Background

Ligand-observed 19F NMR detection is an efficient method for screening libraries of fluorinated molecules in fragment-based drug design campaigns. Screening fluorinated molecules in large mixtures makes 19F NMR a high-throughput method. Typically, these mixtures are generated from pools of well-characterized fragments. By predicting 19F NMR chemical shift, mixtures could be generated for arbitrary fluorinated molecules facilitating for example focused screens.

Methods

In a previous publication, we introduced a method to predict 19F NMR chemical shift using rooted fluorine fingerprints and machine learning (ML) methods. Having observed that the quality of the prediction depends on similarity to the training set, we here propose to assist the prediction with quantum mechanics (QM) based methods in cases where compounds are not well covered by a training set.

Results

Beyond similarity, the performance of ML methods could be associated with individual features in compounds. A combination of both could be used as a procedure to split input data sets into those that could be predicted by ML and those that required QM processing. We could show on a proprietary fluorinated fragment library, known as LEF (Local Environment of Fluorine), and a public Enamine data set of 19F NMR chemical shifts that ML and QM methods could synergize to outperform either method individually. Models built on Enamine data, as well as model building and QM workflow tools, can be found at https://github.com/PatrickPenner/lefshift and https://github.com/PatrickPenner/lefqm.

中文翻译：

---

QM 辅助 ML 进行 19F NMR 化学位移预测

背景

配体观察 19F NMR 检测是在基于片段的药物设计活动中筛选氟化分子文库的有效方法。筛选大型混合物中的氟化分子使 19F NMR 成为一种高通量方法。通常，这些混合物是从充分表征的片段池中生成的。通过预测 19F NMR 化学位移，可以生成任意氟化分子的混合物，从而促进聚焦屏幕等。

方法

在之前的出版物中，我们介绍了一种使用根氟指纹和机器学习 (ML) 方法来预测 19F NMR 化学位移的方法。观察到预测的质量取决于与训练集的相似性，我们在此建议在训练集未很好地覆盖化合物的情况下使用基于量子力学（QM）的方法来辅助预测。

结果

除了相似性之外，机器学习方法的性能还可能与化合物的个体特征相关。两者的组合可以用作将输入数据集拆分为可以通过 ML 预测的数据集和需要 QM 处理的数据集的程序。我们可以在专有的氟化片段库（称为 LEF（氟局部环境））和 19F NMR 化学位移的公共 Enamine 数据集上展示，ML 和 QM 方法可以协同作用，从而优于单独的任何一种方法。基于 Enamine 数据构建的模型以及模型构建和 QM 工作流程工具可以在 https://github.com/PatrickPenner/lefshift 和 https://github.com/PatrickPenner/lefqm 中找到。