University of Strasbourg, 1 rue Blaise Pascal, 67000, Strasbourg, France.
Kazan Federal University, 18 Kremlyovskaya Str., Kazan, Russian Federation, 420008.
J Comput Aided Mol Des. 2018 Mar;32(3):401-414. doi: 10.1007/s10822-018-0101-6. Epub 2018 Jan 29.
We report the first direct QSPR modeling of equilibrium constants of tautomeric transformations (logK ) in different solvents and at different temperatures, which do not require intermediate assessment of acidity (basicity) constants for all tautomeric forms. The key step of the modeling consisted in the merging of two tautomers in one sole molecular graph ("condensed reaction graph") which enables to compute molecular descriptors characterizing entire equilibrium. The support vector regression method was used to build the models. The training set consisted of 785 transformations belonging to 11 types of tautomeric reactions with equilibrium constants measured in different solvents and at different temperatures. The models obtained perform well both in cross-validation (Q = 0.81 RMSE = 0.7 logK units) and on two external test sets. Benchmarking studies demonstrate that our models outperform results obtained with DFT B3LYP/6-311 ++ G(d,p) and ChemAxon Tautomerizer applicable only in water at room temperature.
我们报告了第一个直接的 QSPR 模型,用于预测不同溶剂和不同温度下的互变异构平衡常数(logK),而无需对所有互变异构形式的酸度(碱度)常数进行中间评估。建模的关键步骤包括将两种互变异构体合并为一个单一的分子图(“凝聚反应图”),这使得能够计算出表征整个平衡的分子描述符。支持向量回归方法用于构建模型。训练集由 785 种互变异构反应组成,属于 11 种互变异构反应类型,其平衡常数在不同溶剂和不同温度下测量。所得到的模型在交叉验证(Q=0.81 RMSE=0.7 logK 单位)和两个外部测试集上都表现良好。基准研究表明,我们的模型优于仅在室温下适用于水的 DFT B3LYP/6-311++G(d,p)和 ChemAxon Tautomerizer 获得的结果。