Department of Chemistry, Umeå University, SE-901 87 Umeå, Sweden.
Talanta. 2011 Oct 15;85(5):2686-94. doi: 10.1016/j.talanta.2011.08.060. Epub 2011 Sep 1.
A set of 69 drug-like compounds with corneal permeability was studied using quantitative and qualitative modeling techniques. Multiple linear regression (MLR) and multilayer perceptron neural network (MLP-NN) were used to develop quantitative relationships between the corneal permeability and seven molecular descriptors selected by stepwise MLR and sensitivity analysis methods. In order to evaluate the models, a leave many out cross-validation test was performed, which produced the statistic Q(2)=0.584 and SPRESS=0.378 for MLR and Q(2)=0.774 and SPRESS=0.087 for MLP-NN. The obtained results revealed the suitability of MLP-NN for the prediction of corneal permeability. The contribution of each descriptor to MLP-NN model was evaluated. It indicated the importance of the molecular volume and weight. The pattern recognition methods principal component analysis (PCA) and hierarchical clustering analysis (HCA) have been employed in order to investigate the possible qualitative relationships between the molecular descriptors and the corneal permeability. The PCA and HCA results showed that, the data set contains two groups. Then, the same descriptors used in quantitative modeling were considered as inputs of counter propagation neural network (CPNN) to classify the compounds into low permeable (LP) and very low permeable (VLP) categories in supervised manner. The overall classification non error rate was 95.7% and 95.4% for the training and prediction test sets, respectively. The results revealed the ability of CPNN to correctly recognize the compounds belonging to the categories. The proposed models can be successfully used to predict the corneal permeability values and to classify the compounds into LP and VLP ones.
一套 69 种具有角膜通透性的类药化合物，采用定量和定性建模技术进行了研究。多元线性回归（MLR）和多层感知器神经网络（MLP-NN）用于建立角膜通透性与通过逐步 MLR 和敏感性分析方法选择的七个分子描述符之间的定量关系。为了评估模型，进行了许多外部交叉验证测试，结果分别为 MLR 的统计量 Q(2)=0.584 和 SPRESS=0.378，以及 MLP-NN 的 Q(2)=0.774 和 SPRESS=0.087。获得的结果表明 MLP-NN 适合于预测角膜通透性。评估了每个描述符对 MLP-NN 模型的贡献。结果表明分子体积和重量的重要性。已经采用了模式识别方法主成分分析（PCA）和层次聚类分析（HCA），以研究分子描述符与角膜通透性之间可能存在的定性关系。PCA 和 HCA 的结果表明，数据集包含两个组。然后，将定量建模中使用的相同描述符视为反向传播神经网络（CPNN）的输入，以有监督的方式将化合物分类为低渗透性（LP）和超低渗透性（VLP）类别。训练集和预测集的总体分类无错误率分别为 95.7%和 95.4%。结果表明 CPNN 能够正确识别属于这些类别的化合物。所提出的模型可成功用于预测角膜通透性值，并将化合物分类为 LP 和 VLP 类。
