[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119141-en":3,"doc-seo-119141-105":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},119141,8796095462418,"Noah","https://ap-avatar.wpscdn.com/avatar/80000253c1241d02b47?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778826106357471780",8,"Research & Report","A Hybrid Structure-Based Machine Learning Approach for Predicting Kinase Inhibition by Small Molecules","Kinases drive drug discovery through therapeutic inhibitors and large-scale biophysical affinity measurements, yet many kinases’ precise target spectra remain incompletely characterized. This study presents a structure-based machine learning framework for qualitative and quantitative kinome-wide binding. It combines the Kinase Inhibitor Complex (KinCo) dataset linking predicted kinase structures with experimental binding constants, a training loss that jointly leverages qualitative and quantitative data, and a KinCo-trained hybrid model. Results show improved prediction of binary and quantitative kinase–compound interaction affinities versus crystal-structure-only and structure-free approaches, with better capture of kinase biochemistry and stronger generalization to distant kinase sequences and compound scaffolds.","This article is licensed under CC-BY-NC-ND 4.0  \n[pubs.acs.org/jcim](pubs.acs.org/jcim)  Article   \nA Hybrid Structure-Based Machine Learning Approach for Predicting Kinase Inhibition by Small Molecules  \nChangchang Liu, Peter Kutchukian, Nhan D. Nguyen, Mohammed AlQuraishi,* and Peter K. Sorger *  \n Cite This: J. Chem. Inf. Model. 2023, 63, 5457−5472  \nRead Online  \nACCESS  \n Metrics & More  \n Article Recommendations  \n*sı   \nSupporting Information  \nDownloaded via 99.7.2.48 on September 17, 2024 at 16:15:56 (UTC) . See [https://pubs.acs.org/sharingguidelines](https://pubs.acs.org/sharingguidelines) for options on how to legitimately share published articles.  \nABSTRACT: Kinases have been the focus of drug discovery programs for three decades leading to over 70 therapeutic kinase inhibitors and biophysical affinity measurements for over 130,000 kinase-compound pairs. Nonetheless, the precise target spectrum for many kinases remains only partly understood. In this study, we describe a computational approach to unlocking qualitative and quantitative kinome-wide binding measurements for structurebased machine learning. Our study has three components: (i) a Kinase Inhibitor Complex (KinCo) data set comprising in silico predicted kinase structures paired with experimental binding constants, (ii) a machine learning loss function that integrates qualitative and quantitative data for model training, and (iii) a structure-based machine learning model trained on KinCo. We show that our approach outperforms methods trained on crystal structures alone in predicting binary and quantitative kinase-compound interaction affinities; relative to structure-free methods, our approach also captures known kinase biochemistry and more successfully generalizes to distant kinase sequences and compound scaffolds.  \n■ INTRODUCTION  \nMammalian kinases make up a large family of enzymes that bind ATP and catalyze phosphotransfer to a protein or small molecule substrate. Among the set of approximately 700 human proteins having structures associated with kinase activity, 544 have a highly conserved Protein Kinase Like (PKL) three-dimensional fold. 1−3 These kinases have diverse functions in the regulation of cell division, migration, morphology, and metabolism, and many are components of multienzyme signal transduction cascades.4 Multiple kinases involved in cell signaling networks are mutated or differentially expressed in human disease, often serving as driver mutations in cancer.5 As a result, kinases have been the focus of intense drug development efforts. Most kinase inhibitors are ATPcompetitive molecules that interact with the ATP binding site although some, generally referred to as “allosteric inhibitors”, bind outside the catalytic site.6,7  \nDue to the conserved structure of the ATP binding site, small molecule kinase inhibitors commonly inhibit kinases other than the one they were designed to target (we will refer to the intended or most commonly accepted target as the“nominal target”).8,9 For example, crizotinib was developed asan inhibitor of the MET tyrosine kinase but was later found to also inhibit ALK, and this later activity enabled its approval for advanced or metastatic nonsmall-cell-lung-cancers carrying ALK fusion genes.10 A complete understanding of the target spectrum of kinase inhibitors is rarely achieved in preclinical development, and the polypharmacology of many approved therapeutics is only discovered after they are in widespread  \nuse.8 It would nonetheless be highly advantageous were preclinical drug development programs able to accurately predict the full spectrum of kinases that a particular small molecule is likely to bind and use this information as part of insilico compound optimization.  \nA variety of experimental assays are available to measure interactions between kinase inhibitors and their kinase targets at the kinome scale. These include several different types of competitive binding assays that measure binding to ","cbCaip5YJMY62BxQ","https://ap.wps.com/l/cbCaip5YJMY62BxQ","pdf",3247037,1,16,"English","en",105,"# Abstract\n## KinCo dataset and training loss\n## Structure-based hybrid model and performance\n## Generalization to distant kinases and compound scaffolds","[{\"question\":\"What problem does the study address in kinase inhibitor discovery?\",\"answer\":\"It targets the incomplete understanding of kinases’ precise target spectra, even though many inhibitors and binding measurements exist.\"},{\"question\":\"What are the three main components of the proposed approach?\",\"answer\":\"The method uses the KinCo dataset (predicted kinase structures with experimental binding constants), a hybrid loss function integrating qualitative and quantitative data, and a structure-based machine learning model trained on KinCo.\"},{\"question\":\"How does the approach perform compared with existing methods?\",\"answer\":\"It outperforms models trained only on crystal structures for both binary and quantitative affinity prediction, and it better generalizes than structure-free methods while capturing known kinase biochemistry.\"}]","A Hybrid Structure-Based Machine Learning Approach for Predicting Kinase Inhibition by Small Molecules | PDF",1785722666,40,{"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},"a-hybrid-structure-based-machine-learning-approach-for-predicting-kinase-inhibition-by-small-molecules","",{"@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/a-hybrid-structure-based-machine-learning-approach-for-predicting-kinase-inhibition-by-small-molecules/119141/",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 problem does the study address in kinase inhibitor discovery?","Question",{"text":75,"@type":76},"It targets the incomplete understanding of kinases’ precise target spectra, even though many inhibitors and binding measurements exist.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What are the three main components of the proposed approach?",{"text":80,"@type":76},"The method uses the KinCo dataset (predicted kinase structures with experimental binding constants), a hybrid loss function integrating qualitative and quantitative data, and a structure-based machine learning model trained on KinCo.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the approach perform compared with existing methods?",{"text":84,"@type":76},"It outperforms models trained only on crystal structures for both binary and quantitative affinity prediction, and it better generalizes than structure-free methods while capturing known kinase biochemistry.","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},[93,97,101,105,110,115,119,122,127,130,134],{"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":29,"slug":118},7,"Healthcare","healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"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"]