[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127342-en":3,"doc-seo-127342-105":31,"detail-sidebar-cat-0-en-105":92},{"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},127342,962085564381,"Clementine","https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8",8,"Research & Report","Advancing Toxicology Through Machine Learning and Deep Learning-Based Toxicity Prediction - Research Summary","Integration of artificial intelligence and deep learning is used to improve toxicity prediction for chemical compounds and support safer drug development. The study compares machine learning and deep learning models for toxicity assessment, using ANN, random forest, KNN, SVM, decision tree, and convolutional neural networks. Reported experiments show notable accuracy gains, including CNN and LSTM results that validate AI-driven approaches for reliable toxicity scoring. Findings aim to enhance both assessment speed and quality.","Advancing Toxicology Through Machine Learning and Deep Learning-Based Toxicity Prediction  \nSameh Zarif∗ ,† , Alaa Taha El Maria‡, Mahmoud Ahmed Shawky§ , ¶  , Shuja Ansari§ ,  \nAhmed Gamal Abdellatif Ibrahim¶ , Islam M. Ibrahim ∥ , Marian Wagdy∗∗  \n∗ Dept. of Info. Techno., Faculty of Comp. and Info., Menoufia Univ., Egypt, sameh.shenoda@ci.menofia.edu.eg † Artificial Intelligence Dept., Faculty of Artificial Intelligence, Egyptian Russian Univ., Egypt, Sameh-zarief@eru.edu.eg ‡ Dept. of Artificial Intelligence, Mansoura National Univ., New Mansoura, Egypt, Alaa.ai [0067@ai.kfs.edu.eg](0067@ai.kfs.edu.eg)  \n§ James Watt School, Univ. of Glasgow, Glasgow, United Kingdom, {mahmoud.shawky, [shuja.ansari](shuja.ansari}@glasgow.ac.uk)[}](shuja.ansari}@glasgow.ac.uk)[@glasgow.ac.uk](shuja.ansari}@glasgow.ac.uk)[ ](shuja.ansari}@glasgow.ac.uk)¶ Dept. of Communications and Electronics Engineering, Air Defense College, EMA, Cairo, Egypt ∥ Faculty of Engineering and technology, Egyptian Chinese Univ., Cairo, Egypt, [islam.mohammed@ecu.edu.eg](islam.mohammed@ecu.edu.eg)[ ](islam.mohammed@ecu.edu.eg)∗∗ Dept. of Info. Techno., Faculty of Computers and Information, Tanta Univ., Egypt, marian [wagdy@ics.tanta.edu.eg](wagdy@ics.tanta.edu.eg)  \nAbstract—In recent years, the integration of artificial intelligence (AI) and deep learning algorithms has significantly advanced the field of toxicity prediction. This research investigates the application of various machine learning and deep learning models for predicting the toxicity of chemical compounds, aiming to enhance both the accuracy and efficiency of toxicity assessments. The study employs a diverse set of algorithms, including artificial neural networks (ANN), random forest, K-nearest neighbor (KNN), support vector machine (SVM), decision tree, and convolutional neural networks (CNN). The experimental results demonstrate substantial improvements in predictive accuracy, with ANN achieving 90.7%, recurrent neural networks (RNN) 87.8%, CNN 95.36%, and long short-term memory (LSTM) reaching 97.42% . These findings underscore the potential of AIdriven approaches to deliver reliable toxicity predictions, thereby supporting the development of safer chemical compounds and pharmaceutical products.  \nIndex Terms—Artificial neural network, Toxicity prediction, Tox21, CHEMBL, Convolutional neural network, Recurrent neural network, Long short-term memory.  \nI. INTRODUCTION  \nHumans are routinely exposed to a wide range of chemical substances through food, household products, and medications—some of which may be toxic. Detecting these potentially harmful compounds requires rigorous testing, often demanding significant time, cost, and resources. Notably, despite promising outcomes in preclinical studies, more than 30% of drug candidates fail during clinical trials due to unforeseen toxic effects [1] . Consequently, the development of novel, costeffective methods for toxicity assessment holds great promise for improving both environmental safety and drug development efficiency [2] . Toxicity remains one of the primary causes of drug candidate failure, contributing substantially to the high costs and prolonged timelines associated with drug development. The entire process—from the identification of lead compounds to regulatory approval—takes an average of 12 years and is characterized by a remarkably low success rate of just 0.01% to 0.02% . This highlights the necessity for continuous experimentation, rigorous toxicity testing, and comprehensive scientific review to ensure drug safety and efficacy [3]–[5] .  \nOne significant form of drug-induced harm is on-target toxicity, also known as mechanism-based toxicity. This occurs when a drug binds to its intended biological target and elicits both therapeutic and adverse effects. A well-documented example is statins, which inhibit HMG-CoA reductase to lower cholesterol levels but can also lead to muscle-related side effects through the same mechanism. Managing ","cbCainHTaR5D946A","https://ap.wps.com/l/cbCainHTaR5D946A","pdf",534782,2,1,7,"English","en",105,"# Introduction\n## Drug-induced toxicity and challenges\n## Computational vs experimental toxicity assessment\n# Proposed approach\n## Datasets and preprocessing\n## LSTM-based architecture\n# Model evaluation\n## Comparison of ML and deep learning models","[{\"question\":\"Why is toxicity prediction important in drug development?\",\"answer\":\"Toxic effects cause a substantial share of drug candidate failures, creating high costs and long timelines. Earlier and more efficient toxicity assessment helps reduce these risks.\"},{\"question\":\"Which machine learning and deep learning models are evaluated?\",\"answer\":\"The study tests ANN, random forest, KNN, SVM, decision tree, CNN, RNN, and LSTM for toxicity prediction and bioactivity-related performance.\"},{\"question\":\"What preprocessing steps are used before modeling?\",\"answer\":\"Multiple datasets (eToxPred, Ames, ChEMBL) are combined with preprocessing including descriptor calculation (e.g., Lipinski rules), activity classification, and fingerprint extraction.\"}]","Advancing Toxicology Through Machine Learning and Deep Learning-Based Toxicity Prediction - Research Summary | PDF",1785938394,18,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":29},"advancing-toxicology-through-machine-learning-and-deep-learning-based-toxicity-prediction-research-summary","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,48,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":20},"https://docshare.wps.com/document/","Document",{"item":49,"name":12,"@type":44,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/advancing-toxicology-through-machine-learning-and-deep-learning-based-toxicity-prediction-research-summary/127342/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-22","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why is toxicity prediction important in drug development?","Question",{"text":76,"@type":77},"Toxic effects cause a substantial share of drug candidate failures, creating high costs and long timelines. Earlier and more efficient toxicity assessment helps reduce these risks.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"Which machine learning and deep learning models are evaluated?",{"text":81,"@type":77},"The study tests ANN, random forest, KNN, SVM, decision tree, CNN, RNN, and LSTM for toxicity prediction and bioactivity-related performance.",{"name":83,"@type":74,"acceptedAnswer":84},"What preprocessing steps are used before modeling?",{"text":85,"@type":77},"Multiple datasets (eToxPred, Ames, ChEMBL) are combined with preprocessing including descriptor calculation (e.g., Lipinski rules), activity classification, and fingerprint extraction.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":22,"doc_module":4,"doc_module_name":47,"category_name":117,"show_sort_weight":118,"slug":119},"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":47,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":47,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":47,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":47,"category_name":137,"show_sort_weight":107,"slug":138},19,"General","general"]