Retrosynthesis is at the core of organic chemistry. Recently, the rapid growth of artificial intelligence (AI) has spurred a variety of novel machine learning approaches for data-driven synthesis planning. These methods learn complex patterns from reaction databases in order to predict, for a given product, sets of reactants that can be used to synthesise that product. However, their performance as measured by the top-N accuracy in matching published reaction precedents still leaves room for improvement. This work aims to enhance these models by learning to re-rank their reactant predictions. Specifically, we design and train an energy-based model to re-rank, for each product, the published reaction as the top suggestion and the remaining reactant predictions as lower-ranked. We show that re-ranking can improve one-step models significantly using the standard USPTO-50k benchmark dataset, such as RetroSim, a similarity-based method, from 35.7 to 51.8% top-1 accuracy and NeuralSym, a deep learning method, from 45.7 to 51.3%, and also that re-ranking the union of two models’ suggestions can lead to better performance than either alone. However, the state-of-the-art top-1 accuracy is not improved by this method.

中文翻译：

---

通过重新排序提高模型的一步逆合成性能

逆合成是有机化学的核心。最近，人工智能 (AI) 的快速发展激发了各种用于数据驱动合成规划的新型机器学习方法。这些方法从反应数据库中学习复杂的模式，以便针对给定的产品预测可用于合成该产品的反应物组。然而，通过匹配已发表反应先例的前 N ​​个准确度来衡量，它们的性能仍有改进的空间。这项工作旨在通过学习重新排列它们的反应物预测来增强这些模型。具体来说，我们设计并训练了一个基于能量的模型，为每种产品重新排列已发表的反应作为最高建议，将剩余的反应物预测重新排列为较低等级。我们表明，使用标准 USPTO-50k 基准数据集（例如 RetroSim，一种基于相似性的方法，top-1 准确率从 35.7% 到 51.8% 和深度学习方法 NeuralSym，从45.7% 到 51.3%，而且重新排列两个模型的建议的联合可以导致比单独一个更好的性能。但是，这种方法并没有提高最先进的 top-1 精度。