Robust modelling of acute toxicity towards fathead minnow (<i>Pimephales promelas)</i> using counter-propagation artificial neural networks and genetic algorithm

Large worldwide use of chemicals has caused great concern about their possible adverse effects on human health, flora and fauna. Increased production of new chemicals has also increased demand for their risk assessment. Traditionally, results from animal tests have been used to assess toxicity of chemicals. However, such methods are ethically questionable since they involve killing and causing suffering of the test animals. Therefore, new <i>in silico</i> methods are being sought to replace the traditional <i>in vivo</i> and <i>in vitro</i> testing methods. In this article we report on one method that can be used to build robust models for the prediction of compounds’ properties from their chemical structure. The method has been developed by combining a genetic algorithm, a counter-propagation artificial neural network and cross-validation. It has been tested using existing data on toxicity to fathead minnow (<i>Pimephales promelas</i>). The results show that the method may give reliable results for chemicals belonging to the applicability domain of the developed models. Therefore, it can aid the risk assessment of chemicals and consequently reduce demand for animal tests.全球范围内化学品的大规模应用，引发了人们对其可能给人类健康、动植物带来不良影响的广泛担忧。新型化学品产量的持续增长，也进一步提升了其风险评估的需求。传统上，科研人员常借助动物实验结果评估化学品的毒性，但此类方法因涉及实验动物的宰杀与痛苦，在伦理层面饱受争议。因此，学界正积极探寻新型计算机模拟（in silico）方法，以替代传统的体内（in vivo）与体外（in vitro）测试手段。本文介绍一种可基于化合物化学结构构建稳健模型、用于预测其性质的方法。该方法通过结合遗传算法、对向传播人工神经网络（Counter-propagation Artificial Neural Network）与交叉验证技术开发而成。研究团队采用针对黑头呆鱼（Pimephales promelas）毒性的现有数据集对该方法进行了测试。结果显示，对于落入所构建模型适用域范围内的化学品，该方法可输出可靠的预测结果。因此，该方法能够辅助化学品风险评估工作，进而减少对动物实验的需求。