Skin Corrosion/Irritation (Corr./Irrit.) has long been a health hazard in the Globally Harmonized System (GHS). Several in silico models have been built to predict Skin Corr./Irrit. as an alternative to the increasingly restricted animal testing. However, current studies are limited by data amount/quality and model availability. To address these issues, we compiled a traceable consensus GHS data set comprising 731 Corr., 1283 Irrit., and 1205 negative (Neg.) samples from 6 governmental databases and 2 external data sets. Then, a series of binary classifiers were developed with five machine learning (ML) algorithms and six molecular representations. For 10-fold cross-validation, the best Corr. vs Neg. classifier achieved an Area Under the Receiver Operating Characteristic Curve (AUC) of 97.1%, while the best Irrit. vs Neg. classifier achieved an AUC of 84.7%. Compared with existing in silico tools on external validation, our Attentive FP classifiers showed the highest metrics on Corr. vs Neg. and the second highest accuracy on Irrit. vs Neg. The SHapley Additive exPlanation approach was further applied to figure out important molecular features, and the attention weights were visualized to perform interpretable prediction. Structural alerts associated with Skin Corr./Irrit. were also identified. The interpretable Attentive FP classifiers were integrated into the software AttentiveSkin at https://github.com/BeeBeeWong/AttentiveSkin. The conventional ML classifiers are also provided on our platform admetSAR at http://lmmd.ecust.edu.cn/admetsar2/. Considering the data deficiency and the limited model availability of Skin Corr./Irrit., we believe that our data set and models could facilitate chemical safety assessment and relevant studies.

中文翻译：

---

AttentiveSkin：通过可解释的机器学习方法预测化学品对皮肤的腐蚀/刺激潜力

皮肤腐蚀/刺激 (Corr./Irrit.) 长期以来一直是全球统一制度 (GHS) 中的健康危害。已经建立了几个计算机模型来预测皮肤腐蚀/刺激。作为日益受到限制的动物试验的替代方案。然而，当前的研究受到数据量/质量和模型可用性的限制。为了解决这些问题，我们编制了一个可追踪的共识 GHS 数据集，其中包括来自 6 个政府数据库和 2 个外部数据集的 731 个 Corr.、1283 个 Irrit. 和 1205 个阴性 (Neg.) 样本。然后，使用五种机器学习（ML）算法和六种分子表示开发了一系列二元分类器。对于 10 倍交叉验证，最好的 Corr。与阴性。分类器的接收器工作特征曲线下面积 (AUC) 达到 97.1%，同时 Irrit 最好。与阴性。分类器的 AUC 达到 84.7%。与现有的外部验证计算机工具相比，我们的 Attentive FP 分类器在 Corr 上显示出最高的指标。与阴性。以及 Irrit 的第二高准确度。与阴性。进一步应用 SHapley Additive exPlanation 方法来找出重要的分子特征，并将注意力权重可视化以执行可解释的预测。与皮肤腐蚀/刺激相关的结构性警报。也被识别出来。可解释的 Attentive FP 分类器已集成到软件 AttentiveSkin 中，网址为 https://github.com/BeeBeeWong/AttentiveSkin。我们的平台 admetSAR 上也提供了传统的 ML 分类器，网址为 http://lmmd.ecust.edu.cn/admetsar2/。考虑到皮肤腐蚀/刺激的数据缺乏和模型可用性有限，我们相信我们的数据集和模型可以促进化学品安全评估和相关研究。