机器学习用于预测人类药物诱导的心脏毒性:一个范围审查
Ja-Young Han1, Min Jung Kim1, Hyunwoo Kim2
1Graduate School of Pharmaceutical Sciences, Ewha Womans University, Seoul 03760, Republic of Korea.
Toxics
|December 24, 2025
概括
机器学习模型在预测超越hERG抑制的各种药物诱导心脏毒性结果方面表现有希望. 严格的验证和异质的数据整合对于提高药物安全性预测准确度至关重要.
科学领域:
- 药理学和毒理学 药理学和毒理学
- 计算生物学 计算生物学
- 药物开发 药物开发
背景情况:
- 药物诱导的心脏毒性是制药研究和患者安全的一个重大障碍.
- 现有的机器学习 (ML) 方法往往只关注特定的机制,如hERG抑制.
- 对于全面的心脏毒性评估,需要更广泛的预测范围.
研究的目的:
- 系统地审查使用ML模型预测广泛的药物诱导心脏毒性的研究.
- 在这个领域确定常见的数据源,特征,算法和性能指标.
- 评估ML在药物心脏毒性预测中的当前状态和潜力.
主要方法:
- 在主要的科学数据库 (PubMed,EMBASE,SCOPUS,Web of Science) 进行系统的文献搜索.
- 数据的提取和分类,包括研究来源,特征类型,ML算法和性能评估方法.
- 分析了25项符合ML基于心脏毒性预测的纳入标准的研究.
主要成果:
- 研究涵盖了各种心脏毒性结果,如心律不整,心力衰竭和心肌梗塞.
- SIDER数据库和分子描述符是常见的数据来源和特征.
- 支持矢量机器 (SVM) 和随机森林 (RF) 经常被使用,显示出有希望的预测性能,AUC-ROC> 0.70和准确性> 0.75在几个情况下.
- 外部验证有限,但显示了ML的潜力.
结论:
- 机器学习对预测各种药物诱导的心脏毒性有很大的前景.
- 整合不同的数据类型和采用强大的验证策略是提高预测模型的关键.
- 需要进一步的研究来解决外部验证的局限性,并提高模型的通用性.
相关概念视频
Pharmacogenomics: Identification of New Drug Targets
Advances in genomics have profoundly influenced drug discovery by increasing both the speed and accuracy of pharmaceutical development. Pharmacogenomics, which examines how genetic variation influences drug response, facilitates the identification of novel therapeutic targets and enables patient stratification for personalized treatment. These strategies contribute to improved drug efficacy, minimized adverse effects, and more efficient clinical trial design.Mapping genetic differences...
Drug Toxicity: Overview
Drug toxicity quantifies the harm a compound causes to an organism, varying by dose and potentially impacting whole systems or specific organs like the liver. Toxic reactions may arise from venomous insect or spider bites, with effects ranging from mild symptoms to severe outcomes such as brain damage or death. Common forms of acute poisoning include ethanol intoxication and overdose of pain or fever medications, with substances like GHB and heroin being particularly lethal at doses close to...
Drug Toxicity: Risk factors
Adverse Drug Reactions (ADRs) are potential complications that arise during pharmacotherapy, influenced by multiple risk factors. Age plays a significant role; both neonates and the elderly are at heightened risk due to their respective immature and diminished metabolic and elimination processes. Gender also impacts ADRs, with females experiencing a 1.5 to 1.7-fold greater risk than males, which may be linked to pharmacokinetic, pharmacodynamic, and hormonal differences. Notably, neonates, the...
Drug toxicity: Idiosyncratic Reactions
Idiosyncratic drug reactions represent abnormal chemical responses that vary significantly among individuals, ranging from extreme sensitivity to low doses to insensitivity to high doses. These reactions often occur due to the drug's covalent binding with serum proteins, forming a foreign hapten that triggers an immunotoxicological response. The variability in drug reactions has a strong pharmacogenetic foundation, with genetic differences crucial in how individuals metabolize drugs. For...
Toxicity Testing in Animals
Toxicity tests in animals are grounded on two main assumptions: first, the effects observed in laboratory animals can be extrapolated to humans, especially when adjusted for body surface area; second, high-dose exposure in animals is essential to identify potential human hazards from lower doses. This is based on the quantal dose-response concept, which faces the challenge of extrapolating results from relatively few test animals to much larger human populations. For example, a 0.01% incidence...
Pharmaceutical Poisoning: Potential Scenarios
Pharmaceutical poisoning can occur through various channels, impacting an estimated 2 million hospitalized patients in the U.S. annually with serious adverse drug responses. These scenarios encompass both therapeutic uses, such as drug toxicity, where even standard dosages can lead to severe central nervous system depression, and non-therapeutic exposures, including accidental ingestion by children, and environmental and occupational exposures.Unintentional poisonings often involve exploratory...


