[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118707-en":3,"doc-seo-118707-105":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},118707,7971461741311,"Ophelia","https://ap-avatar.wpscdn.com/avatar/74000253aff267980c6?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779345379180704826",8,"Research & Report","Molecular machine learning past the chemical Kármán Line - PhD thesis","A doctoral thesis presenting four years of research applying artificial intelligence to drug discovery, using generative AI to support idea generation, literature navigation, writing refinement, and computer-code troubleshooting while keeping all intellectual contributions human. The work studies domain-specific, chemistry-constrained molecular machine learning and analyzes potential misuse and dual-use risks, concluding existential risks are less likely than with general agentic systems. The thesis develops an approach framework and evaluates limitations via activity cliffs across multiple chapters.","Molecular machine learning past the chemical Kármán Line  \nCitation for published version (APA):  \nvan Tilborg, D. W. (2025) . Molecular machine learning past the chemical Kármán Line. [Phd Thesis 1 (Research TU/e / Graduation TU/e), Biomedical Engineering] . Eindhoven University of Technology.  \nDocument status and date:  \nPublished: 11/11/2025  \nDocument Version:  \nPublisher’s PDF, also known as Version of Record (includes final page, issue and volume numbers)  \nPlease check the document version of this publication:  \n• A submitted manuscript is the version of the article upon submission and before peer-review. There can be important differences between the submitted version and the official published version of record. People interested in the research are advised to contact the author for the final version of the publication, or visit the DOI to the publisher's website.  \n• The final author version and the galley proof are versions of the publication after peer review.  \n• The final published version features the final layout of the paper including the volume, issue and page numbers.  \nLink to publication  \nGeneral rights  \nCopyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights.  \n• Users may download and print one copy of any publication from the public portal for the purpose of private study or research.  \n• You may not further distribute the material or use it for any profit-making activity or commercial gain  \n• You may freely distribute the URL identifying the publication in the public portal.  \nIf the publication is distributed under the terms of Article 25fa of the Dutch Copyright Act, indicated by the “Taverne” license above, please follow below link for the End User Agreement:  \n[www.tue.nl/taverne](www.tue.nl/taverne)  \nTake down policy  \nIf you believe that this document breaches copyright please contact us at:  \n[openaccess@tue.nl](openaccess@tue.nl)  \nproviding details and we will investigate your claim.  \nDownload date: 28. Apr. 2026  \nMolecular machine learning  past the chemical Kármán line  \nDerek Willem van Tilborg  \nMolecular machine learning past the chemical Kármán line  \nPROEFSCHRIFT  \nter verkrijging van de graad van doctor aan de Technische Universiteit Eindhoven, op gezag van de rector magnificus prof. dr. S.K. Lenaerts, voor een commissie aangewezen door het College voor Promoties, in het openbaar te verdedigen op dinsdag 11 november 2025 om 11:00 uur  \ndoor  \nDerek Willem van Tilborg  \ngeboren te Baarle-Nassau  \nDit proefschrift is goedgekeurd door de promotoren en de samenstelling van de promotiecommissie is als volgt:  \nVoorzitter: prof. dr. M. Merkx  \n1e promoter: dr. F. Grisoni  \n2e promoter: [prof. dr. ir. L. Brunsveld](prof. dr. ir. L. Brunsveld)  \nLeden: prof. dr. J.L. Reymond (University of Bern, Switzerland)  \nprof. dr. A. Volkamer (Saarland University, Duitsland) dr. L. Albertazzi  \ndr. F. Eduati  \nHet onderzoek dat in dit proefschrift wordt beschreven is uitgevoerd in overeenstemming met de TU/e Gedragscode Wetenschapsbeoefening.  \n© 2025 D.W. van Tilborg All rights reserved.  \nISBN: 978-90-386-6518-4  \nA catalogue is available from the Eindhoven University of Technology library. Printed by Gildeprint, Enschede, The Netherlands.  \nThis research has been financially supported by the European Union (ERC, ReMINDER, 101077879), the Irene Curie Fellowship, the Federation of European Biochemical Societies, the Centre for Living Technologies, and SURF (NWO personal grants EINF-5379, EINF-9333, EINF-6669, and EINF-15347) .  \nThe use of artificial intelligence to research artificial intelligence  \nThis thesis presents four years of research on the application of artificial intelligence (AI) to drug discovery. During this period, powerful generative AI models such as Large Lang","cbCailyIpGvzY1Gh","https://ap.wps.com/l/cbCailyIpGvzY1Gh","pdf",36962745,1,277,"English","en",105,"# Chapter 1 | Aim and outline\n## 1.1 The central challenge of molecular machine learning\n## 1.2 Outline\n## 1.3 References\n# Chapter 2 | An introduction to molecular machine learning for drug discovery\n## 2.1 Drug discovery\n## 2.2 It is worse than you think\n## 2.3 Molecular encoding\n## 2.4 Molecular machine learning\n## 2.5 Low-data drug discovery\n## 2.6 References\n# Chapter 3 | Exposing the limitations of molecular machine learning with activity cliffs\n## 3.1 Abstract\n## 3.2 Introduction\n## 3.3 Study design\n## 3.4 Results\n## 3.5 Discussion\n## 3.6 Methods\n## 3.7 Supplementary material\n## 3.8 References\n# Chapter 4 | Machine learning-guided high thr","[{\"question\":\"How is AI used in the thesis research workflow?\",\"answer\":\"Generative AI models like LLMs support brainstorming, scientific literature navigation, writing refinement, and solving problems in computer code. The thesis states that LLMs are not used to write original prose or code on the author’s behalf, and intellectual contributions are human-origin.\"},{\"question\":\"What is the thesis stance on existential risks from AI?\",\"answer\":\"The thesis argues that rapidly advancing agentic models could cause large-scale disruptions, but the specific AI models explored here are domain-specific and constrained by the empirical nature of chemistry. This constraint makes existential risks considerably less likely.\"},{\"question\":\"What limitation does the thesis investigate regarding molecular machine learning?\",\"answer\":\"The thesis focuses on exposing limitations through activity cliffs, and organizes the investigation around study design, results, discussion, methods, supplementary material, and references in the relevant chapter.\"}]","Molecular machine learning past the chemical Kármán Line - PhD thesis | PDF",1785685013,698,{"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},"molecular-machine-learning-past-the-chemical-karman-line-phd-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/molecular-machine-learning-past-the-chemical-karman-line-phd-thesis/118707/",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},"How is AI used in the thesis research workflow?","Question",{"text":75,"@type":76},"Generative AI models like LLMs support brainstorming, scientific literature navigation, writing refinement, and solving problems in computer code. The thesis states that LLMs are not used to write original prose or code on the author’s behalf, and intellectual contributions are human-origin.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is the thesis stance on existential risks from AI?",{"text":80,"@type":76},"The thesis argues that rapidly advancing agentic models could cause large-scale disruptions, but the specific AI models explored here are domain-specific and constrained by the empirical nature of chemistry. This constraint makes existential risks considerably less likely.",{"name":82,"@type":73,"acceptedAnswer":83},"What limitation does the thesis investigate regarding molecular machine learning?",{"text":84,"@type":76},"The thesis focuses on exposing limitations through activity cliffs, and organizes the investigation around study design, results, discussion, methods, supplementary material, and references in the relevant chapter.","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"]