基于机制的层次机器学习,用于对雌激素,雄激素和甲状腺干扰活动的高通量量预测
Rong Zhang1, Baodi Chang1, Haoyue Tan1,2,3
1State Key Laboratory of Water Pollution Control and Green Resource Recycling, School of Environment, Nanjing University, Nanjing 210023, Jiangsu, China.
我们开发了一个新的框架来准确预测内分泌破坏性化学物质 (EDC) 活动,改进了对雌激素,雄激素和甲状腺 (EAT) 干扰的现有模型. 这种方法增强了化学安全评估.
科学领域:
- 环境化学环境化学
- 毒理学 毒理学 毒理学
- 计算化学计算化学
背景情况:
- 对内分泌干扰化学品 (EDC) 的量化高通量模型受到数据问题和复杂性的限制.
- 现有的模型难以准确预测雌激素,雄激素和甲状腺 (EAT) 干扰.
研究的目的:
- 开发一个机理上基于信息的层次框架,用于定量预测EAT破坏活动.
- 提高内分泌功率预测的准确性和可解释性.
主要方法:
- 数据精制:五步策划创建一个高可信度的数据集,删除错误的阳性和负面.
- 机械集群:基于碎片的方法来分类EAT活动模式.
- 定量建模:由分子模拟提供信息的集群特异组合回归器用于强度估计.
主要成果:
- 与传统方法相比,实现了更好的模型性能 (R2 = 0.72-0.78,RMSE = 0.22-0.48 log10(μM))
- 确定了强大的EAT激动剂 (芳香核,极子替代物) 和对抗剂 (柔性链,刚性支架) 的关键结构特征.
- 分子模拟揭示了受体激活和受体破坏的机制,由激动剂和对抗剂.
结论:
- 开发的框架为准确和可解释的内分泌功率预测提供了下一代战略.
- 机械洞察力增强对EDC受体相互作用的理解.
- 这种方法可以帮助优先考虑化学品进行进一步的测试和风险评估.
更多相关视频
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
07:13Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
Published on: April 18, 2025
相关概念视频
Mechanical Efficiency of Real Machines
However, in reality, no machine can be truly ideal, and all of them experience some...
The Thyroid Gland
The follicles have a central cavity lined by simple cuboidal to squamous epithelial cells called follicular cells. These cells produce the glycoprotein...
Predicting Molecular Geometry
Machines
A free-body diagram of the...
Reaction Mechanisms
For instance, the decomposition of ozone appears to follow a mechanism with two steps:
Machines: Problem Solving II
