a State Key Laboratory of Chemical Resource Engineering, Department of Pharmaceutical Engineering , Beijing University of Chemical Technology , P. R . China.
SAR QSAR Environ Res. 2018 Oct;29(10):755-784. doi: 10.1080/1062936X.2018.1513952.
Cyclooxygenase-1 (COX-1) is one isoform of COX, and it is a main target of nonsteroidal anti-inflammatory drugs (NSAIDs). It is important to develop efficient and selective COX-1 inhibitors. In this work, 12 classification models for 1530 cyclooxygenase-1 (COX-1) inhibitors were built by support vector machine (SVM), decision tree (DT) and random forest (RF) methods. The best classification model (model 1A) was built by SVM with MACCS fingerprints. The classification accuracies for the training and test sets were 99.67% and 97.39%, respectively. The Matthews correlation coefficient (MCC) of the test set was 0.94. We also divided the 1530 COX-1 inhibitors into nine subsets according to their different scaffolds using Kohonen's self-organizing map (SOM). In addition, six quantitative structure-activity relationship (QSAR) models for 181 COX-1 inhibitors whose IC were measured by enzyme immunoassay were built by multiple linear regression (MLR) and SVM. The best QSAR model (model 5A) was built by SVM with CORINA Symphony descriptors. The correlation coefficients of the training and test sets are 0.93 and 0.84, respectively. The models built in this study can be obtained from the authors.
环氧化酶-1（COX-1）是 COX 的一种同工酶，是非甾体抗炎药（NSAIDs）的主要作用靶点。开发高效、选择性的 COX-1 抑制剂非常重要。在这项工作中，通过支持向量机（SVM）、决策树（DT）和随机森林（RF）方法构建了 12 个用于 1530 种环氧化酶-1（COX-1）抑制剂的分类模型。使用 MACCS 指纹构建了最佳分类模型（模型 1A）。训练集和测试集的分类准确率分别为 99.67%和 97.39%。测试集的马修斯相关系数（MCC）为 0.94。我们还根据抑制剂的不同骨架，使用 Kohonen 的自组织映射（SOM）将 1530 种 COX-1 抑制剂分为九个子集。此外，通过多元线性回归（MLR）和 SVM 构建了 181 种 COX-1 抑制剂的 6 个定量构效关系（QSAR）模型，这些抑制剂的 IC 由酶免疫测定法测定。使用 CORINA Symphony 描述符构建的最佳 QSAR 模型（模型 5A）。训练集和测试集的相关系数分别为 0.93 和 0.84。本研究中构建的模型可以从作者处获得。
