[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120560-en":3,"doc-seo-120560-105":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},120560,687197207919,"Theodora","https://ap-avatar.wpscdn.com/avatar/a000253d6f5f7c60be?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779446848396160552",8,"Research & Report","Machine learning driven design of spiropyran photoswitches","Generative machine learning is used to design novel spiropyran photoswitches with enhanced switching speed and absorption bands that show small spectral overlap between open and closed states, enabling high addressability. A scaffold decoration strategy is applied to fine-tune a general chemical recurrent neural network (RNN) on a curated photoswitch dataset. The fine-tuned model is benchmarked against a pretrained baseline and literature-reported compounds, producing diverse, novel candidates while reducing bias in decoration patterns and functional group selection. Synthesis and experimental characterization of newly designed spiropyrans validate model-derived design principles.","Digital  \nDiscovery  \nPAPER  \nCite this: Digital Discovery, 2025, 4, 3098  \nReceived 23rd July 2025  \nAccepted 16th September 2025 DOI: 10.1039/d5dd00327j[rsc.li/digitaldiscovery](rsc.li/digitaldiscovery)  \nMachine learning driven design of spiropyran photoswitches  \nRobert Strothmann,a Mehran Amanpur,b Tom Nevesel´y, b Stefan Hecht,*b Karsten Reuter  *a and Johannes T. Margraf  *ac  \nThis study presents the development and application of a generative machine learning model for the design of novel spiropyran photoswitches with enhanced switching speed and absorption bands with small spectral overlap between the open and closed form (i.e. high addressability) . Leveraging a scaffold decoration approach, we fine-tuned a general chemical recurrent neural network (RNN) model on a curated dataset of photoswitches. The fine-tuned model was evaluated against both the pretrained baseline and literature-reported spiropyran compounds, demonstrating superior performance in generating diverse and novel candidates. Notably, the fine-tuned model effectively mitigates common biases in decoration patterns and functional group selection observed in the literature. The study also outlines the synthesis and experimental characterization of several newly designed spiropyran photoswitches, validating the design principles derived from the generative model. These findings highlight the potential of generative models in accelerating the discovery of advanced molecular photoswitches with tailored properties.  \n1. Introduction  \nPhotoswitches are molecules that isomerize upon exposure to light and whose initial state can subsequently be restored by irradiation with another wavelength, or via a thermal process with a characteristic lifetime s (see Fig. 1(a)) . Molecular photoswitches have been known for over 150 years.1 In this time a wide variety of classes of switches have been developed, including azobenzenes,2–4 spiropyrans5,6 (SP), diarylethenes7,8 and others.9–11 Possible applications range from photosensitive devices and data storage,12,13 over photopharmacology,14,15 to molecular machines.16,17  \nThis wide range of applications leads to different demands for the switching behavior. Thermal backreactions are for instance not desired in data storage applications, since the molecules need to be switched back and forth in a controlled manner. This class of switches are referred to as P-type photoswitches in the literature (P indicating a photochemical backreaction) . The ideal timescale for thermal backreactions in other applications (using T-type thermal switches) can range from minutes in drug delivery to less than seconds in 3D printing applications.18,19 Furthermore, the wavelengths used  \naFritz-Haber-Institute of the Max-Planck-Society, Faradayweg 4-6, 14195 Berlin, Germany. E-mail: reuter@􀀁i.mpg.de  \nbHumboldt-Universitt zu Berlin, Brook-Taylor-Straße 2, 12489 Berlin, Germany. E-mail: [sh@chemie.hu-berlin.de](sh@chemie.hu-berlin.de)  \nc University of Bayreuth, Bavarian Center for Battery Technology (BayBatt), Weiherstraße 26, 95448 Bayreuth, Germany. E-mail: johannes.margraf@ [uni-bayreuth.de](uni-bayreuth.de)  \nfor switching must o􀀁en be in some desired range due to technical as well as material/biological boundary conditions (such as tissue penetration depth) .  \nAll of this implies that there is no single optimal photoswitch, but rather a range of optimal switches for different applications. Even for a given application, the existence of multiple competing design targets will usually lead to a Pareto front of candidates that represent different trade-offs between the target properties. Overall, photoswitch design is thus a highly challenging task. Unfortunately, this challenge is still most commonly addressed via trial and error. Here, a common strategy is to modify known photoswitches, for example by adding or exchanging side groups. This approach is prone to human bias towards speci􀀁c chemistries, e.g. based on previous knowledge or synthetic acc","cbCaieTHGECtshgS","https://ap.wps.com/l/cbCaieTHGECtshgS","pdf",1251016,1,11,"English","en",105,"# Introduction\n## Photoswitch concepts and application demands\n## Challenges in photoswitch design\n## Machine learning approaches for unbiased molecular design\n## Generative models and denovo molecular discovery\n## Study scope: spiropyran-based xolography printing","[{\"question\":\"What is the main goal of the generative machine learning model in this study?\",\"answer\":\"To design novel spiropyran photoswitches with improved switching speed and absorption behavior, including high addressability with small spectral overlap between open and closed forms.\"},{\"question\":\"How is the machine learning model trained and evaluated?\",\"answer\":\"A general chemical RNN is fine-tuned using a scaffold decoration approach on a curated photoswitch dataset, then evaluated against both a pretrained baseline and literature-reported spiropyran compounds.\"},{\"question\":\"How do the authors validate that the generated designs are meaningful?\",\"answer\":\"They outline synthesis and perform experimental characterization of several newly designed spiropyran photoswitches to confirm design principles derived from the generative model.\"}]","Machine learning driven design of spiropyran photoswitches | PDF",1785730649,28,{"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-design-of-spiropyran-photoswitches","",{"@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-design-of-spiropyran-photoswitches/120560/",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},"What is the main goal of the generative machine learning model in this study?","Question",{"text":75,"@type":76},"To design novel spiropyran photoswitches with improved switching speed and absorption behavior, including high addressability with small spectral overlap between open and closed forms.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is the machine learning model trained and evaluated?",{"text":80,"@type":76},"A general chemical RNN is fine-tuned using a scaffold decoration approach on a curated photoswitch dataset, then evaluated against both a pretrained baseline and literature-reported spiropyran compounds.",{"name":82,"@type":73,"acceptedAnswer":83},"How do the authors validate that the generated designs are meaningful?",{"text":84,"@type":76},"They outline synthesis and perform experimental characterization of several newly designed spiropyran photoswitches to confirm design principles derived from the generative model.","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"]