[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125986-en":3,"doc-seo-125986-105":31,"detail-sidebar-cat-0-en-105":93},{"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":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},125986,687207024478,"Liam","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Drug target, class level, and PathFX pathway information share utility for machine learning prediction of common drug-induced side effects","Drug development frequently fails due to toxicity and intolerable adverse effects, motivating machine-learning approaches that use domain knowledge to anticipate side effects. This study evaluates how predictive value differs among drug targets, drug class information defined by level 2 ATC codes, and PathFX pathway representations for predicting 30 common drug-induced side effects. Model comparisons show level 2 ATC codes deliver the highest overall predictive accuracy, while coefficient analyses indicate side effects depend more on drug targets and drug classes than on PathFX targets and network proteins, supporting safer drug design.","TYPE Original Research PUBLISHED 23 November 2023 DOI 10.3389/fdsfr.2023.1287535  \nOPEN ACCESS  \nEDITED BY  \nPantelis Natsiavas,  \nInstitute of Applied Biosciences, Centre for Research and Technology Hellas (INAB|CERTH), Greece  \nREVIEWED BY  \nSalvatore Crisafulli, University of Verona, Italy Roman Tremmel,  \nDr. Margarete Fischer-Bosch Institut für Klinische Pharmakologie (IKP), Germany  \n*CORRESPONDENCE  \nHan Jie Liu,  \n [shawnliu60@g.ucla.edu](shawnliu60@g.ucla.edu)[ ](shawnliu60@g.ucla.edu)Jennifer L. Wilson,  \n [jenniferwilson@g.ucla.edu](jenniferwilson@g.ucla.edu)  \nRECEIVED 01 September 2023  \nACCEPTED 07 November 2023  \nPUBLISHED 23 November 2023  \nCITATION  \nLiu HJ and Wilson JL (2023), Drug target, class level, and PathFX pathway information share utility for machine learning prediction of common druginduced side effects.  \nFront. Drug Saf. Regul. 3:1287535 .  \ndoi: 10.3389/fdsfr.2023.1287535  \nCOPYRIGHT  \n© 2023 Liu and Wilson. This is an openaccess article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.  \nDrug target, class level, and PathFX pathway information share utility for machine learning  \nprediction of common drug-induced side effects  \nHan Jie Liu* and Jennifer L. Wilson*  \nDepartment of Bioengineering, University of California—Los Angeles, Los Angeles, CA, United States  \nIntroduction: Development of drugs often fails due to toxicity and intolerable side effects. Recent advancements in the scientific community have rendered it possible to leverage machine learning techniques to predict individual side effects with domain knowledge features (i. e., drug classification) . While several factors can be used to anticipate drug effects including their targets, pathways, and drug classes, it is unclear which domain knowledge is most predictive and whether certain domain knowledge is more important than others for different side effects.  \nMethods: The goal of this project is to understand the predictive values of drug targets, drug classification (i.e., level 2 ATC codes), and protein-protein interaction networks (i.e., PathFX targets and network proteins) for machine learning prediction of 30 frequently occurring drug-induced side effects.  \nResults: We compared the prediction accuracy for individual side effects of trained models across five domain knowledge combinations and discovered that level 2 ATC codes have the highest predictive value across the domain knowledge features. Logistic regression coefficient analyses further suggest that side effects are more dependent on drug targets and drug classes, and less so on PathFX targets and network proteins.  \nDiscussion: Our quantitative assessments may inform the development of safe and effective drugs by understanding the domain knowledge features underlying frequently occurring drug-induced side effects.  \nKEYWORDS  \nmachine learning (ML), drug development, drug safety, domain knowledge analysis, drug target, protein-protein interaction (PPI) networks, drug side effect prediction  \n1 Introduction  \nThe development of drugs often fails during clinical trials due to toxicity and intolerable side effects. Sun et al. (2022) analyzed clinical trial data from 2010 to 2017 and found that over 30% of drugs failed due to unmanageable toxicity. Furthermore, off-target toxicity from drugs can trigger dangerous side effects and cause clinical trial failure (Lin et al., 2019) . For instance, the kinase inhibitor Sunitinib is known to trigger cardiotoxicity through its interaction with proteins outside of what the drug was intended to bind (Force and Kolaja, 2011) . Currently, there are strict guidelines and prot","cbCaidP2WVSW0BnD","https://ap.wps.com/l/cbCaidP2WVSW0BnD","pdf",1144520,6,1,14,"English","en",105,"# Introduction\n## Methods\n## Results\n## Discussion","[{\"question\":\"What is the main goal of the study?\",\"answer\":\"To determine which domain knowledge sources—drug targets, level 2 ATC drug class codes, or PathFX pathway features—most improve machine learning prediction of 30 common drug-induced side effects.\"},{\"question\":\"Which domain knowledge feature shows the highest predictive value?\",\"answer\":\"Level 2 ATC codes (drug class classification) show the highest predictive value across the evaluated domain knowledge feature combinations.\"},{\"question\":\"How do PathFX pathway features compare with drug targets and drug classes?\",\"answer\":\"Logistic regression coefficient analyses suggest side effects are more dependent on drug targets and drug classes, and less so on PathFX targets and network proteins.\"}]","Drug target, class level, and PathFX pathway information share utility for machine learning prediction of common drug-induced side effects | PDF",1785902401,35,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":88,"head_meta":90,"extra_data":92,"updated_unix":29},"drug-target-class-level-and-pathfx-pathway-information-share-utility-for-machine-learning-prediction-of-common-drug-induced-side-effects","",{"@graph":37,"@context":87},[38,55,70],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":54},"https://docshare.wps.com/document/drug-target-class-level-and-pathfx-pathway-information-share-utility-for-machine-learning-prediction-of-common-drug-induced-side-effects/125986/",4,{"url":53,"name":13,"@type":56,"author":57,"headline":13,"publisher":59,"fileFormat":62,"inLanguage":24,"description":14,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73,79,83],{"name":74,"@type":75,"acceptedAnswer":76},"What is the main goal of the study?","Question",{"text":77,"@type":78},"To determine which domain knowledge sources—drug targets, level 2 ATC drug class codes, or PathFX pathway features—most improve machine learning prediction of 30 common drug-induced side effects.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"Which domain knowledge feature shows the highest predictive value?",{"text":82,"@type":78},"Level 2 ATC codes (drug class classification) show the highest predictive value across the evaluated domain knowledge feature combinations.",{"name":84,"@type":75,"acceptedAnswer":85},"How do PathFX pathway features compare with drug targets and drug classes?",{"text":86,"@type":78},"Logistic regression coefficient analyses suggest side effects are more dependent on drug targets and drug classes, and less so on PathFX targets and network proteins.","https://schema.org",{"og:url":53,"og:type":89,"og:title":13,"og:site_name":60,"og:description":14},"article",{"robots":91,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":94},[95,99,103,107,112,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":96,"show_sort_weight":97,"slug":98},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":100,"show_sort_weight":101,"slug":102},"Literature",80,"literature",{"id":54,"doc_module":4,"doc_module_name":47,"category_name":104,"show_sort_weight":105,"slug":106},"Exam",70,"exam",{"id":108,"doc_module":4,"doc_module_name":47,"category_name":109,"show_sort_weight":110,"slug":111},5,"Comic",60,"comic",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":108,"slug":139},19,"General","general"]