Department of Chemistry, Michigan State University, 578 S. Shaw Lane, East Lansing, Michigan 48824, United States.
J Chem Inf Model. 2021 Apr 26;61(4):1647-1656. doi: 10.1021/acs.jcim.0c01492. Epub 2021 Mar 29.
While accurately modeling the conformational ensemble is required for predicting properties of flexible molecules, the optimal method of obtaining the conformational ensemble appears as varied as their applications. Ensemble structures have been modeled by generation, refinement, and clustering of conformations with a sufficient number of samples. We present a conformational clustering algorithm intended to automate the conformational clustering step through the Louvain algorithm, which requires minimal hyperparameters and importantly no predefined number of clusters or threshold values. The conformational graphs produced by this method for -succinyl-l-homoserine, oxidized nicotinamide adenine dinucleotide, and 200 representative metabolites each preserved the geometric/energetic correlation expected for points on the potential energy surface. Clustering based on these graphs provides partitions informed by the potential energy surface. Automating conformational clustering in a workflow with AutoGraph may mitigate human biases introduced by guess and check over hyperparameter selection while allowing flexibility to the result by not imposing predefined criteria other than optimizing the model's loss function. Associated codes are available at https://github.com/TanemuraKiyoto/AutoGraph.
虽然准确地模拟构象系综对于预测柔性分子的性质是必需的，但获得构象系综的最佳方法似乎与其应用一样多种多样。通过足够数量的样本生成、精化和构象聚类来构建构象系综。我们提出了一种构象聚类算法，通过 Louvain 算法实现构象聚类步骤的自动化，该算法需要最小的超参数，并且重要的是不需要预定义的聚类数量或阈值。通过这种方法为 -succinyl-l-homoserine、氧化型烟酰胺腺嘌呤二核苷酸和 200 个代表性代谢物生成的构象图保留了在势能面上的点所预期的几何/能量相关性。基于这些图的聚类提供了由势能面提供的分区。在 AutoGraph 工作流中自动化构象聚类可以减轻在超参数选择中通过猜测和检查引入的人为偏见，同时通过不施加除优化模型的损失函数之外的预定义标准来保持结果的灵活性。相关代码可在 https://github.com/TanemuraKiyoto/AutoGraph 上获得。
