The evaluation of persistency of chemicals in environmental media (water, soil, sediment) is included in European Regulations, in the context of the Persistence, Bioaccumulation and Toxicity (PBT) assessment. In silico predictions are valuable alternatives for compounds screening and prioritization. However, already existing prediction tools have limitations: narrow applicability domains due to their relatively small training sets, and lack of medium-specific models. A dataset of 1579 unique compounds has been collected, merging several persistence data sources annotated by, at least, one experimental dissipation half-life value for the given environmental medium. This dataset was used to train binary classification models discriminating persistent/non-persistent (P/nP) compounds based on REACH half-life thresholds on sediment, water and soil compartments. Models were built using ISIDA (In SIlico design and Data Analysis) fragment descriptors and support vector regression, random forest and naïve Bayesian machine-learning methods. All models scored satisfactory performances: sediment being the most performing one (BA_ext = 0.91), followed by water (BA_ext = 0.77) and soil (BA_ext = 0.76). The latter suffer from low detection of persistent (‘P’) compounds (Sn_ext = 0.50), reflecting discrepancies in reported half-life measurements among the different data sources. Generated models and collected data are made publicly available.

在持久性，生物蓄积性和毒性（PBT）评估的背景下，欧洲法规中包括了对环境介质（水，土壤，沉积物）中化学物质的持久性的评估。在计算机模拟中，预测是化合物筛选和优先排序的有价值的替代方法。但是，已经存在的预测工具具有局限性：由于训练集相对较小，因此适用范围较窄，并且缺乏针对特定介质的模型。收集了1579种独特化合物的数据集，合并了几个持久性数据源，这些数据源至少由给定环境介质的一个实验耗散半衰期值标注。此数据集用于训练二元分类模型，该模型基于沉积物上的REACH半衰期阈值来区分持久性/非持久性（P / nP）化合物，水和土壤隔室。使用ISIDA（在SIlico设计和数据分析中）片段描述符构建模型，并支持矢量回归，随机森林和朴素的贝叶斯机器学习方法。所有模型的表现均令人满意：沉积物是表现最好的（BA_ext  = 0.91），然后是水（BA _ext  = 0.77）和土壤（BA _ext  = 0.76）。后者的持久性（'P'）化合物检出率低（Sn _ext  = 0.50），反映出不同数据源之间报告的半衰期测量结果存在差异。生成的模型和收集的数据可公开获得。