[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117155-en":3,"doc-seo-117155-105":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},117155,137441390410,"Hazel","https://ap-avatar.wpscdn.com/avatar/2000252f4ab5702993?_k=1776741390130283984",8,"Research & Report","Predicting redox potentials by graph-based machine learning methods","Accurate prediction of oxidation and reduction potentials is essential across chemistry, yet purely theoretical computations can be costly and slow compared with experimental measurements. This article tackles the problem using machine learning with emphasis on graph-based approaches, including graph edit distances, graph kernels, and graph neural networks, highlighting their connections to theoretical chemistry. It introduces the ORedOx159 database with 318 one-electron redox reactions and 159 large organic compounds and reference values from density functional theory. The study evaluates common ML models through extensive analyses on ORedOx159, showing improved in silico performance using rapidly computed descriptors, with MAE values of 5.6 kcal mol−1 for reductions and 7.2 kcal mol−1 for oxidations.","Received: 8 November 2023 Revised: 25 March 2024 Accepted: 19 April 2024  \nDOI: 10.1002/jcc.27380  \nRES EARCH A RTICLE  \nPredicting redox potentials by graph-based machine learning methods  \nLinlin Jia 1  | ric Brémond 2  | Larissa Zaida 2 | Benoit Gaüzère 3  | Vincent Tognetti 4  | Laurent Joubert 4  \n1The PRG Group, Institute of Computer Science, University of Bern, Bern, Switzerland 2Université Paris Cité, ITODYS, CNRS, Paris, France  \n3LITIS, Univ Rouen Normandie, INSA Rouen Normandie, Université Le Havre Normandie, Normandie Univ, Rouen, France 4Normandy Univ., COBRA UMR 6014 & FR 3038, Université de Rouen, INSA Rouen, CNRS, Mont St Aignan Cedex, France  \nCorrespondence  \nVincent Tognetti, Normandy Univ., COBRA UMR 6014 & FR 3038, Université de Rouen, INSA Rouen, CNRS, 1 rue Tesnière, 76821 Mont St Aignan Cedex, France. [Email: vincent.tognetti@univ-rouen.fr](Email: vincent.tognetti@univ-rouen.fr)  \nAbstract  \nThe evaluation of oxidation and reduction potentials is a pivotal task in various chemical fields. However, their accurate prediction by theoretical computations, which is a complementary task and sometimes the only alternative to experimental measurement, may be often resource-intensive and time-consuming. This paper addresses this challenge through the application of machine learning techniques, with a particular focus on graph-based methods (such as graph edit distances, graph kernels, and graph neural networks) that are reviewed to enlighten their deep links with theoretical chemistry. To this aim, we establish the ORedOx159 database, a comprehensive, homogeneous (with reference values stemming from density functional theory calculations), and reliable resource containing 318 one-electron reduction and oxidation reactions and featuring 159 large organic compounds. Subsequently, we provide an instructive overview of the good practice in machine learning and of commonly utilized machine learning models. We then assess their predictive performances on the ORedOx159 dataset through extensive analyses. Our simulations using descriptors that are computed in an almost instantaneous way result in a notable improvement in prediction accuracy, with mean absolute error (MAE) values equal to 5.6 kcal mol􀀁1 for reduction and 7 .2 kcal mol􀀁1 for oxidation potentials, which paves a way toward efficient in silico design of new electrochemical systems.  \nKEYWOR DS  \ndensity functional theory, graph-based machine learning methods, ORedOx159 database, Redox potential prediction  \n1 | INTRODUCTION  \nThe experimental optimization of chemical reagents is very often a time-consuming and financially expensive task as it requires numerous tries that can also involve hazardous compounds or complex synthetic strategies. As a consequence, the exploration of the chemical space  \nA major part of this work was done when the author was at COBRA lab, France.  \nfor a given property frequently remains limited to a small number of variations, and the fine-tuning that is performed is then far from being optimal. It is thus highly desirable to have at disposal a fast screening tool that can efficiently guide the applied chemists for the selection of the best synthetic targets.  \nNumerical techniques are certainly suitable candidates for shortcut strategies that can be led at larger scales, provided the associated computations can treat the systems both in a reasonable time and  \nThis is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.  \n© 2024 The Authors. Journal of Computational Chemistry published by Wiley Periodicals LLC.  \n2  \nJIA ET AL.  \nwith a sufficient accuracy. Advanced quantum chemistry (QC) methods, such as density functional theory (DFT) or postHartree-Fock methods, are indeed capable of achieving the latter point mentioned. However, their application to extensive compound searches is limited ","cbCaifqGHLKktvxV","https://ap.wps.com/l/cbCaifqGHLKktvxV","pdf",3778417,1,14,"English","en",105,"# Abstract\n# Introduction\n## Motivation for fast redox-potential screening\n## Limits of advanced quantum chemistry methods\n## Machine learning as a scalable alternative\n## Scope and goal of this study","[{\"question\":\"Why is predicting oxidation and reduction potentials difficult with purely theoretical computations?\",\"answer\":\"Advanced quantum chemistry methods like DFT and post-Hartree-Fock can be accurate but are computationally expensive, often requiring hours to days per molecule, which limits large-scale exploration.\"},{\"question\":\"What is the ORedOx159 database introduced in the paper?\",\"answer\":\"ORedOx159 is a homogeneous resource containing 318 one-electron reduction and oxidation reactions and 159 large organic compounds, with reference values derived from density functional theory calculations.\"},{\"question\":\"Which graph-based machine learning methods are emphasized for redox potential prediction?\",\"answer\":\"The paper focuses on graph-based techniques such as graph edit distances, graph kernels, and graph neural networks, and relates them to theoretical chemistry concepts.\"}]","Predicting redox potentials by graph-based machine learning methods | PDF",1785674146,35,{"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},"predicting-redox-potentials-by-graph-based-machine-learning-methods","",{"@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/predicting-redox-potentials-by-graph-based-machine-learning-methods/117155/",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},"Why is predicting oxidation and reduction potentials difficult with purely theoretical computations?","Question",{"text":75,"@type":76},"Advanced quantum chemistry methods like DFT and post-Hartree-Fock can be accurate but are computationally expensive, often requiring hours to days per molecule, which limits large-scale exploration.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is the ORedOx159 database introduced in the paper?",{"text":80,"@type":76},"ORedOx159 is a homogeneous resource containing 318 one-electron reduction and oxidation reactions and 159 large organic compounds, with reference values derived from density functional theory calculations.",{"name":82,"@type":73,"acceptedAnswer":83},"Which graph-based machine learning methods are emphasized for redox potential prediction?",{"text":84,"@type":76},"The paper focuses on graph-based techniques such as graph edit distances, graph kernels, and graph neural networks, and relates them to theoretical chemistry concepts.","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"]