Linking the Neural Machine Translation and the Prediction of Organic Chemistry Reactions
Juno Nam Jurae Kim Seoul Science High School, Seoul 110-530, Korea
Abstract
Finding the main product of a chemical reaction is one of the important problems of organic chemistry. This paper describes a method of applying a neural machine translation model to the prediction of organic chemical reactions. In order to translate ‘reactants and reagents’ to ‘products’, a gated recurrent unit based sequence–to–sequence model and a parser to generate input tokens for model from reaction SMILES strings were built. Training sets are composed of reactions from the patent databases, and reactions manually generated applying the elementary reactions in an organic chemistry textbook of Wade. The trained models were tested by examples and problems in the textbook. The prediction process does not need manual encoding of rules (e.g., SMARTS transformations) to predict products, hence it only needs sufficient training reaction sets to learn new types of reactions.
中文速览
预测有机化学反应的主要产物一直是化学信息学的核心难题，传统方法要么依赖人工编写规则（如SMARTS转换），要么需要高昂的量子力学计算成本。研究者把这个问题类比成"语言翻译"——将反应物和试剂的SMILES字符串"翻译"成产物的SMILES字符串，并构建了一个基于门控循环单元（GRU）的序列到序列（sequence-to-sequence）神经机器翻译模型，训练数据来自专利反应数据库以及按有机化学教材反应模板自动生成的反应集。在用教材例题和习题进行测试时，同时使用两类训练集的模型（real+gen）在正确率和Tanimoto相似度上均优于仅用生成数据训练的模型，甚至能在一定程度上预测训练集中未覆盖的反应类型（如芳香族反应）。这项工作的意义在于完全摆脱了人工编写转化规则的束缚，只需积累足够的反应数据即可扩展到新反应类型，为构建更灵活、可扩展的自动化有机合成规划工具提供了新思路。
原文 arXiv:1612.09529;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1612.09529v1