properties influence the development and potential treatment of diseases such as cancer or stroke. The master’s thesis addresses the lack of reliable engineering tools for protein interfaces by applying modern machine-learning approaches. It reviews current state-of-the-art methods, analyzes their limitations and benefits, and proposes improvements, including self-supervised geometric deep learning. The selected tools and model are applied to staphylokinase, a promising thrombolytic drug candidate.","Assignment of master’s thesis  \nTitle: Machine learning for the design of protein–protein interactions  \nStudent: Bc. Anton Bushuiev  \nSupervisor: Dr. Ing. Josef Šivic  \nStudy program: Informatics  \nBranch / specialization: Knowledge Engineering  \nDepartment: Department of Applied Mathematics  \nValidity: until the end of summer semester 2023/2024  \nInstructions  \nProtein–protein interactions are essential for biological processes. The development and possible treatment of diseases, such as cancer or stroke, are directly linked to specific properties of involved protein–protein interactions (Leader et al., 2008; Nikitin et al., 2022). Therefore, the design of proteins with desired binding properties is a central challenge for pharmacology. While several attempts at tackling this problem using machine learning have been made, the domain is relatively new, and there is still no reliable tool for engineering protein–protein interfaces. The thesis aims to approach this challenge using modern machine learning (Bronstein et al., 2021). More specifically, the objectives of the project are to:  \n1. Review state-of-the-art machine-learning methods for the design of protein interactions. Identify their limitations and benefits.  \n2. Explore the possibilities for addressing the identified limitations and improving the state-of-the-art methods for designing protein interactions. For example, a promising direction is self-supervised geometric deep learning from unlabeled crystallized protein–  \nprotein interactions to learn a new powerful neural base representation for protein interaction tasks.  \n3. Apply the selected representative tools and (optionally) the proposed new model to staphylokinase, a promising thrombolytic drug candidate.  \nElectronically approved by Ing. Magda Friedjungová, Ph.D. on 3 February 2023 in Prague.  \nMaster’s thesis  \nMachine learning for the design of protein–protein interactions  \nAnton Bushuiev  \nDepartment of Applied Mathematics  \nSupervisors: Dr. Josef ˇSivic, Dr. Stanislav Mazurenko, Dr. Ji Sedl  \nMay 4, 2023  \nAcknowledgements  \nFirst of all, I would like to express my lifelong gratitude to my parents for making my education possible and for all their support.  \nI am deeply grateful to Dr. Josef ˇSivic for providing me with the unique opportunity to work on this exciting project and for being an outstanding scientific advisor. I am sincerely thankful to Dr. Stanislav Mazurenko for his excellent cosupervision and the unique multidisciplinary expertise he has shared with me. I would also like to express my deep appreciation to Dr. Ji Sedl and Petr Kouba for their help and intellectual contribution to the development of the project.  \nLastly, I want to convey my utmost appreciation to Prof. JiDamborsk´y, MUDr. Jan Mian, and Dr. David Bedn for all the insightful discussions on the problematics of protein design, which have been strongly enhancing my understanding of the domain.  \nThis work was supported by the Ministry of Education, Youth and Sports of the Czech Republic through the e-INFRA CZ (ID:90140) and also by the project National Institute for Neurological Research (Programme EXCELES, ID Project No. LX22NPO5107) -Funded by the European Union – Next Generation EU.  \nDeclaration  \nI hereby declare that the presented thesis is my own work and that I have cited all sources of information in accordance with the Guideline for adhering to ethical principles when elaborating an academic final thesis.  \nI acknowledge that my thesis is subject to the rights and obligations stipulated by the Act No. 121/2000 Coll., the Copyright Act, as amended, in particular that the Czech Technical University in Prague has the right to conclude a license agreement on the utilization of this thesis as a school work under the provisions of Article 60 (1) of the Act.  \nIn Prague on May 4, 2023 . . .. . .. . .. . .. . .. . .. . .  \nCzech Technical University in Prague  \nFaculty of Information Technology  \n© 2023 Anton Bushuiev. All righ","cbCaimFz0khAK7ds","https://ap.wps.com/l/cbCaimFz0khAK7ds","pdf",13249243,4,1,101,"English","en",105,"# Instructions\n## Objectives\n## Acknowledgements\n## Declaration\n## Citation of this thesis\n## Abstrakt / Abstract","[{\"question\":\"How does the thesis propose to improve existing methods?\",\"answer\":\"A promising direction highlighted is self-supervised geometric deep learning trained from unlabeled crystallized protein–protein interaction data to learn strong neural representations for interaction tasks.\"}]","Machine learning for the design of protein–protein interactions | PDF",1785902658,255,{"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":79,"head_meta":81,"extra_data":83,"updated_unix":29},"machine-learning-for-the-design-of-proteinprotein-interactions","",{"@graph":37,"@context":78},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":20},"https://docshare.wps.com/document/machine-learning-for-the-design-of-proteinprotein-interactions/126035/",{"url":53,"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","2026-08-22","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72],{"name":73,"@type":74,"acceptedAnswer":75},"How does the thesis propose to improve existing methods?","Question",{"text":76,"@type":77},"A promising direction highlighted is self-supervised geometric deep learning trained from unlabeled crystallized protein–protein interaction data to learn strong neural representations for interaction tasks.","Answer","https://schema.org",{"og:url":53,"og:type":80,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":82,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":85},[86,90,94,98,103,108,113,116,121,124,128],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":87,"show_sort_weight":88,"slug":89},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":91,"show_sort_weight":92,"slug":93},"Literature",80,"literature",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Exam",70,"exam",{"id":99,"doc_module":4,"doc_module_name":47,"category_name":100,"show_sort_weight":101,"slug":102},5,"Comic",60,"comic",{"id":104,"doc_module":4,"doc_module_name":47,"category_name":105,"show_sort_weight":106,"slug":107},6,"Technology",50,"technology",{"id":109,"doc_module":4,"doc_module_name":47,"category_name":110,"show_sort_weight":111,"slug":112},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":114,"slug":115},30,"research-report",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},9,"Religion & Spirituality",20,"religion-spirituality",{"id":119,"doc_module":4,"doc_module_name":47,"category_name":122,"show_sort_weight":119,"slug":123},"World Cup","world-cup",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":125,"slug":127},10,"Lifestyle","lifestyle",{"id":129,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":99,"slug":131},19,"General","general"]