首页 正文

Current research in toxicology. 2025 May 22:8:100242. doi: 10.1016/j.crtox.2025.100242 Q23.02025

Prediction of the classification, labelling and packaging regulation H-statements with confidence using conformal prediction with N-grams and molecular fingerprints

基于N元语法和分子指纹的符合预测法自信地预测分类、标签和包装条例H项标准 翻译改进

Ulf Norinder  1  2, Ziye Zheng  3  4  5, Ian Cotgreave  4

作者单位 +展开

作者单位

  • 1 Department of Computer and Systems Sciences, Stockholm University, P.O. Box 1073, SE-164 25 Kista, Sweden.
  • 2 MTM Research Centre, School of Science and Technology, Örebro University, 701 82 Örebro, Sweden.
  • 3 Cytiva, Björkgatan 30, 75 323 Uppsala, Sweden.
  • 4 Chemical and Pharmaceutical Safety, Research Institute of Sweden (RISE), Forskargatan 18, 15 136 Södertälje, Sweden.
  • 5 IVL Swedish Environmental Research Institute, 10 031 Stockholm, Sweden.
  • DOI: 10.1016/j.crtox.2025.100242 PMID: 40519565

    摘要 中英对照阅读

    Effective chemical hazard labelling systems are essential for safeguarding human health and the environment as a result of widespread chemical use, and machine-learning models can be used to predict hazard labels efficiently and reduce the use of animal tests. This investigation shows the utility of N-grams and other fingerprint featurization procedures for predicting classification, labelling and packaging (CLP). Regulation H-statements, particularly in a... ...点击完成人机验证后继续浏览

    有效的化学品危害标识系统对于保障人类健康和环境免受广泛使用化学品的影响至关重要。机器学习模型可以用来高效预测危害标签,减少动物实验的使用。这项研究展示了N-gram和其他指纹特征化方法在预测分类、标记和包装(CLP)法规H声明方面的实用性,特别是在集成(共识)设置中尤为如此。通过类别进行共识建模或使用符合性预测中位p值似乎特别有利,以便同时获得高符合性预测有效性和效率以及良好的平衡准确性、敏感性和特异性。利用N-gram可以处理SMILES字符串中的所有符号,包括与金属和盐类相关的那些符号,这些可能对化合物表现出实验确定的毒性至关重要。本研究开发的模型是获取化学品危害分类H声明的有效工具,可用于化学品危害评估、读取跨域以及风险管理。

    关键词: CLP法规;符合性预测;共识建模;H声明;分子指纹;N-gram;随机森林。

    © 2025 The Authors.

    翻译效果不满意? 用Ai改进或 寻求AI助手帮助 ,对摘要进行重点提炼
    Copyright © Current research in toxicology. 中文内容为AI机器翻译,仅供参考!

    相关内容

    期刊名:Current research in toxicology

    缩写:

    ISSN:2666-027X

    e-ISSN:2666-027X

    IF/分区:3.0/Q2

    文章目录 更多期刊信息

    全文链接
    引文链接
    复制
    已复制!
    推荐内容
    Prediction of the classification, labelling and packaging regulation H-statements with confidence using conformal prediction with N-grams and molecular fingerprints