相关实验视频

Updated: May 27, 2025

A High-throughput Assay for the Prediction of Chemical Toxicity by Automated Phenotypic Profiling of Caenorhabditis elegans

A High-throughput Assay for the Prediction of Chemical Toxicity by Automated Phenotypic Profiling of Caenorhabditis elegans

Published on: March 14, 2019

用可解释的机器学习技术对不平衡的数据进行农药生殖毒性的预测建模

Mihkel Kotli¹, Geven Piir¹, Uko Maran¹

¹Institute of Chemistry, University of Tartu, Ravila 14a, Tartu 50411, Estonia.

|February 17, 2025

概括

开发计算模型来预测地的化学生殖毒性对于环境安全至关重要. 这项研究创建了一个先进的定量结构-活动关系 (QSAR) 模型,达到77%的平衡精度,以确定关键的有毒结构特征.

科学领域:

环境毒理学环境毒理学
计算化学的计算化学
生态毒理学生态毒理学

背景情况:

虫是重要的土壤指标物种,因此对它们的生殖毒性评估至关重要.
目前用于确定化学物质生殖毒性的现有方法是不够的,需要计算方法.
需要预测模型来描述和预测化学物质对繁殖的影响.

研究的目的:

开发一个先进的定量结构-活动关系 (QSAR) 模型来预测地的繁殖毒性.
为了应对生态毒理学建模中复杂,不平衡的数据集所带来的挑战.
使用SHAP值来解释影响农药毒性的结构特征.

主要方法:

集成的梯度增强决策树,用于特征选择的遗传算法和用于超参数调整的贝叶斯优化.
使用SHAP (夏普利添加式解释) 值来解释模型的可解释性.
构建了一个最终的堆叠组合模型,结合了个别模型的优势.

主要成果:

在一个由147种化合物组成的外部测试集上,获得了77%的平衡精度.
确定了溶解和可水解键的数量作为影响毒性的关键分子描述因素.
证明了开发的QSAR模型的明确定义的应用领域.

结论:

开发的QSAR模型为的繁殖毒性提供了足够的预测能力.
该模型的可解释性突出了与农药毒性相关的关键结构特征.
该模型遵循FAIR原则,并在QsarDB.org上公开提供,以便更广泛地使用.

更多相关视频

Comprehensive Assessment of Germline Chemical Toxicity Using the Nematode Caenorhabditis elegans

Comprehensive Assessment of Germline Chemical Toxicity Using the Nematode Caenorhabditis elegans

Published on: February 22, 2015

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

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...