相关实验视频
Updated: May 30, 2025

08:50
Predictive Immune Modeling of Solid Tumors
Published on: February 25, 2020
6.9K
InterDIA:通过整体机器学习方法对药物诱导的自身免疫性进行可解释的预测
Lina Huang1, Peineng Liu1, Xiaojie Huang1
1Department of Clinical Pharmacy, Jieyang People's Hospital 522000, China.
Toxicology
|January 27, 2025
概括
我们开发了InterDIA,这是一种机器学习工具,使用分子性质预测药物诱导的自身免疫性 (DIA). 它准确地识别出有毒化合物,帮助早期药物开发和了解DIA病原性.
科学领域:
- 计算毒理学计算毒理学
- 免疫学 免疫学 免疫学
- 药物开发 药物开发
背景情况:
- 由于其复杂性,药物诱导的自身免疫 (DIA) 存在重大预测毒理学挑战.
- 现有的方法与DIA的特异性呈现和病原发生有困难.
- 准确预测DIA对于安全的药物开发至关重要.
研究的目的:
- 开发一个可解释的机器学习框架 (InterDIA) 来预测DIA毒性.
- 确定与DIA相关的关键分子物理化学性质.
- 为早期评估自身免疫药物毒性的实用工具提供.
主要方法:
- 开发了InterDIA,一种使用分子物理化学性质的可解释机器学习框架.
- 采用多策略特征选择和组合重新采样 (简单的组合分类器) 来增强预测.
- 使用SHAP (夏普利添加式解释) 进行模型预测的机械解释.
主要成果:
- 简单组合分类器实现了高性能:AUC为0.8836 (交叉验证) 和0.8930 (外部验证).
- 确定了DIA的关键物理化学决定因素,包括脂性,电荷分布和拓特征.
- 证明模型能够区分具有不同免疫原潜力的相似化合物.
结论:
- InterDIA提供了一种可靠和可解释的方法来预测DIA毒性.
- 识别了与DIA病变发生相关的分子签名,提供了机械学的见解.
- 开发的网络平台为早期风险评估在药物开发中的实际应用提供了便利.
相关概念视频
Autoimmune Disorders
380
Autoimmune diseases are a group of disorders in which the body's immune system mistakenly attacks its own cells, tissues, and organs. This results from an overactive immune response against substances and tissues normally present in the body. Let's delve into the concept and mechanism of autoimmune diseases from an immune system point of view, explore different causes and examples of such diseases, and discuss potential solutions.
Concept and Mechanism of Autoimmune Diseases
The immune...
Concept and Mechanism of Autoimmune Diseases
The immune...
380
Allergic Drug Reactions
806
Allergic reactions related to drugs are hypersensitivity responses driven by the immune system and bear no connection to the drug's therapeutic action. While drugs in isolation do not trigger an immune response, they can interact with endogenous proteins to form antigens. These antigens stimulate lymphocytes to produce antibodies. IgE-type antibodies attach themselves to mast cells. Upon subsequent exposure to the same stimulus, the antigen-antibody interaction is initiated, unleashing...
806

