於 2018 年 Nature 期刊上發表，Waller、Segler et al. 與 Reaxys 團隊合作發展了一個深度學習的電腦演算法，針對類藥分子、天然產物，預測一系列的合成反應式、規劃逆合成藍圖，現在這個人工智慧工具已接收來自 Reaxys 資料庫一千五百萬條單步驟有機反應的訓練，能夠針對目標分子，產生逆合成樹狀路徑，追朔至商用可獲得的起始材料，此策略將在未來，顯著的精簡合成化學家面對逆合成分析的方法。

Waller and Segler et al. (Nature 2018, 555, 604–610) in collaboration with the Reaxys® team have developed a deep learning computer algorithm that produces blueprints for the sequences of reactions needed to create small organic molecules, such as drug-like compounds or natural products. Now, an artificial intelligence tool has been trained on more than 15 million unique single-step organic reactions from Reaxys®, which generates a retrosynthesis tree back to commercially available starting materials for a given target molecule. This approach has the potential to significantly streamline the way synthetic chemists approach retrosynthetic analysis in the future.