Basak Subhash C, Mills Denise, Hawkins Douglas M, Kraker Jessica J
University of Minnesota Duluth, Natural Resources Research Institute, Center for Water and Environment, 5013 Miller Trunk Hwy, Duluth, MN 55811, USA.
Chem Biodivers. 2009 Apr;6(4):487-502. doi: 10.1002/cbdv.200800111.
Blood: air partition coefficient (BApc) is important in assessing toxicokinetics of chemicals. Since very few experimental data are available, quantitative structure-activity relationship (QSAR) models based on calculated molecular descriptors can be useful in estimating BApc. Since all descriptors used in the analysis are computed strictly from structure, they can be applied to any chemical, real or hypothetical. In this article, we report models for BApc estimation using four methods, including stepwise ordinary least-squares regression, which is commonly used in QSAR studies but often results in an inflated 'naïve' q2, over-representing the predictive ability of the model. The models developed using proper statistical techniques had q2 values of 0.825 and 0.841, and may be used to reliably predict BApc values for new compounds that are structurally similar to those upon which the models are based. The models developed using improper techniques had associated q2 values, as computed using naïve methods, of 0.920 and 0.934, severely overstating their actual quality.
空气分配系数（BApc）在评估化学物质的毒代动力学方面很重要。由于可获得的实验数据非常少，基于计算得到的分子描述符的定量构效关系（QSAR）模型可用于估计BApc。由于分析中使用的所有描述符都严格根据结构计算得出，因此它们可应用于任何真实或假设的化学物质。在本文中，我们报告了使用四种方法估计BApc的模型，包括逐步普通最小二乘法回归，该方法常用于QSAR研究，但常常导致“朴素”的q2值虚高，高估了模型的预测能力。使用适当统计技术开发的模型的q2值分别为0.825和0.841，可用于可靠地预测与模型所基于的化合物结构相似的新化合物的BApc值。使用不当技术开发的模型，按照朴素方法计算，其相关q2值分别为0.920和0.934，严重高估了它们的实际质量。
