相关实验视频

Updated: Jun 6, 2025

In Silico Modeling Method for Computational Aquatic Toxicology of Endocrine Disruptors: A Software-Based Approach Using QSAR Toolbox

In Silico Modeling Method for Computational Aquatic Toxicology of Endocrine Disruptors: A Software-Based Approach Using QSAR Toolbox

Published on: August 28, 2019

构建可解释的集体学习模型,用于预测鱼类中的有机化学物质生物积累参数

Minghua Zhu¹, Zijun Xiao², Tao Zhang³

¹Key Laboratory of Integrated Regulation and Resources Development of Shallow Lakes of Ministry of Education, Hohai University, Nanjing 210098, China; College of Environment, Hohai University, Nanjing 210098, China.

Journal of hazardous materials

|November 23, 2024

概括

集体学习模型显著改善了化学生物积累参数的预测,优于单个模型. 这种方法通过提供准确的预测和可解释的结果来提高化学风险评估.

科学领域:

环境化学环境化学
计算毒理学计算毒理学
化学信息学化学信息学

背景情况:

准确预测生物积累参数对于化学品安全评估至关重要.
现有的预测模型通常由于单个算法依赖而受到有限的准确性和糟糕的解释性的影响.

研究的目的:

开发使用集体学习 (EL) 和夏普利添加式扩展 (SHAP) 的生物积累参数的增强预测模型.
与单个模型相比,评估EL模型的性能和可解释性.

主要方法:

使用2496种化学物质的数据集,为三个生物积累参数构建EL模型.
使用确定系数 (R2) 验证模型准确性.
使用基于结构-活动-景观 (AD_SAL) 的方法对适用性领域的表征.
应用SHAP用于模型解释,以确定影响生物积累的关键分子特征.

主要成果:

在EL模型中,预测准确度更高,在验证集中确定系数高达0.861.
开发的模型在本研究和先前的研究中表现优于单个模型.
SHAP分析揭示了水性,水溶性和分子大小影响生物积累的关键特征.
这些模型成功地用于预测中国化学库存中的4374种化学品的生物积累.

结论:

组合学习与SHAP相结合,为预测生物积累参数提供了强大的和可解释的方法.
开发的模型和适用性领域评估支持准确的化学风险评估和管理.
这项研究为环境化学安全提供了有价值的数据和预测工具.

关键词:

生物积累因子的生物积累因子生物度因子生物度因子生物放大因子生物放大因子组合学习学习组合学习机器学习是机器学习.

更多相关视频

Experimental Protocol for Examining Behavioral Response Profiles in Larval Fish: Application to the Neuro-stimulant Caffeine

Experimental Protocol for Examining Behavioral Response Profiles in Larval Fish: Application to the Neuro-stimulant Caffeine

Published on: July 24, 2018

Laboratory Estimation of Net Trophic Transfer Efficiencies of PCB Congeners to Lake Trout Salvelinus namaycush from Its Prey

Laboratory Estimation of Net Trophic Transfer Efficiencies of PCB Congeners to Lake Trout Salvelinus namaycush from Its Prey

Published on: August 29, 2014

相关概念视频

Mechanistic Models: Compartment Models in Individual and Population Analysis

Mechanistic Models: Compartment Models in Individual and Population Analysis

Mechanistic models are utilized in individual analysis using single-source data, but imperfections arise due to data collection errors, preventing perfect prediction of observed data. The mathematical equation involves known values (Xi), observed concentrations (Ci), measurement errors (εi), model parameters (ϕj), and the related function (ƒi) for i number of values. Different least-squares metrics quantify differences between predicted and observed values. The ordinary least...