...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Environmental toxicology and chemistry >PARTIAL LEAST SQUARE AND K-NEAREST NEIGHBOR ALGORITHMS FOR IMPROVED 3D QUANTITATIVE SPECTRAL DATA-ACTIVITY RELATIONSHIP CONSENSUS MODELING OF ACUTE TOXICITY
【24h】

PARTIAL LEAST SQUARE AND K-NEAREST NEIGHBOR ALGORITHMS FOR IMPROVED 3D QUANTITATIVE SPECTRAL DATA-ACTIVITY RELATIONSHIP CONSENSUS MODELING OF ACUTE TOXICITY

机译：改进的3D定量光谱数据活性关系的局部最小二乘法和K近邻算法，对急性毒性的共识模型

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

A diverse set of 154 chemicals that included US Food and Drug Administration-regulated compounds tested for their aquatic toxicity in Daphnia magna were modeled by a 3-dimensional quantitative spectral data-activity relationship (3D-QSDAR). Two distinct algorithms, partial least squares (PLS) and Tanimoto similarity-based k-nearest neighbors (KNN), were used to process bin occupancy descriptor matrices obtained after tessellation of the 3D-QSDAR space into regularly sized bins. The performance of models utilizing bins ranging in size from 2 ppm × 2 ppm × 0.5 A to 20 ppm × 20 ppm × 2.5 A was explored. Rigorous quality-control criteria were imposed: 1) 100 randomized 20% hold-out test sets were generated and the average R_(test)~2 of the respective models was used as a measure of their performance, and 2) a Y-scrambling procedure was used to identify chance correlations. A consensus between the best-performing composite PLS model using 0.5 A × 14 ppm × 14 ppm bins and 10 latent variables (average R_(test)~2 = 0.770) and the best composite KNN model using 0.5 A × 8 ppm × 8 ppm and 2 neighbors (average R_(test)~2 = 0.801) offered an improvement of about 7.5% (R_(test consensus)~2 = 0.845). Projection of the most frequently occurring bins on the standard coordinate space indicated that the presence of a primary or secondary amino group-substituted aromatic systems-would result in an increased toxic effect in Daphnia. The presence of a second aromatic ring with highly electronegative substituents 5 A to 7 A apart from the first ring would lead to a further increase in toxicity.
机译：通过3维定量光谱数据-活性关系（3D-QSDAR）对包括154种化学物质在内的多种化学物质进行建模，这些化学物质包括受美国食品和药物管理局管制的对水蚤的水生毒性的化合物。两种截然不同的算法，即偏最小二乘（PLS）和基于Tanimoto基于相似度的k最近邻（KNN），用于将3D-QSDAR空间细分为规则大小的bin后获得的bin占用描述符矩阵。探索了利用尺寸范围从2 ppm×2 ppm×0.5 A到20 ppm×20 ppm×2.5 A的垃圾箱的模型的性能。施加严格的质量控制标准：1）生成100个随机的20％保留测试集，并将各个模型的平均R_（test）〜2用作其性能的度量，以及2）Y加扰该程序用于识别机会相关性。使用0.5 A×14 ppm×14 ppm仓位和10个潜变量（平均R_（test）〜2 = 0.770）的最佳复合PLS模型与使用0.5 A×8 ppm×8 ppm的最佳复合KNN模型之间的共识2个邻居（平均R_（test）〜2 = 0.801）提高了约7.5％（R_（测试共识）〜2 = 0.845）。在标准坐标空间上最常出现的垃圾箱的投影表明，伯或仲氨基取代的芳族系统的存在会导致水蚤的毒性增加。与第一环分开的具有高负电性取代基5 A至7 A的第二芳环的存在将导致毒性的进一步增加。

著录项

  • 来源
    《Environmental toxicology and chemistry》 |2014年第6期|1271-1282|共12页
  • 作者

    Iva B. Stoyanova-Slavova; Svetoslav H. Slavov; Bruce Pearce; Dan A. Buzatu; Richard D. Beger; Jon G. Wilkes;

  • 作者单位

    Division of Systems Biology, National Center for Toxicological Research, US Food and Drug Administration, Jefferson, Arizona;

    Division of Systems Biology, National Center for Toxicological Research, US Food and Drug Administration, Jefferson, Arizona;

    Division of Systems Biology, National Center for Toxicological Research, US Food and Drug Administration, Jefferson, Arizona;

    Division of Systems Biology, National Center for Toxicological Research, US Food and Drug Administration, Jefferson, Arizona;

    Division of Systems Biology, National Center for Toxicological Research, US Food and Drug Administration, Jefferson, Arizona;

    Division of Systems Biology, National Center for Toxicological Research, US Food and Drug Administration, Jefferson, Arizona;

  • 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

    Aquatic toxicology; Computational toxicology; Multivariate statistic; 3D quantitative spectral data-activity relationship (QSDAR); Consensus modeling;

    机译：水生毒理学;计算毒理学;多元统计;3D定量光谱数据-活性关系（QSDAR）;共识建模;

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