...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Environmental Science & Technology >Identification of Potential PBT/POP-Like Chemicals by a Deep Learning Approach Based on 2D Structural Features
【24h】

Identification of Potential PBT/POP-Like Chemicals by a Deep Learning Approach Based on 2D Structural Features

机译：通过基于2D结构特征的深度学习方法识别潜在的PBT / POP样化学品

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Identifying potential persistent organic pollutants (POPs) and persistent, bio accumulative, and toxic (PBT) substances from industrial chemical inventories are essential for chemical risk assessment, management, and pollution control. Inspired by the connections between chemical structures and their properties, a deep convolutional neural network (DCNN) model was developed to screen potential PBT/POP-like chemicals. For each chemical, a two-dimensional molecular descriptor representation matrix based on 2424 molecular descriptors was used as the model input. The DCNN model was trained via a supervised learning algorithm with 1306 PBT/POP-like chemicals and 9990 chemicals currently known as non-POPs/PBTs. The model can achieve an average prediction accuracy of 95.3 ± 0.6% and an F-measurement of 79.3 ± 2.5% for PBT/POP-like chemicals (positive samples only) on external data sets. The DCNN model was further evaluated with 52 experimentally determined PBT chemicals in the REACH PBT assessment list and correctly recognized 47 chemicals as PBTon-PBT chemicals. The DCNN model yielded a total of 4011 suspected PBT/POP like chemicals from 58 079 chemicals merged from five published industrial chemical lists. The proportions of PBT/POP-like substances in the chemical inventories were 6.9-7.8%, higher than a previous estimate of 3-5%. Although additional PBT/POP chemicals were identified, no new family of PBT/POP-like chemicals was observed.
机译：鉴定潜在的持续有机污染物（POPs）和持续性，生物累积和来自工业化学库存的生物累积和有毒（PBT）物质对于化学风险评估，管理和污染控制至关重要。灵感来自化学结构与其性质之间的联系，开发了深度卷积神经网络（DCNN）模型，以筛分潜在的PBT / POP样化学品。对于每个化学品，使用基于2424个分子描述符的二维分子描述符表示矩阵作为模型输入。 DCNN模型通过监督的学习算法培训，具有1306个PBT / POP样化学物质和9990种Chemicals，目前称为非POPS / PBT。该模型可以达到95.3±0.6％的平均预测精度，并且F-Meastion为PBT / POP样化学品（仅限阳性样品）在外部数据集上的59.3±2.5％。进一步评估DCNN模型，在REACH PBT评估清单中进行了52种实验确定的PBT化学品，并将47种化学品正确认可为PBT /非PBT化学品。 DCNN模型总共产生4011个疑似PBT /流行物，如来自58 079种化学品的化学品，从五个出版的工业化学品清单合并。化学库存中PBT / POP样物质的比例为6.9-7.8％，高于先前估计为3-5％。虽然鉴定了额外的PBT / POP化学品，但没有观察到任何新的PBT / POP样化学品。

著录项

  • 来源
    《Environmental Science & Technology》 |2020年第13期|8221-8231|共11页
  • 作者

    Xiangfei Sun; Xianming Zhang; Derek C.G. Muir; Eddy Y. Zeng;

  • 作者单位

    Guangdong Key Laboratory of Environmental Pollution and Health School of Environment Jinan University Guangzhou 511443 China;

    Department of Physical and Environmental Sciences University of Toronto Toronto Ontario Canada MIC 1A4 Environment and Climate Change Canada Aquatic Contaminants Research Division Burlington Ontario Canada L7S 1A;

    Guangdong Key Laboratory of Environmental Pollution and Health School of Environment Jinan University Guangzhou 511443 China Environment and Climate Change Canada Aquatic Contaminants Research Division Burlington Ontario Canada L7S 1A;

    Guangdong Key Laboratory of Environmental Pollution and Health School of Environment and Research Center of Low Carbon Economy for Guangzhou Region Jinan University Guangzhou 511443 China;

  • 收录信息 美国《科学引文索引》(SCI);美国《工程索引》(EI);美国《生物学医学文摘》(MEDLINE);美国《化学文摘》(CA);
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号