The octanol–water partition coefficient (K_ow) is an extremely important and widely used parameter for the study of the distribution and balance of organic pollutants in environmental media. Therefore, the theoretical determination and prediction of such a property are vital in environmental chemistry. The past research on the use of models based on the quantitative structure–property relationship (QSPR) for the estimation of K_ow has significant problems such as data redundancy and computational complexity in the molecular description. In this work, the genetic algorithm is coupled with the random forest algorithm to select the most suitable molecular feature combination from a vast number of features. As a consequence, the number of descriptors for developing the model recommended in available models is significantly reduced. Moreover, a combination of the backpropagation neural network and Bayesian optimization allows the development of an intelligent procedure for tuning the relevant model parameters. On the basis of comparison of the obtained estimations to the results of the available QSPR models in the literature, the developed model in this work shows considerably higher accuracy and predictability.

中文翻译：

---

构建基于DNN的QSPR属性预测模型中特征与超参数确定的双重自适应智能优化

辛醇-水分配系数（K _ow）是研究环境介质中有机污染物分布和平衡的一个极其重要和广泛使用的参数。因此，这种性质的理论确定和预测在环境化学中至关重要。过去研究使用基于定量结构-性能关系（QSPR）的模型估计K _ow在分子描述中存在数据冗余、计算复杂等重大问题。在这项工作中，遗传算法与随机森林算法相结合，从海量特征中选择最合适的分子特征组合。因此，用于开发可用模型中推荐的模型的描述符数量显着减少。此外，反向传播神经网络和贝叶斯优化的组合允许开发用于调整相关模型参数的智能程序。在将获得的估计与文献中可用的 QSPR 模型的结果进行比较的基础上，本工作中开发的模型显示出相当高的准确性和可预测性。