[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126812-en":3,"doc-seo-126812-105":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},126812,1099523885074,"Ivy","https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc",8,"Research & Report","CIRCE: Web-Based Platform for the Prediction of Cannabinoid Receptor Ligands Using Explainable Machine Learning","The endocannabinoid system, including cannabinoid receptor 1 and 2 (CB1R and CB2R), underlies multiple pathologies such as neurodegeneration, cancer, neuropathic and inflammatory pain, obesity, and inflammatory bowel disease. Because CB1R and CB2R are highly similar, designing subtype-selective ligands remains challenging. CIRCE is an explainable machine learning web platform that combines multi-layer classifiers with Shapley value analysis to support selective CB1R/CB2R ligand prediction and rationalize structural features.","versione accettata non edit . di  \n[https://doi.org/10.1021/acs.jcim.3c00914](https://doi.org/10.1021/acs.jcim.3c00914)  \n1 CIRCE: Web-Based Platform for the Prediction of  \n2 Cannabinoid Receptor Ligands Using Explainable  \n3 Machine Learning  \n4 Nicola Gambacorta1,2, Fulvio Ciriaco3, Nicola Amoroso1, Cosimo Damiano Altomare1, Jürgen  \n5 Bajorath2 * and Orazio Nicolotti1 *  \n6 1Dipartimento di Farmacia Scienze del Farmaco, Università degli Studi di Bari “Aldo Moro”, Via 7 E. Orabona, 4, I-70125 Bari, Italy;  \n8 2Department of Life Science Informatics and Data Science, B-IT, LIMES Program Unit Chemical  \n9 Biology and Medicinal Chemistry, Rheinische Friedrich-Wilhelms-Universität, Friedrich- 10 Hirzebruch-Allee 5/6, D-53115 Bonn, Germany;  \n11 3Dipartimento di Chimica, Università degli Studi di Bari “Aldo Moro”, Via E. Orabona, 4, I-70125  \n12 Bari, Italy;  \n13 *Corresponding authors  \n14  [orazio.nicolotti@uniba.it](orazio.nicolotti@uniba.it) (for editorial correspondence)  \n15 [bajorath@bit.uni-bonn.de](bajorath@bit.uni-bonn.de)[ ](bajorath@bit.uni-bonn.de)16  \n17  \n19 ABSTRACT  \n20 The endocannabinoid system, which includes cannabinoid receptor 1 and 2 subtypes (CB 1R and 21 CB2R, respectively), is responsible for the onset of various pathologies including  \n22 neurodegeneration, cancer, neuropathic and inflammatory pain, obesity, and inflammatory bowel  \n23 disease. Given the high similarity of CB 1R and CB2R, generating subtype-selective ligands is still  \n24 an open challenge. In this work, the Cannabinoid Iterative Revaluation for Classification and  \n25 Explanation (CIRCE) compound prediction platform has been generated based on explainable  \n26 machine learning to support the design of selective CB 1R and CB2R ligands. Multi-layer classifiers  \n27 were combined with Shapley value analysis to facilitate explainable predictions. In test calculations, 28 CIRCE predictions reached ~80% accuracy and structural features determining ligand predictions  \n29 were rationalized. CIRCE was designed as a web-based prediction platform that is made freely  \n30 available as a part of our study.  \n31  \n32 Introduction  \n33 Cannabinoid receptors 1 and 2 (CB 1R and CB2R) constitute the endocannabinoid system and  \n34 represent the molecular targets of the 9-tetrahydrocannabinol (9-THC), a psychoactive agent  \n35 derived from Cannabis sativa. CB 1R and CB2R are responsible for many physiological functions  \n36 such as appetite, pain perception, memory, and immunomodulation. 1,2  \n37 CB 1R and CB2R are largely expressed in the central nervous system (CNS) as well as in the 38 immune system and have distinct tissue distributions and functions. CB 1R is a major player in the  \n39 regulation of higher cognitive functions, neuronal development and synaptic plasticity, reward and  \n40 addiction, pain, and food intake. CB 1R is also associated with biological and pathological processes  \n41 outside the CNS, being its expression reported in different types of hepatic cells, in the  \n42 cardiovascular system, in the adipose tissue, muscles, and mitochondria. The CB 1R deregulation is  \n43 behind the onset of several pathological conditions such as obesity3–5, neurodegenerative diseases, 44 glaucoma, pain, and cancer. Unlike CB 1R, CB2R has so far received less attention, and when it was  \n45 first discovered, CB2 activity was only found in lymphoid organs, immune cells, and hematopoietic  \n46 cells. In fact, CB2 is primarily expressed in all immune system tissues and circulating cells, with  \n47 varying degrees of expression and activity depending on the stimulus, cell type, and cell activation.  \n48 In this respect, CB2R plays a pivotal role in a wide spectrum of pathological conditions: it can act as  \n49 an antitumor agent by inhibiting cells proliferation or by decreasing angiogenesis or metastasis, or it  \n50 can be used for palliative care 6 ; furthermore, it is also implicated in several central nervous system  \n51 conditions. 1,7–9  \n52 C","cbCais2M0a6svFcF","https://ap.wps.com/l/cbCais2M0a6svFcF","pdf",5545325,1,29,"English","en",105,"# Abstract\n# Introduction\n## Endocannabinoid system and cannabinoid receptors\n## Subtype-selective ligand design challenge\n## CIRCE explainable prediction approach","[{\"question\":\"What biological targets does CIRCE aim to predict ligands for?\",\"answer\":\"CIRCE supports the design of subtype-selective ligands for cannabinoid receptor 1 (CB1R) and cannabinoid receptor 2 (CB2R).\"},{\"question\":\"How does CIRCE make its predictions explainable?\",\"answer\":\"It combines multi-layer classifiers with Shapley value analysis to rationalize which structural features drive ligand predictions.\"},{\"question\":\"What performance level did CIRCE achieve in test calculations?\",\"answer\":\"Test calculations reported approximately 80% accuracy, along with rationalization of structural features determining the predictions.\"}]","CIRCE: Web-Based Platform for the Prediction of Cannabinoid Receptor Ligands Using Explainable Machine Learning | PDF",1785934941,73,{"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},"circe-web-based-platform-for-the-prediction-of-cannabinoid-receptor-ligands-using-explainable-machine-learning","",{"@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/circe-web-based-platform-for-the-prediction-of-cannabinoid-receptor-ligands-using-explainable-machine-learning/126812/",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 biological targets does CIRCE aim to predict ligands for?","Question",{"text":75,"@type":76},"CIRCE supports the design of subtype-selective ligands for cannabinoid receptor 1 (CB1R) and cannabinoid receptor 2 (CB2R).","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does CIRCE make its predictions explainable?",{"text":80,"@type":76},"It combines multi-layer classifiers with Shapley value analysis to rationalize which structural features drive ligand predictions.",{"name":82,"@type":73,"acceptedAnswer":83},"What performance level did CIRCE achieve in test calculations?",{"text":84,"@type":76},"Test calculations reported approximately 80% accuracy, along with rationalization of structural features determining the predictions.","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"]