‘Ideal correlations’ for the predictive toxicity to <i>Tetrahymena pyriformis</i>

Predictive models for toxicity to <i>Tetrahymena pyriformis</i> are an important component of natural sciences. The present study aims to build up a predictive model for the endpoint using the so-called index of ideality of correlation (<i>IIC</i>). Besides, the comparison of the predictive potential of these models with the predictive potential of models suggested in the literature is the task of the present study. The Monte Carlo technique is a tool to build up the predictive model applied in this study. The molecular structure is represented via a simplified molecular input-line entry system (SMILES). The <i>IIC</i> is a statistical characteristic sensitive to both the correlation coefficient and mean absolute error. Applying of the <i>IIC</i> to build up quantitative structure–activity relationships (QSARs) for the toxicity to <i>Tetrahymena pyriformis</i> improves the predictive potential of those models for random splits into the training set and the validation set. The calculation was carried out with CORAL software (http://www.insilico.eu/coral). The statistical quality of the suggested models is incredibly good for the external validation set, but the statistical quality of the models for the training set is modest. This is the paradox of ideal correlation, which is obtained with applying the <i>IIC.</i> The Monte Carlo technique is a convenient and reliable way to build up a predictive model for toxicity to <i>Tetrahymena pyriformis</i>. The <i>IIC</i> is a useful statistical criterion for building up predictive models as well as for the assessment of their statistical quality.

针对梨形四膜虫（*Tetrahymena pyriformis*）毒性的预测模型是自然科学领域的重要研究内容。本研究旨在借助相关理想指数（IIC）构建针对该毒性终点的预测模型。此外，本研究的另一项任务是将此类模型的预测性能与文献中已报道模型的预测性能进行对比。本研究采用蒙特卡洛方法构建预测模型，分子结构通过简化分子线性输入规范（SMILES）进行表征。相关理想指数（IIC）是一种同时对相关系数与平均绝对误差敏感的统计特征。将该指数应用于构建针对梨形四膜虫毒性的定量构效关系（QSAR）时，可提升模型在训练集与验证集随机划分场景下的预测性能。本研究的计算工作依托CORAL软件（http://www.insilico.eu/coral）完成。所提模型在外部验证集上的统计表现极佳，但训练集上的统计质量则较为一般，这便是应用相关理想指数（IIC）时所得到的“理想相关性悖论”。蒙特卡洛方法是构建梨形四膜虫毒性预测模型的便捷且可靠的途径。相关理想指数（IIC）既可作为构建预测模型的实用统计准则，也可用于评估模型的统计质量。

搜集汇总

背景与挑战

背景概述

该数据集专注于构建预测Tetrahymena pyriformis毒性的模型，采用蒙特卡洛技术和SMILES分子表示法，并引入理想相关性指数（IIC）来优化QSAR模型的统计质量。其特点在于外部验证集表现出色，但训练集统计质量一般，形成了理想相关性悖论，适用于毒理学、环境科学和化学信息学等领域的研究。