Intelligent Pharmacy最新文献

Harnessing the power of artificial intelligence in pharmaceuticals: Current trends and future prospects 在制药中利用人工智能的力量：当前趋势和未来前景

Intelligent Pharmacy Pub Date : 2025-06-01 DOI: 10.1016/j.ipha.2024.12.001

Saha Aritra , Chauhan Baghel Shikha , Singh Indu

{"title":"Harnessing the power of artificial intelligence in pharmaceuticals: Current trends and future prospects","authors":"Saha Aritra , Chauhan Baghel Shikha , Singh Indu","doi":"10.1016/j.ipha.2024.12.001","DOIUrl":"10.1016/j.ipha.2024.12.001","url":null,"abstract":"<div><div>Introduction of artificial intelligence (AI) technology in the field of pharmaceutical industry has been driven to discovery and development of drugs, also personalized medicine. In this article The review investigates systematic trends facing AI-powered transformation. AI has improved efficiency by reducing the drug development time, costs and success rates due to machine learning (ML), deep learning (DL) and natural language processing (NLP). The literature search was conducted systematically, using core scientific databases to source data-mining research studies on predictive modelling, virtual screening, and automation in AI applications. Findings here underscore the critical role that AI plays in precision medicine, as well as process optimization in manufacture, but ethical issues and privacy of data and regulations add significantly to hurdles. The study confirms that AI presents unique opportunities for developing personalized healthcare and answering global health challenges, nonetheless its adoption involves overcoming ethical and regulatory issues beautiful collaboration and agreeing to industry wide standards. The next-generation products bring hope for low-cost, patient-centric solutions indicating pharmaceutical landscape phases of the paradigm.</div></div>","PeriodicalId":100682,"journal":{"name":"Intelligent Pharmacy","volume":"3 3","pages":"Pages 181-192"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144272262","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Development and evaluation of empagliflozin-loaded solid lipid nanoparticles: Pharmacokinetics and pharmacodynamics for oral delivery 恩格列净负载固体脂质纳米颗粒的开发和评价：口服给药的药代动力学和药效学

Intelligent Pharmacy Pub Date : 2025-06-01 DOI: 10.1016/j.ipha.2024.12.004

Ananda Kumar Chettupalli , Aziz Unnisa , Himabindu Peddapalli , Rajendra Kumar Jadi , Kachupally Anusha , Padmanabha Rao Amarachinta

{"title":"Development and evaluation of empagliflozin-loaded solid lipid nanoparticles: Pharmacokinetics and pharmacodynamics for oral delivery","authors":"Ananda Kumar Chettupalli , Aziz Unnisa , Himabindu Peddapalli , Rajendra Kumar Jadi , Kachupally Anusha , Padmanabha Rao Amarachinta","doi":"10.1016/j.ipha.2024.12.004","DOIUrl":"10.1016/j.ipha.2024.12.004","url":null,"abstract":"<div><div>Type 2 diabetes mellitus is frequently treated with empagliflozin (EZN), a sodium-glucose cotransporter 2 inhibitor. Solid lipid nanoparticles (SLNs) shield the drug from gastrointestinal breakdown and improve the bioavailability of lipophilic drugs. The aim of the study is to use SLNs to enhance EZN's pharmacokinetics and pharmacodynamics in the treatment of diabetes mellitus. To prepare EZN-loaded SLNs, central composite design (CCD) was employed. The optimized batch (optimized EZN-loaded SLNs) had the desired values of dependent variables Vesicle size (R1), Entrapment Efficiency (R2), and Cumulative Drug Release (CDR) (R3). This was achieved by using analysis of variance (ANOVA) to analyse independent variables such as lipid concentration (X1), surfactant concentration (X2), sonication time (X3), and homogenization speed (X4). F8 exhibited the highest drug entrapment (90.6% ± 2.8%), CDR (89.2 ± 3.6), and average particle size (98.6 ± 2.1 nm) among the 30 distinct formulated formulae (F1–F30). Based on the F-value and <em>p</em>-value, the model was determined to be significant for particle size, entrapment efficiency, and CDR. The actual values of particle size entrapment efficiency and CDR closely matched the projected values of the optimized batch. The in vitro release trials produced a burst release followed by a continuous release. When compared to the EZN solution, the relative bioavailability of EZN-loaded SLNs was 1.2 times higher, indicating superior protection against the gastrointestinal environment. In rats with streptozotocin-induced diabetes mellitus, the optimized EZN-loaded SLNs outperformed the basic drug suspension in terms of antidiabetic efficacy. One promising method for administering EZN in the treatment of diabetes mellitus is by SLNs.</div></div>","PeriodicalId":100682,"journal":{"name":"Intelligent Pharmacy","volume":"3 3","pages":"Pages 193-206"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144272264","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Stratification of cephalosporins based on physicochemical and pharmacokinetic variables using multivariate statistical tools 基于物理化学和药代动力学变量使用多变量统计工具的头孢菌素分层

Intelligent Pharmacy Pub Date : 2025-06-01 DOI: 10.1016/j.ipha.2024.09.004

Carlos Alberto Escobar Angulo, Antistio Alviz Amador, Julián Javier Martínez Zambrano

{"title":"Stratification of cephalosporins based on physicochemical and pharmacokinetic variables using multivariate statistical tools","authors":"Carlos Alberto Escobar Angulo, Antistio Alviz Amador, Julián Javier Martínez Zambrano","doi":"10.1016/j.ipha.2024.09.004","DOIUrl":"10.1016/j.ipha.2024.09.004","url":null,"abstract":"<div><h3>Introduction</h3><div>Cephalosporins, a class of beta-lactam antibiotics, are commonly used in medical practice. However, their potential advantages, based on physicochemical and pharmacokinetic variables, are often overlooked. This research, proposing strategies based on multivariate statistics to stratify different cephalosporins, is a significant step towards providing the prescribing team with more rational and effective options. The potential benefits of this research are promising, as it has the potential to significantly improve the efficacy and safety of cephalosporin therapy.</div></div><div><h3>Method</h3><div>Exploratory study and review of pharmacokinetic parameters of cephalosporins. Data were extracted from DrugBank go.drugbank.com, and multivariate statistical techniques such as Pearson correlation and cluster analysis were applied. This approach allowed the identification of groupings of cephalosporins with similar characteristics, thus facilitating their rational selection in clinical practice.</div></div><div><h3>Results</h3><div>The results reveal that cefazolin, cefotetan, cefoperazone, and ceftriaxone form the conglomerate with the most favorable properties for reaching effective concentrations at the site of action due to their high solubility, high percentage of binding to plasma proteins, and adequate residence times in the organism. Solubility, protein binding, half-life, MRT, molecular weight, volume of distribution, number of interactions, and pKa are all critical factors that influence the efficacy and safety of cephalosporin therapy.</div></div><div><h3>Conclusions</h3><div>It is relevant to highlight the use of multivariate statistics as a tool for drug selection and rational use. In the present study, cefazolin, cefotetan, cefoperazone, and ceftriaxone were highlighted as the best therapeutic alternatives according to the variables selected for the study.</div></div>","PeriodicalId":100682,"journal":{"name":"Intelligent Pharmacy","volume":"3 3","pages":"Pages 159-166"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144272368","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Machine learning & deep learning tools in pharmaceutical sciences: A comprehensive review 制药科学中的机器学习和深度学习工具：综合综述

Intelligent Pharmacy Pub Date : 2025-06-01 DOI: 10.1016/j.ipha.2024.11.003

Saleem Javid , Abdul Rahmanulla , Mohammed Gulzar Ahmed , Rokeya sultana , B.R. Prashantha Kumar

{"title":"Machine learning & deep learning tools in pharmaceutical sciences: A comprehensive review","authors":"Saleem Javid , Abdul Rahmanulla , Mohammed Gulzar Ahmed , Rokeya sultana , B.R. Prashantha Kumar","doi":"10.1016/j.ipha.2024.11.003","DOIUrl":"10.1016/j.ipha.2024.11.003","url":null,"abstract":"<div><div>Drug discovery and development is an important area of research for pharmaceutical industries and medicinal chemists. This classical approach demanded significant investments of time and resources to bring a single drug to market. Furthermore, the complexity and vast scale of data from genomics, proteomics, microarrays, and clinical trials present significant challenges in the drug discovery pipeline. Nevertheless, bioinformatics, pharmacoinformatics, and cheminformatics technologies have been developed thanks to breakthroughs in computational methodologies and a surge in multi-omics data, drastically shortening the time it takes to create new drugs. Large amounts of biological data stored in global databases are the building blocks for machine learning and deep learning methods. They make it easier to find patterns and models that can help find therapeutically active molecules with less time, work, and money. Machine learning and deep learning technology are vital in drug design and development. We have applied these algorithms to various drug discovery processes such as protein structure prediction, toxicity prediction, oral bioavailability prediction, de novo design of new chemical scaffolds, structure-based and ligand-based virtual screening, pharmacophore modeling, quantitative structure-activity relationship, drug repositioning, and clinical trial design. Historical evidence underscores the successful implementation of AI and deep learning in this domain. Finally, we highlight some successful machine learning or deep learning-based models employed in the drug design and development pipeline. Furthermore, there has been a notable increase in interest regarding the application of AI technology in hospital pharmacy settings, which has been discussed in this review. This review will be invaluable to medicinal and computational chemists seeking DL tools for drug discovery projects and hospital pharmacies.</div></div>","PeriodicalId":100682,"journal":{"name":"Intelligent Pharmacy","volume":"3 3","pages":"Pages 167-180"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144272261","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Insulin delivery devices in diabetes management: Applications and advancements 胰岛素输送装置在糖尿病管理：应用和进展

Intelligent Pharmacy Pub Date : 2025-06-01 DOI: 10.1016/j.ipha.2025.02.002

Runhuang Yang, Zongwen Yang, Jingnan Chi, Ya Zhu

{"title":"Insulin delivery devices in diabetes management: Applications and advancements","authors":"Runhuang Yang, Zongwen Yang, Jingnan Chi, Ya Zhu","doi":"10.1016/j.ipha.2025.02.002","DOIUrl":"10.1016/j.ipha.2025.02.002","url":null,"abstract":"<div><div>With continuous advancements in diabetes management technology, insulin delivery devices have become increasingly central to the treatment of diabetes. This review discusses the applications and development of various insulin delivery technologies, including insulin pens and pumps, in the management of type 1 diabetes (T1DM) and type 2 diabetes (T2DM). Insulin pens are widely used among individuals with T2DM due to their ease of use and dosing accuracy. The recent development of smart insulin pens has further enhanced patient adherence and glycemic control. Insulin pumps, particularly patch pumps, provide more precise glucose management for individuals with T1DM and select T2DM patients, significantly reducing glycemic variability and the risk of hypoglycemia. Patch pumps, as an innovative insulin infusion device, are particularly suitable for patients requiring discreet and convenient use, owing to their compact, lightweight, and tubeless design. This is especially pertinent for the large population of individuals with T2DM. However, mechanical patch pumps still require further optimization, particularly in displaying infusion volume and key operational parameters, to facilitate real-time monitoring and timely therapeutic adjustments by both patients and clinicians. This review summarizes the advantages and limitations of different types of insulin delivery devices and explores their potential role in clinical practice. Further advancements in these systems are expected to offer safer, more convenient, precise, and cost-effective treatment options for diabetes management.</div></div>","PeriodicalId":100682,"journal":{"name":"Intelligent Pharmacy","volume":"3 3","pages":"Pages 235-242"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144272263","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Smart healthcare: Artificial intelligences impact on drug development and patient care 智能医疗保健：人工智能对药物开发和患者护理的影响

Intelligent Pharmacy Pub Date : 2025-06-01 DOI: 10.1016/j.ipha.2025.01.003

Sachin Mendhi , Krutika Sawarkar , Amruta Shete , Kuldeep Vinchurkar , Sachin S. Mali , Sudarshan Singh , Pooja V. Nagime

{"title":"Smart healthcare: Artificial intelligences impact on drug development and patient care","authors":"Sachin Mendhi , Krutika Sawarkar , Amruta Shete , Kuldeep Vinchurkar , Sachin S. Mali , Sudarshan Singh , Pooja V. Nagime","doi":"10.1016/j.ipha.2025.01.003","DOIUrl":"10.1016/j.ipha.2025.01.003","url":null,"abstract":"<div><div>The integration of artificial intelligence (AI) into healthcare has catalyzed significant advancements in drug development and patient care, revolutionizing traditional methodologies. This review explores the multifaceted impact of AI on critical areas, highlighting its transformative potential and addressing associated challenges. In drug development, AI facilitates accelerated discovery processes, enhances precision in predicting drug efficacy and safety, and optimizes clinical trial designs. AI-driven technologies such as machine learning (ML) algorithms and deep learning models enable the analysis of vast datasets, leading to the identification of novel therapeutic targets and personalized treatment strategies. In patient care, AI enhances diagnostic accuracy, enables predictive analytics for disease management, and supports telemedicine as well as remote monitoring, thereby improving patient outcomes and accessibility to healthcare services. Despite the promising advancements, the review critically examines the ethical, regulatory, and implementation challenges that accompany AI integration in healthcare. By providing a comprehensive overview of AI's current and potential contributions, this paper aims to provide an elaborative guide that future research and policymaking in smart healthcare.</div></div>","PeriodicalId":100682,"journal":{"name":"Intelligent Pharmacy","volume":"3 3","pages":"Pages 225-234"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144272366","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Artificial intelligence, computational tools and robotics for drug discovery, development, and delivery 用于药物发现、开发和交付的人工智能、计算工具和机器人技术

Intelligent Pharmacy Pub Date : 2025-06-01 DOI: 10.1016/j.ipha.2025.01.001

Ayodele James Oyejide , Yemi Adekola Adekunle , Oluwatosin David Abodunrin , Ebenezer Oluwatosin Atoyebi

{"title":"Artificial intelligence, computational tools and robotics for drug discovery, development, and delivery","authors":"Ayodele James Oyejide , Yemi Adekola Adekunle , Oluwatosin David Abodunrin , Ebenezer Oluwatosin Atoyebi","doi":"10.1016/j.ipha.2025.01.001","DOIUrl":"10.1016/j.ipha.2025.01.001","url":null,"abstract":"<div><div>The integration of Artificial Intelligence (AI) and robotics into the pharmaceutical sector is rapidly transforming drug discovery, development, and delivery (D-DDD) processes. Traditional drug development is often characterized by lengthy timelines, high costs, and complex challenges associated with target identification, drug efficacy, and safety profiling. AI and robotics offer transformative solutions, bringing speed, precision, and scalability to various stages of D-DDD. In this review, we analyze cutting-edge advancements in AI-driven predictive modeling, machine learning algorithms for molecular screening, and data mining techniques that enable efficient drug target identification and toxicity prediction. We also explore robotics applications that enhance automation in high-throughput screening, compound synthesis, and patient-specific drug delivery systems. Through examining the applications, limitations, and future trends of these technologies, this review provides a comprehensive outlook on the potential of AI and robotics to streamline the drug pipeline and enable personalized therapeutic strategies. Our review reveals that the convergence of AI, robotics, and big data has potential to reshape pharmaceutical research, reduce costs, and pave the way for more accessible, effective therapies. This review thus serves as a critical resource for understanding the future trajectory of intelligent, technology-driven pharmacy and its implications for advancing healthcare.</div></div>","PeriodicalId":100682,"journal":{"name":"Intelligent Pharmacy","volume":"3 3","pages":"Pages 207-224"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144272365","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

ECLUNG consensus/guidelines development principles and methods (2024 edition) ECLUNG共识/指南制定原则和方法（2024年版）

Intelligent Pharmacy Pub Date : 2025-04-01 DOI: 10.1016/j.ipha.2024.11.004

Chunwei Xu , Yue Hao , Dong Wang , Shirong Zhang , Wenxian Wang , Qian Wang , Tangfeng Lv , Zhengbo Song , Ziming Li

引用次数: 0

Evaluation of the hypoglycemic and hypotensive efficacy of sodium-glucose cotransporter-2 inhibitors in patients with type 2 diabetes: A model-based dose–response network meta-analysis 评价钠-葡萄糖共转运蛋白-2抑制剂对2型糖尿病患者的降糖降压效果：基于模型的剂量-反应网络meta分析

Intelligent Pharmacy Pub Date : 2025-04-01 DOI: 10.1016/j.ipha.2025.02.001

Sanbao Chai , Fengqi Liu , Pei Li , Siyan Zhan , Feng Sun

{"title":"Evaluation of the hypoglycemic and hypotensive efficacy of sodium-glucose cotransporter-2 inhibitors in patients with type 2 diabetes: A model-based dose–response network meta-analysis","authors":"Sanbao Chai , Fengqi Liu , Pei Li , Siyan Zhan , Feng Sun","doi":"10.1016/j.ipha.2025.02.001","DOIUrl":"10.1016/j.ipha.2025.02.001","url":null,"abstract":"<div><h3>Aims</h3><div>To study the dose effect relationship of sodium-glucose cotransporter-2 inhibitor (SGLT-2i) in reducing blood glucose and blood pressure in type 2 diabetes mellitus (T2DM).</div></div><div><h3>Materials and methods</h3><div>We searched PubMed, Embase, Web of Science, Cochrane Library, and clinicaltrials.gov for related literature, with the search period spanning from the establishment of each platform to May 1, 2024. The main analysis method used is model-based network meta-analysis.</div></div><div><h3>Results</h3><div>A total of 192 RCTs involving <strong>67,677</strong> patients with T2DM were included in this study. The results showed that SGLT-2i reduced glycated hemoglobin A1c (HbA1c) in T2DM by 0.50 % (95 % CI: 0.49 % ∼ 0.50 %) compared with placebo. The hypoglycemic effects of Luseogliflozin and Henagliflozin on HbA1c ranked first and second, with values of 0.92 % (95 % CI: 0.61 % ∼ 1.28 %) and 0.91 % (95 % CI: 0.61 % ∼ 1.36 %), respectively. Compared with placebo, the results showed that SGLT-2i lowered systolic blood pressure (SBP) by 3.23 mmHg (95 % CI: 3.19 mmHg ∼ 3.26 mmHg) and diastolic blood pressure (DBP) by 4.16 mmHg (95 % CI: 4.13 mmHg ∼ 4.18 mmHg) in patients with T2DM, respectively. Canagliflozin showed the greatest reduction in SBP and Luseogliflozin showed the greatest reduction in DBP, respectively.</div></div><div><h3>Conclusions</h3><div>The effect of SGLT-2i in reducing HbA1c in patients with T2DM increased with increasing daily dose, with Luseogliflozin and Henagliflozin being the most effective. SGLT-2i significantly reduced both SBP and DBP in T2DM, but there was no significant dose–response relationship. Among the SGLT-2i, Canagliflozin and Luseogliflozin exhibited better antihypertensive effects.</div></div>","PeriodicalId":100682,"journal":{"name":"Intelligent Pharmacy","volume":"3 2","pages":"Pages 150-158"},"PeriodicalIF":0.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143767172","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Enhancing drug discovery with AI: Predictive modeling of pharmacokinetics using Graph Neural Networks and ensemble learning 用人工智能增强药物发现：使用图神经网络和集成学习的药代动力学预测建模

Intelligent Pharmacy Pub Date : 2025-04-01 DOI: 10.1016/j.ipha.2024.11.002

R. Satheeskumar

{"title":"Enhancing drug discovery with AI: Predictive modeling of pharmacokinetics using Graph Neural Networks and ensemble learning","authors":"R. Satheeskumar","doi":"10.1016/j.ipha.2024.11.002","DOIUrl":"10.1016/j.ipha.2024.11.002","url":null,"abstract":"<div><div>Accurately predicting pharmacokinetic (PK) parameters such as absorption, distribution, metabolism, and excretion (ADME) is essential for optimizing drug efficacy, safety, and development timelines. Traditional experimental methods are often slow and expensive, driving the need for advanced AI-based approaches in PK modeling. This study compares cutting-edge machine learning models, including Graph Neural Networks (GNNs), Transformers, and Stacking Ensembles, against traditional models like Random Forest and XGBoost, using a dataset of over 10,000 bioactive compounds from the ChEMBL database. The Stacking Ensemble model achieved the highest accuracy (<em>R</em><sup>2</sup> of 0.92, MAE of 0.062), outperforming GNNs (<em>R</em><sup>2</sup> of 0.90) and Transformers (<em>R</em><sup>2</sup> of 0.89). These AI models excelled in capturing complex molecular interactions and long-range dependencies, significantly improving PK predictions. The high accuracy achieved (<em>R</em><sup>2</sup> = 0.92) by the Stacking Ensemble method indicates that AI models can streamline the drug discovery process by reducing costly in vivo experiments, enabling faster go/no-go decisions during preclinical evaluations, and ultimately accelerating the development of new therapeutics. This reduction in time and cost could facilitate broader industry adoption of AI-driven PK modeling. Furthermore, Bayesian optimization was employed to fine-tune hyperparameters, further enhancing the performance and robustness of these predictive models.</div></div>","PeriodicalId":100682,"journal":{"name":"Intelligent Pharmacy","volume":"3 2","pages":"Pages 127-140"},"PeriodicalIF":0.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143767169","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0