Davide Bassani, Neil John Parrott, Nenad Manevski, Jitao David Zhang
{"title":"您的另一项任务:通过机器学习预测小分子药物的药代动力学特性。","authors":"Davide Bassani, Neil John Parrott, Nenad Manevski, Jitao David Zhang","doi":"10.1080/17460441.2024.2348157","DOIUrl":null,"url":null,"abstract":"<p><strong>Introduction: </strong>Prediction of pharmacokinetic (PK) properties is crucial for drug discovery and development. Machine-learning (ML) models, which use statistical pattern recognition to learn correlations between input features (such as chemical structures) and target variables (such as PK parameters), are being increasingly used for this purpose. To embed ML models for PK prediction into workflows and to guide future development, a solid understanding of their applicability, advantages, limitations, and synergies with other approaches is necessary.</p><p><strong>Areas covered: </strong>This narrative review discusses the design and application of ML models to predict PK parameters of small molecules, especially in light of established approaches including <i>in vitro-in vivo</i> extrapolation (IVIVE) and physiologically based pharmacokinetic (PBPK) models. The authors illustrate scenarios in which the three approaches are used and emphasize how they enhance and complement each other. In particular, they highlight achievements, the state of the art and potentials of applying machine learning for PK prediction through a comphrehensive literature review.</p><p><strong>Expert opinion: </strong>ML models, when carefully crafted, regularly updated, and appropriately used, empower users to prioritize molecules with favorable PK properties. Informed practitioners can leverage these models to improve the efficiency of drug discovery and development process.</p>","PeriodicalId":12267,"journal":{"name":"Expert Opinion on Drug Discovery","volume":null,"pages":null},"PeriodicalIF":6.0000,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Another string to your bow: machine learning prediction of the pharmacokinetic properties of small molecules.\",\"authors\":\"Davide Bassani, Neil John Parrott, Nenad Manevski, Jitao David Zhang\",\"doi\":\"10.1080/17460441.2024.2348157\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Introduction: </strong>Prediction of pharmacokinetic (PK) properties is crucial for drug discovery and development. Machine-learning (ML) models, which use statistical pattern recognition to learn correlations between input features (such as chemical structures) and target variables (such as PK parameters), are being increasingly used for this purpose. To embed ML models for PK prediction into workflows and to guide future development, a solid understanding of their applicability, advantages, limitations, and synergies with other approaches is necessary.</p><p><strong>Areas covered: </strong>This narrative review discusses the design and application of ML models to predict PK parameters of small molecules, especially in light of established approaches including <i>in vitro-in vivo</i> extrapolation (IVIVE) and physiologically based pharmacokinetic (PBPK) models. The authors illustrate scenarios in which the three approaches are used and emphasize how they enhance and complement each other. In particular, they highlight achievements, the state of the art and potentials of applying machine learning for PK prediction through a comphrehensive literature review.</p><p><strong>Expert opinion: </strong>ML models, when carefully crafted, regularly updated, and appropriately used, empower users to prioritize molecules with favorable PK properties. Informed practitioners can leverage these models to improve the efficiency of drug discovery and development process.</p>\",\"PeriodicalId\":12267,\"journal\":{\"name\":\"Expert Opinion on Drug Discovery\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":6.0000,\"publicationDate\":\"2024-06-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Expert Opinion on Drug Discovery\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1080/17460441.2024.2348157\",\"RegionNum\":2,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/5/10 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q1\",\"JCRName\":\"PHARMACOLOGY & PHARMACY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Expert Opinion on Drug Discovery","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1080/17460441.2024.2348157","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/5/10 0:00:00","PubModel":"Epub","JCR":"Q1","JCRName":"PHARMACOLOGY & PHARMACY","Score":null,"Total":0}
引用次数: 0
摘要
导言:药代动力学(PK)特性预测对于药物发现和开发至关重要。机器学习(ML)模型利用统计模式识别来学习输入特征(如化学结构)和目标变量(如 PK 参数)之间的相关性,正越来越多地用于这一目的。为了将用于 PK 预测的 ML 模型嵌入工作流程并指导未来的发展,有必要深入了解这些模型的适用性、优势、局限性以及与其他方法的协同作用:这篇叙述性综述讨论了预测小分子 PK 参数的 ML 模型的设计和应用,特别是考虑到体外-体内外推法(IVIVE)和基于生理的药代动力学(PBPK)模型等既定方法。作者举例说明了这三种方法的应用场景,并强调了它们如何相互促进和补充。特别是,他们通过全面的文献综述,强调了应用机器学习进行 PK 预测的成就、技术水平和潜力:专家观点:机器学习模型经过精心设计、定期更新和合理使用,可以帮助用户优先选择具有良好 PK 特性的分子。知情的从业人员可以利用这些模型提高药物发现和开发过程的效率。
Another string to your bow: machine learning prediction of the pharmacokinetic properties of small molecules.
Introduction: Prediction of pharmacokinetic (PK) properties is crucial for drug discovery and development. Machine-learning (ML) models, which use statistical pattern recognition to learn correlations between input features (such as chemical structures) and target variables (such as PK parameters), are being increasingly used for this purpose. To embed ML models for PK prediction into workflows and to guide future development, a solid understanding of their applicability, advantages, limitations, and synergies with other approaches is necessary.
Areas covered: This narrative review discusses the design and application of ML models to predict PK parameters of small molecules, especially in light of established approaches including in vitro-in vivo extrapolation (IVIVE) and physiologically based pharmacokinetic (PBPK) models. The authors illustrate scenarios in which the three approaches are used and emphasize how they enhance and complement each other. In particular, they highlight achievements, the state of the art and potentials of applying machine learning for PK prediction through a comphrehensive literature review.
Expert opinion: ML models, when carefully crafted, regularly updated, and appropriately used, empower users to prioritize molecules with favorable PK properties. Informed practitioners can leverage these models to improve the efficiency of drug discovery and development process.
期刊介绍:
Expert Opinion on Drug Discovery (ISSN 1746-0441 [print], 1746-045X [electronic]) is a MEDLINE-indexed, peer-reviewed, international journal publishing review articles on novel technologies involved in the drug discovery process, leading to new leads and reduced attrition rates. Each article is structured to incorporate the author’s own expert opinion on the scope for future development.
The Editors welcome:
Reviews covering chemoinformatics; bioinformatics; assay development; novel screening technologies; in vitro/in vivo models; structure-based drug design; systems biology
Drug Case Histories examining the steps involved in the preclinical and clinical development of a particular drug
The audience consists of scientists and managers in the healthcare and pharmaceutical industry, academic pharmaceutical scientists and other closely related professionals looking to enhance the success of their drug candidates through optimisation at the preclinical level.