试验者:在药物开发的后期阶段,一种以化学为重点的毒性风险预测器
Huanni Zhang1, Matthias Welsch1, William Schueller2
1Department of Pharmaceutical Sciences, Division of Pharmaceutical Chemistry, Faculty of Life Sciences, University of Vienna, Vienna, 1090, Austria; Christian Doppler Laboratory for Molecular Informatics in the Biosciences, Department for Pharmaceutical Sciences, University of Vienna, Vienna, 1090, Austria; Vienna Doctoral School of Pharmaceutical, Nutritional and Sport Sciences (PhaNuSpo), University of Vienna, Vienna, 1090, Austria.
药物发现面临来自晚期毒性失败的挑战. 一个新的预测模型,Trialblazer,使用分子数据来早期识别潜在的毒性风险,帮助药物开发和安全性评估.
科学领域:
- 计算化学是一种计算化学.
- 药物发现 药物发现
- 毒理学 毒理学 毒理学
背景情况:
- 药物开发经常受到后期不良影响的阻碍,导致大量的财务和时间损失.
- 有限的公共数据和预测工具可用于识别晚期毒性,这在制药研究中构成了重大挑战.
研究的目的:
- 开发和验证用于识别具有潜在毒性候选药物的预测模型.
- 创建一个公开可访问的工具,以帮助早期的毒性风险评估.
主要方法:
- 编制了1603种良性药物和238种毒性候选药物的数据集.
- 开发和训练使用摩根指纹和预测生物活性概况的多层感知子 (MLP) 分类器.
- 通过使用欧洲药品署 (EMA) 的交叉验证和外部药监数据,验证了最好的模型Trialblazer.
主要成果:
- 试验者模型实现了0.87的交叉验证ROC-AUC和0.47.47的MCC.
- 该模型成功地根据其安全性概况区分了药物,当应用到外部数据时.
- 来自Trialblazer的预测可以作为潜在毒性风险的指标.
结论:
- 在药物开发过程中,Trialblazer模型为标记具有更高毒性风险的化合物提供了一个有价值的工具.
- 该模型在没有目标信息的情况下预测毒性的能力使其适用于新型化合物.
- 虽然Trialblazer很有用,但它应该补充,而不是取代现有的安全评估方法.
更多相关视频
05:45Developmental Toxicity Assay Based on Real-Time Monitoring of Fibroblast Growth Factor Signal Disruption in Human Induced Pluripotent Stem Cells
Published on: October 10, 2025
16:02Demonstration of the Sequence Alignment to Predict Across Species Susceptibility Tool for Rapid Assessment of Protein Conservation
Published on: February 10, 2023
相关概念视频
Preclinical Development: Overview
Drug Discovery: Overview
Mutagenicity and Carcinogenicity
Effect of Hepatic Disease on Pharmacokinetics: Pathophysiologic Assessment and Liver Function Test
Drug Product Performance: In Vitro–In Vivo Correlation
Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast,...
