[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119476-en":3,"doc-seo-119476-105":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":20,"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},119476,962075114765,"Quinn","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Machine Learning for 3D Small Molecule Drug Discovery - Dissertation","With rapid progress in geometric machine learning and expanding biological datasets, this dissertation targets the opportunity to accelerate drug development while reducing costs through tailored machine learning methods for 3D small molecule drug discovery. It develops a neural energy minimization framework for efficient, accurate molecular conformation prediction. It then extends the approach to atom types and links it to diffusion-based generative models, introducing TargetDiff, a SE(3)-equivariant diffusion model for ligand generation for specific protein pockets. Next, it proposes LinkerNet for PROTAC linker design using diffusion plus physics-inspired fragment pose prediction when fragment poses are unknown, and presents a multi-ligand docking paradigm for improved docking to protein pockets.","© 2024 Jiaqi Guan  \nMACHINE LEARNING FOR 3D SMALL MOLECULE DRUG DISCOVERY  \nBY  \nJIAQI GUAN  \nDISSERTATION  \nSubmitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy in Computer Science in the Graduate College of the  \nUniversity of Illinois Urbana-Champaign, 2024  \nUrbana, Illinois  \nDoctoral Committee:  \nAssociate Professor Jian Peng, Chair  \nProfessor Arindam Banerjee  \nAssistant Professor Mohammed El-Kebir  \nAssociate Professor Jianzhu Ma, Tsinghua University  \nAbstract  \nWith the rapid development of geometric machine learning and the availability of everincreasing biological data, there lies a significant opportunity to expedite drug development processes and substantially reduce associated costs by employing appropriate machine learning (ML) algorithms. This dissertation introduces a suite of tailored ML algorithms aimed at addressing critical challenges in 3D small molecule drug discovery, with the overarching goal of shortening drug development cycles and enhancing drug discovery outcomes. We first investigate the fundamental molecular conformation optimization problem and present a neural energy minimization framework to efficiently and accurately predict molecular conformations. Building upon this groundwork, we extend our framework to atom types and establish connections with diffusion-based generative models. This extension facilitates the introduction of TargetDiff, a SE(3)-equivariant diffusion model to generate ligand molecules for specific protein pockets. We then focus on a specific linker design problem in ROteolysis TArgeting Chimeras (PROTACs) discovery where the fragment poses are unknown, and describe how our proposed LinkerNet addresses this problem with a diffusion model and physics-inspired fragment pose prediction module. Finally, we present a novel paradigm for molecular docking by considering multiple ligands docking to the protein pocket. Collectively, this dissertation showcases the potential of machine learning and deep generative models to revolutionize 3D small molecule drug discovery by translating data into accelerated novel discoveries.  \nAcknowledgments  \nReflecting on the entire journey of my PhD, it was not an easy path. Throughout this journey, there are too many people whom I need to express my gratitude to. At this moment of completing my dissertation, I finally have the opportunity to express my heartfelt gratitude to them.  \nFirst and foremost, I would like to express my deepest gratitude to my advisor, Professor Jian Peng. I met Jian in the summer of 2017, when I was a summer intern under his supervision. Jian’s brilliance, kindness, enthusiasm for research, and meticulous guidance left a deep impression on me. It was my first time coming to the United States, and exactly this experience solidified my determination to pursue a PhD here. Subsequently, I had the privilege of becoming Jian’s Ph.D. student. Throughout my PhD journey, Jian has consistently provided me with invaluable guidance and assistance in my research endeavors. Despite the challenges posed by the pandemic, Jian always went out of his way to help me whenever I needed it. I am forever grateful for his mentorship.  \nI also owe a great deal of gratitude to Professor Jianzhu Ma. After Jian left the school for his startup, Jianzhu became my primary mentor in research. We’ve had countless discussions about research projects, during which Jianzhu consistently offered insightful ideas and constructive feedback on projects and paper writing. His encouragement during my moments of doubt and frustration with paper submissions has been a source of strength, fostering my enthusiasm for research. Without his guidance, the milestones achieved during my doctoral studies would not have been possible. I am deeply thankful for his mentorship and unwavering support.  \nI would also like to thank my committee, Professor Arindam Banerjee and Professor Mohammed El-Kebir. Collaborating with Arindam as the ","cbCaimwb4oEYqglr","https://ap.wps.com/l/cbCaimwb4oEYqglr","pdf",16713521,1,106,"English","en",105,"# Abstract\n# Acknowledgments\n## Advisor and committee\n## Collaborators and mentors\n## Friends and dedication","[{\"question\":\"What is the main objective of the dissertation in 3D small molecule drug discovery?\",\"answer\":\"To introduce tailored machine learning algorithms that shorten drug development cycles and improve drug discovery outcomes by leveraging geometric learning and deep generative models.\"},{\"question\":\"How does the dissertation address molecular conformation optimization?\",\"answer\":\"It presents a neural energy minimization framework to efficiently and accurately predict molecular conformations.\"},{\"question\":\"What models are proposed for ligand or PROTAC-related tasks?\",\"answer\":\"It introduces TargetDiff for generating ligands for specific protein pockets using an SE(3)-equivariant diffusion model, and proposes LinkerNet for PROTAC linker design using diffusion together with physics-inspired fragment pose prediction.\"}]","Machine Learning for 3D Small Molecule Drug Discovery - Dissertation | PDF",1785724514,267,{"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-for-3d-small-molecule-drug-discovery-dissertation","",{"@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-for-3d-small-molecule-drug-discovery-dissertation/119476/",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","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is the main objective of the dissertation in 3D small molecule drug discovery?","Question",{"text":75,"@type":76},"To introduce tailored machine learning algorithms that shorten drug development cycles and improve drug discovery outcomes by leveraging geometric learning and deep generative models.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the dissertation address molecular conformation optimization?",{"text":80,"@type":76},"It presents a neural energy minimization framework to efficiently and accurately predict molecular conformations.",{"name":82,"@type":73,"acceptedAnswer":83},"What models are proposed for ligand or PROTAC-related tasks?",{"text":84,"@type":76},"It introduces TargetDiff for generating ligands for specific protein pockets using an SE(3)-equivariant diffusion model, and proposes LinkerNet for PROTAC linker design using diffusion together with physics-inspired fragment pose 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"]