在非传统的建模框架c-RASAR中应用化学相似性测量,并将维度减小技术与代表性肝毒性数据集相结合
Arkaprava Banerjee1, Kunal Roy2
1Drug Theoretics and Cheminformatics Laboratory, Department of Pharmaceutical Technology, Jadavpur University, Kolkata, 700 032, India.
Scientific reports
|September 6, 2024
概括
这项研究引入了一种新的分类阅读跨结构-活性关系 (c-RASAR) 方法,用于预测化学肝毒性. 与传统方法相比,c-RASAR模型显示出更高的性能和可解释性,为化学安全评估提供了可靠的工具.
科学领域:
- * 计算化学和化学信息学
- * 毒理学和药物安全性评估
- * 机器学习和人工智能在化学研究中的应用
背景情况:
- * 化学信息学的传统机器学习 (ML) 模型依赖于标准分子描述器.
- *预测化学毒性,如肝毒性,对于药物开发和化学安全至关重要.
- *现有的方法往往缺乏解释性,可能无法完全捕捉复杂的结构-活动关系.
研究的目的:
- * 开发和验证一个新的分类阅读跨结构-活动关系 (c-RASAR) 建模框架.
- * 通过结合Read-Cross衍生相似性和基于错误的描述器来改善化学肝毒性的预测.
- *使用可解释AI (XAI) 技术提高预测模型的可解释性.
主要方法:
- * 通过结合定量结构-活动关系 (QSAR) 和 Read-Across 概念,开发c-RASAR模型.
- * 运用与传统的QSAR描述符一起使用Read-Across衍生相似性和基于错误的描述符.
- * 应用各种分类ML算法,缩小维度技术 (t-SNE,UMAP) 和ARKA框架用于模型开发和验证.
- *对测试集和外部数据集的模型性能进行评估,包括与之前报告的模型进行比较.
主要成果:
- *c-RASAR描述符在分组类似化合物和识别活动悬崖方面表现优于标准QSAR描述符.
- *开发的c-RASAR模型,特别是线性LDA模型,显示出对肝毒性的高预测性.
- *可解释AI (XAI) 与Read-Across相结合,提供了对描述器贡献和化学多样性的见解.
- * LDA c-RASAR模型在美国FDA色书数据集和外部数据集上表现优于之前报告的模型.
结论:
- *c-RASAR方法提供了一种简单,可重复和可转移的方法来预测化学肝毒性.
- *RASAR描述符增强可建模性,并促进活动悬崖的识别,改进了传统的QSAR描述符.
- *LDA c-RASAR模型是一种高度预测和可解释的工具,适用于查化学肝毒性.
- *这种方法促进了ML和Read-Across在化学信息学中的应用,用于化学安全评估.
相关概念视频
Structure-Activity Relationships and Drug Design
1.9K
Drug design is a dynamic field that involves discovering and developing new medications based on specific biological targets. This process heavily relies on structure-activity relationships (SAR) and quantitative structure-activity relationships (QSAR) to guide the design and optimization of efficient drugs.
SAR studies the intricate relationship between a drug's chemical structure and biological activity. It focuses on understanding how modifications to a drug's structure can influence...
SAR studies the intricate relationship between a drug's chemical structure and biological activity. It focuses on understanding how modifications to a drug's structure can influence...
1.9K
Model-Independent Approaches for Pharmacokinetic Data: Noncompartmental Analysis
426
Noncompartmental analyses offer an alternative method for describing drug pharmacokinetics without relying on a specific compartmental model. In this approach, the drug's pharmacokinetics are assumed to be linear, with the terminal phase log-linear. This assumption allows for simplified analysis and interpretation of the drug's behavior in the body.
One important characteristic of noncompartmental analyses is that drug exposure increases proportionally with increasing doses. This...
One important characteristic of noncompartmental analyses is that drug exposure increases proportionally with increasing doses. This...
426


