Prediction of Organic Reaction Outcomes Using Machine Learning.
Prediction of Organic Reaction Outcomes Using Machine Learning.
复制标题
DOI：
10.1021/acscentsci.7b00064
复制
发表时间：
2017-05-24
影响因子：
18.2
通讯作者：
Jensen KF
中科院分区：
文献类型：
--
作者：
Coley CW;Barzilay R;Jaakkola TS;Green WH;Jensen KF
计算机辅助合成设计已经存在了40多年，但反合成规划软件一直在努力实现广泛采用。开发高质量途径建议的一个关键挑战是，尽管最初看起来可行，但所提出的反应步骤在实验室中尝试时往往失败。任何合成程序成功的真正衡量标准是预测的结果是否与实验观察到的结果相符。我们报告了一个预测反应结果的模型框架，该框架结合了传统的反应模板使用和神经网络提供的模式识别的灵活性。使用来自授权的美国专利的15,000 000个实验反应记录，训练模型通过对自生成的候选列表进行排序来选择主要（记录的）产品，其中一个候选列表已知是主要产品。候选反应使用独特的基于编辑的表示来表示，强调从反应物到产物的基本转换，而不是组成分子的整体结构。在5倍交叉验证中，训练好的模型将主要产品排序为1的案例占71.8%，排序≤3的案例占86.7%，排序≤5的案例占90.8%。传统反应模板和机器学习的结合可以使用专利文献中的开源数据在硅中预测有机反应产物。
Computer assistance in synthesis design has existed for over 40 years, yet retrosynthesis planning software has struggled to achieve widespread adoption. One critical challenge in developing high-quality pathway suggestions is that proposed reaction steps often fail when attempted in the laboratory, despite initially seeming viable. The true measure of success for any synthesis program is whether the predicted outcome matches what is observed experimentally. We report a model framework for anticipating reaction outcomes that combines the traditional use of reaction templates with the flexibility in pattern recognition afforded by neural networks. Using 15 000 experimental reaction records from granted United States patents, a model is trained to select the major (recorded) product by ranking a self-generated list of candidates where one candidate is known to be the major product. Candidate reactions are represented using a unique edit-based representation that emphasizes the fundamental transformation from reactants to products, rather than the constituent molecules’ overall structures. In a 5-fold cross-validation, the trained model assigns the major product rank 1 in 71.8% of cases, rank ≤3 in 86.7% of cases, and rank ≤5 in 90.8% of cases. A combination of traditional reaction templates and machine learning enables the prediction of organic reaction products in silico using open source data from the patent literature.