二维二项式 LPA3 受体拮抗 QSAR 建模。
2D binary QSAR modeling of LPA3 receptor antagonism.
机构信息
Department of Chemistry and Computational Research on Materials Institute, The University of Memphis, Memphis, TN 38152, United States.
出版信息
J Mol Graph Model. 2010 Jun;28(8):828-33. doi: 10.1016/j.jmgm.2010.03.002. Epub 2010 Mar 7.
A structurally diverse dataset of 119 compounds was used to develop and validate a 2D binary QSAR model for the LPA(3) receptor. The binary QSAR model was generated using an activity threshold of greater than 15% inhibition at 10 microM. The overall accuracy of the model on the training set was 82%. It had accuracies of 55% for active and 91% for inactive compounds, respectively. The model was validated using an external test set of 10 compounds. The accuracy on the external test set was 60% overall, identifying three out of seven actives and all three inactive compounds. This model was combined with similarity searching to rapidly screen libraries and select 14 candidate LPA(3) antagonists. Experimental assays confirmed 13 of these (93%) met the 15% inhibition threshold defining actives. The successful application of the model to select candidates for screening demonstrates the power of this binary QSAR model to prioritize compound selection for experimental consideration.
使用包含 119 个化合物的结构多样化数据集，开发并验证了一种用于 LPA(3) 受体的 2D 二进制 QSAR 模型。该二进制 QSAR 模型的生成使用了 10μM 时大于 15%抑制率的活性阈值。该模型在训练集上的整体准确性为 82%。活性化合物的准确性为 55%，非活性化合物的准确性为 91%。该模型通过包含 10 个化合物的外部测试集进行了验证。该模型在外部测试集上的总准确性为 60%，正确识别出了 7 个活性化合物中的 3 个和所有 3 个非活性化合物。该模型与相似性搜索相结合，快速筛选库并选择了 14 种候选 LPA(3) 拮抗剂。实验测定证实，其中 13 种（93%）符合定义活性化合物的 15%抑制率阈值。该模型成功应用于候选化合物的筛选，证明了这种二进制 QSAR 模型在化合物选择方面的强大功能，可优先考虑进行实验研究。
Zotero 插件