a Department of Chemical Engineering , Amirkabir University of Technology (Tehran Polytechnic) , Tehran , Iran .
SAR QSAR Environ Res. 2014;25(1):35-50. doi: 10.1080/1062936X.2013.826275. Epub 2013 Oct 3.
In this work, quantitative structure-property relationship (QSPR) models were developed to estimate skin permeability based on theoretically derived molecular descriptors and a diverse set of experimental data. The newly developed method combining modified particle swarm optimization (MPSO) and multiple linear regression (MLR) was used to select important descriptors and develop the linear model using a training set of 225 compounds. The adaptive neuro-fuzzy inference system (ANFIS) was used as an efficient nonlinear method to correlate the selected descriptors with experimental skin permeability data (log Kp). The linear and nonlinear models were assessed by internal and external validation. The obtained models with three descriptors show good predictive ability for the test set, with coefficients of determination for the MPSO-MLR and ANFIS models equal to 0.874 and 0.890, respectively. The QSPR study suggests that hydrophobicity (encoded as log P) is the most important factor in transdermal penetration.
在这项工作中，我们开发了定量构效关系 (QSPR) 模型，以便根据理论推导的分子描述符和大量实验数据来估算皮肤渗透性。我们使用了一种新的方法，将改进的粒子群优化算法 (MPSO) 和多元线性回归 (MLR) 相结合，使用 225 种化合物的训练集选择重要的描述符并建立线性模型。自适应神经模糊推理系统 (ANFIS) 被用作一种有效的非线性方法，将所选描述符与实验皮肤渗透性数据 (log Kp) 相关联。线性和非线性模型均通过内部和外部验证进行了评估。具有三个描述符的模型对测试集具有良好的预测能力，MPSO-MLR 和 ANFIS 模型的确定系数分别为 0.874 和 0.890。QSPR 研究表明，疏水性（编码为 log P）是透皮渗透的最重要因素。
