Jahn Andreas, Hinselmann Georg, Fechner Nikolas, Henneges Carsten, Zell Andreas
Center for Bioinformatics, University of Tübingen, Sand 1, 72076 Tübingen, Germany phone/fax:+49 7071 29 77175/+49 7071 29 5091.
Mol Inform. 2010 May 17;29(5):441-55. doi: 10.1002/minf.201000036.
We present a new probabilistic encoding of the conformational space of a molecule that allows for the integration into common similarity calculations. The method uses distance profiles of flexible atom-pairs and computes generative models that describe the distance distribution in the conformational space. The generative models permit the use of probabilistic kernel functions and, therefore, our approach can be used to extend existing 3D molecular kernel functions, as applied in support vector machines, to build QSAR models. The resulting kernels are valid 4D kernel functions and reduce the dependency of the model quality on suitable conformations of the molecules. We showed in several experiments the robust performance of the 4D kernel function, which was extended by our approach, in comparison to the original 3D-based kernel function. The new method compares the conformational space of two molecules within one kernel evaluation. Hence, the number of kernel evaluations is significantly reduced in comparison to common kernel-based conformational space averaging techniques. Additionally, the performance gain of the extended model correlates with the flexibility of the data set and enables an a priori estimation of the model improvement.
我们提出了一种分子构象空间的新概率编码方法，该方法能够集成到常见的相似性计算中。此方法使用柔性原子对的距离分布，并计算描述构象空间中距离分布的生成模型。这些生成模型允许使用概率核函数，因此，我们的方法可用于扩展现有的三维分子核函数（如支持向量机中应用的），以构建定量构效关系（QSAR）模型。所得的核是有效的四维核函数，降低了模型质量对分子合适构象的依赖性。我们在多个实验中表明，与原始的基于三维的核函数相比，通过我们的方法扩展的四维核函数具有稳健的性能。新方法在一次核评估中比较两个分子的构象空间。因此，与基于核的常见构象空间平均技术相比，核评估的次数显著减少。此外，扩展模型的性能提升与数据集的灵活性相关，并能够对模型改进进行先验估计。
