[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119703-en":3,"doc-seo-119703-105":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},119703,1099513958762,"Logic","https://ap-avatar.wpscdn.com/avatar/1000023916a998db790?x-image-process=image/resize,m_fixed,w_180,h_180&k=1784791008015729253",8,"Research & Report","Knowledge-Augmented Graph Machine Learning for Drug Discovery - A Survey","Artificial Intelligence is increasingly applied to drug discovery, yet conventional models struggle with complex biomedical structures such as 2D/3D proteins and molecules and with interpreting their outputs, limiting practical deployment. Graph Machine Learning (GML) has drawn attention for modeling graph-structured biomedical data and capturing functional relationships. Nevertheless, current GML remains constrained by sparse supervision, limited interpretability, and weak use of domain knowledge. This survey systematizes Knowledge-augmented Graph Machine Learning (KaGML), reviews foundational principles, and summarizes methods under a new taxonomy while highlighting future research directions and practical resources.","arXiv :2302 .0826 1v2 [ cs .LG] 7 Mar 2023  \nKNOWLEDGE-AUGMENTED GRAPH MACHINE LEARNING  \nFOR DRUG DISCOVERY  \nA SURVEY FROM PRECISION TO INTERPRETABILITY  \nZhiqiang Zhong  \nAarhus University [zzhong@cs.au.dk](zzhong@cs.au.dk)  \nAnastasia Barkova  \nWhiteLab Genomics  \n[abarkova@whitelabgx.com](abarkova@whitelabgx.com)  \nDavide Mottin  \nAarhus University [davide@cs.au.dk](davide@cs.au.dk)  \nMarch 8, 2023  \nABSTRACT  \nThe integration of Artificial Intelligence (AI) into the field of drug discovery has been a growing area of interdisciplinary scientific research. However, conventional AI models are heavily limited in handling complex biomedical structures (such as 2D or 3D protein and molecule structures) and providing interpretations for outputs, which hinders their practical application. As of late, Graph Machine Learning (GML) has gained considerable attention for its exceptional ability to model graph-structured biomedical data and investigate their properties and functional relationships.  \nDespite extensive efforts, GML methods still suffer from several deficiencies, such as the limited ability to handle supervision sparsity and provide interpretability in learning and inference processes, and their ineffectiveness in utilising relevant domain knowledge. In response, recent studies have proposed integrating external biomedical knowledge into the GML pipeline to realise more precise and interpretable drug discovery with limited training instances. However, a systematic definition for this burgeoning research direction is yet to be established. This survey presents a comprehensive overview of long-standing drug discovery principles, provides the foundational concepts and cutting-edge techniques for graph-structured data and knowledge databases, and formally summarises Knowledgeaugmented Graph Machine Learning (KaGML) for drug discovery. we propose a thorough review of related KaGML works, collected following a carefully designed search methodology, and organise them into four categories following a novel-defined taxonomy. To facilitate research in this promptly emerging field, we also share collected practical resources that are valuable for intelligent drug discovery and provide an in-depth discussion of the potential avenues for future advancements.  \n1 Introduction  \nDrug discovery and development have been one of the most prominent and challenging research tasks for decades [1, 2, 3] . Prior to a drug being marketed and distributed to patients, it must undergo a multitude of research validations. From initial early drug discovery to preclinical development, and subsequent to clinical trials and final regulatory approval, it usually takes 10-15 years and costs around 2 billion US dollars [4, 5, 6] . To reduce the financial burden and increase the success rate, researchers have been working on accelerating drug discovery by taking advantage of Artificial Intelligence (AI) techniques [7, 8, 9, 10, 11] . Technological advances now allow for the creation of vast amounts of data in areas such as genomics, proteomics, and imaging, which can be used to inform the drug discovery process [9, 12] . Biomedical data is highly interconnected [13, 14] and can be easily represented as graphs (or networks), which have a variety of applications at different stages of the drug discovery and development process. For instance, as illustrated in Figure 1-(a), biomedical data can be hierarchically represented as graphs. Starting from the molecular level, atoms can be represented as nodes, and chemical bonds as edges of (2D or 3D) molecular graphs [15, 16] . On the macro-molecule level, interactions (edges) between amino acid residues (nodes) organise as (2D or 3D) protein graphs [17, 18] . At the compound level, edges in the drug-drug interaction (DDI) network can indicate chemical interactions (edges) between drugs (nodes) measured by long-term clinical screens [19, 20] .  \nA PREPRINT-MARCH 8, 2023  \n(a) Biomedical Data are Graphs  \nMolecule Network Pro","cbCaib8uVkKFHqDo","https://ap.wps.com/l/cbCaib8uVkKFHqDo","pdf",3218434,1,37,"English","en",105,"# Introduction\n## Drug discovery pipeline and motivation for AI\n## Graph representation of biomedical data\n## Graph Machine Learning and Graph Neural Networks","[{\"question\":\"Why do conventional AI models face challenges in drug discovery?\",\"answer\":\"They are limited in handling complex biomedical structures like 2D/3D protein and molecule representations and in providing interpretations for their outputs, which hinders practical use.\"},{\"question\":\"What strengths does Graph Machine Learning (GML) offer for drug discovery?\",\"answer\":\"GML can model graph-structured biomedical data and analyze properties and functional relationships within such graphs.\"},{\"question\":\"What deficiencies motivate Knowledge-augmented Graph Machine Learning (KaGML)?\",\"answer\":\"GML methods still struggle with supervision sparsity, interpretability during learning and inference, and insufficient utilization of relevant domain knowledge; KaGML integrates external biomedical knowledge to improve precision and interpretability with limited training instances.\"}]","Knowledge-Augmented Graph Machine Learning for Drug Discovery - A Survey | PDF",1785725862,93,{"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},"knowledge-augmented-graph-machine-learning-for-drug-discovery-a-survey","",{"@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/knowledge-augmented-graph-machine-learning-for-drug-discovery-a-survey/119703/",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":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why do conventional AI models face challenges in drug discovery?","Question",{"text":75,"@type":76},"They are limited in handling complex biomedical structures like 2D/3D protein and molecule representations and in providing interpretations for their outputs, which hinders practical use.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What strengths does Graph Machine Learning (GML) offer for drug discovery?",{"text":80,"@type":76},"GML can model graph-structured biomedical data and analyze properties and functional relationships within such graphs.",{"name":82,"@type":73,"acceptedAnswer":83},"What deficiencies motivate Knowledge-augmented Graph Machine Learning (KaGML)?",{"text":84,"@type":76},"GML methods still struggle with supervision sparsity, interpretability during learning and inference, and insufficient utilization of relevant domain knowledge; KaGML integrates external biomedical knowledge to improve precision and interpretability with limited training instances.","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"]