[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118561-en":3,"doc-seo-118561-105":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},118561,13056703019662,"Evangeline","https://ap-avatar.wpscdn.com/avatar/be000253a8e92610077?_k=1778726343310543188",8,"Research & Report","Advancing Molecular Machine Learning Representations with Stereoelectronics-Infused Molecular Graphs","Molecular representation underpins physical understanding and modern molecular machine learning, yet many existing methods rely on information-sparse formats such as strings, fingerprints, global descriptors, or simple molecular graphs. This work proposes stereoelectronics-infused molecular graphs by injecting quantum-chemical-rich information through stereoelectronic effects. A tailored double graph neural network workflow learns and applies the infused representation to downstream tasks without costly quantum-chemical calculations. Results show sizable gains for message-passing 2D models, strong extrapolation from small to much larger molecules, and chemical insight into orbital interactions in previously intractable systems including proteins. A companion web application enables rapid user exploration.","Lawrence Berkeley National Laboratory  \nLBL Publications  \nTitle  \nAdvancing molecular machine learning representations with stereoelectronics-infused molecular graphs  \nPermalink  \n[https://escholarship.org/uc/item/4z75t755](https://escholarship.org/uc/item/4z75t755)  \nJournal  \nNature Machine Intelligence, 7(5)  \nISSN  \n2522-5839  \nAuthors  \nBoiko, Daniil A  \nReschützegger, Thiago Sanchez-Lengeling, Benjamin et al.  \nPublication Date  \n2025-05-01  \nDOI  \n10.1038/s42256-025-01031-9  \nCopyright Information  \nThis work is made available under the terms of a Creative Commons Attribution License, available at [https://creativecommons.org/licenses/by/4.0/](https://creativecommons.org/licenses/by/4.0/)  \nPeer reviewed  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \nAdvancing Molecular Machine Learning Representations with Stereoelectronics-Infused Molecular Graphs  \nDaniil A. Boiko,1 Thiago Reschützegger,2 Benjamin Sanchez-Lengeling,3,4,5 Samuel M. Blau,*6 Gabe Gomes*1,7,8,9  \n1. Department of Chemical Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA  \n2. Department of Chemical Engineering, Federal University of Santa Maria, Santa Maria, RS, Brazil 3. Google DeepMind, Cambridge, MA, USA (previous affiliation, where most of this work was done)  \n4. Department of Chemical Engineering and Applied Chemistry, University of Toronto, Toronto, ON M5S 3E5, Canada (current affiliation)  \n5. Vector Institute for Artificial Intelligence, Toronto, ON, Canada (current affiliation)  \n6. Energy Technologies Area, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USA  \n7. Department of Chemistry, Carnegie Mellon University, Pittsburgh, PA 15213, USA  \n8. Machine Learning Department, Carnegie Mellon University, Pittsburgh, PA 15213, USA  \n9. Wilton E. Scott Institute for Energy Innovation, Carnegie Mellon University, Pittsburgh, PA 15213, USA  \n* [corresponding authors: ](corresponding authors: smblau@lbl.gov)[smblau@lbl.gov](corresponding authors: smblau@lbl.gov), [gabegomes@cmu.edu](gabegomes@cmu.edu)  \nAbstract  \nMolecular representation is a critical element in our understanding of the physical world and the foundation for modern molecular machine learning. Previous molecular machine learning models have employed strings, fingerprints, global features, and simple molecular graphs that are inherently information-sparse representations. However, as the complexity of prediction tasks increases, the molecular representation needs to encode higher fidelity information. This work introduces a novel approach to infusing quantumchemical-rich information into molecular graphs via stereoelectronic effects, enhancing expressivity and interpretability. Learning to predict the stereoelectronics-infused representation with a tailored double graph neural network workflow enables its application to any downstream molecular machine learning task without expensive quantum chemical calculations. We show that the explicit addition of stereoelectronic information significantly improves the performance of message-passing 2D machine learning models for molecular property prediction. We show that the learned representations trained on small molecules can accurately extrapolate to much larger molecular structures, yielding chemical insight into orbital interactions for previously intractable systems, such as entire proteins, opening new avenues of molecular design. Finally, we have developed a web application ([simg.cheme.cmu.edu](simg.cheme.cmu.edu)) where users can rapidly explore stereoelectronic information for their own molecular systems.  \nKeywords  \nMolecular machine learning, graph neural networks, molecular properties, deep learning, quantum chemistry, active learning  \nIntroduction  \nMolecular representation is a cornerstone in chemistry. 1,2 Following chemists' intuition, skeletal structures became the chemical lingua franca. They allow us to capture the wide diversity of","cbCaipegbNsod466","https://ap.wps.com/l/cbCaipegbNsod466","pdf",6242941,1,35,"English","en",105,"# Abstract\n# Introduction\n## Molecular representation as a foundation for chemistry and ML\n## Molecular property prediction and the role of representations\n## Existing representation types and symmetry considerations\n## Motivation for stereoelectronics-infused molecular graphs","[{\"question\":\"What limitation of current molecular ML representations does the paper address?\",\"answer\":\"The work targets information-sparse representations such as strings, fingerprints, global features, and simple molecular graphs, which become insufficient as prediction tasks grow more complex.\"},{\"question\":\"How does the proposed method incorporate stereoelectronic information?\",\"answer\":\"It infuses quantum-chemical-rich information into molecular graphs using stereoelectronic effects, then learns the infused representation via a tailored double graph neural network workflow.\"},{\"question\":\"Can the learned representations be used without expensive quantum chemical calculations?\",\"answer\":\"Yes. The paper states the approach enables applying the stereoelectronics-infused representation to downstream tasks without performing costly quantum chemical calculations.\"}]","Advancing Molecular Machine Learning Representations with Stereoelectronics-Infused Molecular Graphs | PDF",1785684219,88,{"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},"advancing-molecular-machine-learning-representations-with-stereoelectronics-infused-molecular-graphs","",{"@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/advancing-molecular-machine-learning-representations-with-stereoelectronics-infused-molecular-graphs/118561/",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 limitation of current molecular ML representations does the paper address?","Question",{"text":75,"@type":76},"The work targets information-sparse representations such as strings, fingerprints, global features, and simple molecular graphs, which become insufficient as prediction tasks grow more complex.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed method incorporate stereoelectronic information?",{"text":80,"@type":76},"It infuses quantum-chemical-rich information into molecular graphs using stereoelectronic effects, then learns the infused representation via a tailored double graph neural network workflow.",{"name":82,"@type":73,"acceptedAnswer":83},"Can the learned representations be used without expensive quantum chemical calculations?",{"text":84,"@type":76},"Yes. The paper states the approach enables applying the stereoelectronics-infused representation to downstream tasks without performing costly quantum chemical calculations.","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"]