Accurate Solubility Prediction with Error Bars for Electrolytes: A Machine Learning Approach
Accurate Solubility Prediction with Error Bars for Electrolytes: A Machine Learning Approach
复制标题
DOI：
10.1021/ci600205g
复制
发表时间：
2007-01
影响因子：
5.6
通讯作者：
A. Schwaighofer;T. Schroeter;S. Mika;Julian Laub;A. T. Laak;D. Sülzle;U. Ganzer;N. Heinrich;K. Müller
中科院分区：
文献类型：
--
作者：
A. Schwaighofer;T. Schroeter;S. Mika;Julian Laub;A. T. Laak;D. Sülzle;U. Ganzer;N. Heinrich;K. Müller
在药物设计和发现以及化学研究的许多其他领域中，需要准确的用于预测水的溶解度的电子模型。我们提出了一个基于测量数据的水的溶解度的统计模型，使用了一个高斯过程非线性回归模型(GPsol)。我们将我们的结果与14项科学研究和6项商业工具的结果进行了比较。这表明，所开发的模型在预测电解液的溶解度方面取得了比现有商业工具高得多的精度。除了高精度，提出的机器学习模型还为每个单独的预测提供了误差条。
Accurate in silico models for predicting aqueous solubility are needed in drug design and discovery and many other areas of chemical research. We present a statistical modeling of aqueous solubility based on measured data, using a Gaussian Process nonlinear regression model (GPsol). We compare our results with those of 14 scientific studies and 6 commercial tools. This shows that the developed model achieves much higher accuracy than available commercial tools for the prediction of solubility of electrolytes. On top of the high accuracy, the proposed machine learning model also provides error bars for each individual prediction.