Institute of Bioorganic Chemistry and Petrochemistry, National Academy of Sciences of Ukraine, Murmanska 1, Kyiv 9402660, Ukraine.
J Mol Graph Model. 2012 Feb;32:32-8. doi: 10.1016/j.jmgm.2011.10.001. Epub 2011 Oct 14.
A series of diverse organic compounds, phosphodiesterase type 4 (PDE-4) inhibitors, have been modeled using a QSAR-based approach. 48 QSAR models were compared by following the same procedure with different combinations of descriptors and machine learning methods. QSAR methodologies used random forests and associative neural networks. The predictive ability of the models was tested through leave-one-out cross-validation, giving a Q² = 0.66-0.78 for regression models and total accuracies Ac=0.85-0.91 for classification models. Predictions for the external evaluation sets obtained accuracies in the range of 0.82-0.88 (for active/inactive classifications) and Q² = 0.62-0.76 for regressions. The method showed itself to be a potential tool for estimation of IC₅₀ of new drug-like candidates at early stages of drug development.
采用基于 QSAR 的方法对一系列不同的有机化合物，即磷酸二酯酶 4 型 (PDE-4) 抑制剂进行了建模。通过采用不同的描述符和机器学习方法组合，按照相同的程序对 48 个 QSAR 模型进行了比较。QSAR 方法采用随机森林和关联神经网络。通过留一法交叉验证测试模型的预测能力，回归模型的 Q²值为 0.66-0.78，分类模型的总准确度 Ac 为 0.85-0.91。通过外部评估集的预测，得到的准确度范围为 0.82-0.88（用于活性/非活性分类），回归的 Q²值为 0.62-0.76。该方法可作为药物开发早期估计新型类药性候选物 IC₅₀的潜在工具。
