[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125252-en":3,"doc-seo-125252-105":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},125252,687197207057,"Sage","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Machine Learning-Driven Optimization of Continuous-Flow Photoredox Amine Synthesis","Photoredox catalysis supports the synthesis of pharmaceutically relevant C(sp3)-rich tertiary amines, yet robust process development is difficult due to scarce mechanistic models and a large reaction space. This work applies machine learning-driven optimization of a continuous-flow tertiary amine synthesis using six continuous variables and solvent as a discrete choice. A workflow generates a priori knowledge (e.g., solubility predictions) and deploys NEMO Bayesian optimization to map a Pareto front for yield and reaction cost.","This article is licensed under CC-BY 4.0   \n[pubs.acs.org/OPRD](pubs.acs.org/OPRD)  Article   \nMachine Learning-Driven Optimization of Continuous-Flow Photoredox Amine Synthesis  \nPerman Jorayev, Sebastian Soritz, Simon Sung, Mohammed I. Jeraal, Danilo Russo, Alexandre Barthelme, Frédéric C. Toussaint, Matthew J. Gaunt, and Alexei A. Lapkin *  \n Cite This: Org. Process Res. Dev. 2025, 29, 1411−1422  \nRead Online  \n\n|  |  |  |  |  |  |\n| --- | --- | --- | --- | --- | --- |\n| ACCESS   | Metrics & More |  |  Article Recommendations |  | *sı Supporting Information |\n\nABSTRACT: Photoredox catalysis plays an important role in the synthesis of pharmaceutically relevant compounds such as C(sp3) -rich tertiary amines. The difficulty of identifying underlying mechanistic models for such novel transformations, coupled with the large reaction space of this reaction class, means that developing a robust process is challenging. In this work, we demonstrate the machine learning-driven optimization of a photoredox tertiary amine synthesis with six continuous variables (e.g., concentration, temperature, residence time) and solvent choice as a discrete variable, in a semiautomated continuous flow setup. Starting with a large library of solvents, the workflow included multiple steps of a priori knowledge generation (e.g., solubility predictions) to narrow the discrete space. A novel Bayesian optimization algorithm, nomadic exploratory multiobjective optimization (NEMO), was then deployed to identify and populate the Pareto front for the two reaction objectives􀀁yield and reaction cost. Permutation feature importance and partial dependence plots identified the most important parameters for high yield, sig3, the asymmetry of the s-profile for the discrete space, and equivalences of alkene and Hantzsch ester for the continuous variables. Catalyst loading and residence time were found to be correlated to absorbed photon equivalence, while catalyst loading was additionally e main parameter to drive cost. Even though productivity not an optimization objective, the best result achieved in flow was 25 times higher than  \nreactions in batch, which equals to 12 g per day throughput.  \nKEYWORDS: Bayesian optimization, photoredox chemistry, flow chemistry, automation  \n1. INTRODUCTION  \nRecently, visible-light photocatalysis has seen increased adoption in academia and industry, especially in the field of continuous flow chemistry in plug or laminar flow reactors, owing to its ability to streamline access to pharmaceutically relevant compounds under milder conditions, which would normally require lengthy multistep syntheses.1 However, while the use of flow reactors allows for faster reaction times and more efficient process control compared to their batch alternatives, holistic and robust process development of such processes for novel chemical transformations is still a laborious and complex task. This is mostly due to the difficulties in identifying the underlying chemical and physical parameters that affect the process objective(s), quantifying the nonlinear interactions between them, and the lack of prior experimental and computational data. These difficulties necessitate the development of a workflow to (i) efficiently generate a priori knowledge (such as optimal reactor and lamp choices, solubility predictions, and featurization of discrete variables with relevant molecular descriptors) and (ii) use said knowledge to efficiently find the trade-off curve of competing process objectives (i.e., the Pareto front).  \nThe advancements in the field of photocatalysis have mainly been triggered by a deeper understanding of the underlying mechanisms, a wider range of photocatalysts, and improved light-emitting diode (LED) technology in terms of energy efficiency, cost, and temperature control. Since the first reported application of photoredox catalysis in organic  \nchemistry more than 40 years ago,2 the field has significantly expanded with the recent years.3,4 ","cbCaimg1hpg2IQAp","https://ap.wps.com/l/cbCaimg1hpg2IQAp","pdf",2784550,1,12,"English","en",105,"# Abstract\n# 1. Introduction","[{\"question\":\"What workflow is used to optimize the continuous-flow photoredox amine synthesis?\",\"answer\":\"The approach combines semiautomated continuous-flow experiments with a priori knowledge generation (including solubility predictions) to narrow the discrete solvent space, then uses Bayesian optimization (NEMO) to explore and optimize the process.\"},{\"question\":\"Which variables are optimized in the study?\",\"answer\":\"Six continuous variables (such as concentration, temperature, and residence time) are optimized alongside solvent choice treated as a discrete variable.\"},{\"question\":\"How are the optimization results evaluated?\",\"answer\":\"The method identifies and populates the Pareto front based on two objectives: reaction yield and reaction cost, using analysis tools including permutation feature importance and partial dependence plots.\"}]","Machine Learning-Driven Optimization of Continuous-Flow Photoredox Amine Synthesis | PDF",1785897730,30,{"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-driven-optimization-of-continuous-flow-photoredox-amine-synthesis","",{"@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-driven-optimization-of-continuous-flow-photoredox-amine-synthesis/125252/",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","2026-08-05",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 workflow is used to optimize the continuous-flow photoredox amine synthesis?","Question",{"text":75,"@type":76},"The approach combines semiautomated continuous-flow experiments with a priori knowledge generation (including solubility predictions) to narrow the discrete solvent space, then uses Bayesian optimization (NEMO) to explore and optimize the process.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which variables are optimized in the study?",{"text":80,"@type":76},"Six continuous variables (such as concentration, temperature, and residence time) are optimized alongside solvent choice treated as a discrete variable.",{"name":82,"@type":73,"acceptedAnswer":83},"How are the optimization results evaluated?",{"text":84,"@type":76},"The method identifies and populates the Pareto front based on two objectives: reaction yield and reaction cost, using analysis tools including permutation feature importance and partial dependence plots.","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},[93,97,101,105,110,115,120,122,127,130,134],{"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":29,"slug":121},"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]