University of Science and Technology of China, Hefei, Anhui 230027, China.
Microsoft Research, Beijing 100080, China.
Bioinformatics. 2022 Feb 7;38(5):1244-1251. doi: 10.1093/bioinformatics/btab817.
Molecule generation, which is to generate new molecules, is an important problem in bioinformatics. Typical tasks include generating molecules with given properties, molecular property improvement (i.e. improving specific properties of an input molecule), retrosynthesis (i.e. predicting the molecules that can be used to synthesize a target molecule), etc. Recently, deep-learning-based methods received more attention for molecule generation. The labeled data of bioinformatics is usually costly to obtain, but there are millions of unlabeled molecules. Inspired by the success of sequence generation in natural language processing with unlabeled data, we would like to explore an effective way of using unlabeled molecules for molecule generation.
We propose a new method, back translation for molecule generation, which is a simple yet effective semisupervised method. Let X be the source domain, which is the collection of properties, the molecules to be optimized, etc. Let Y be the target domain which is the collection of molecules. In particular, given a main task which is about to learn a mapping from the source domain X to the target domain Y, we first train a reversed model g for the Y to X mapping. After that, we use g to back translate the unlabeled data in Y to X and obtain more synthetic data. Finally, we combine the synthetic data with the labeled data and train a model for the main task. We conduct experiments on molecular property improvement and retrosynthesis, and we achieve state-of-the-art results on four molecule generation tasks and one retrosynthesis benchmark, USPTO-50k.
Our code and data are available at https://github.com/fyabc/BT4MolGen.
Supplementary data are available at Bioinformatics online.
分子生成，即生成新的分子，是生物信息学中的一个重要问题。典型的任务包括生成具有给定性质的分子、分子性质改进（即改进输入分子的特定性质）、逆合成（即预测可用于合成目标分子的分子）等。最近，基于深度学习的方法在分子生成方面受到了更多的关注。生物信息学的标记数据通常获取成本较高，但有上百万个未标记的分子。受自然语言处理中使用未标记数据进行序列生成成功的启发，我们希望探索一种有效利用未标记分子进行分子生成的方法。
我们提出了一种新的方法，即用于分子生成的反向翻译，这是一种简单而有效的半监督方法。令 X 为源域，即属性、待优化的分子等的集合。令 Y 为目标域，即分子的集合。特别地，给定一个主要任务，即学习从源域 X 到目标域 Y 的映射，我们首先为 Y 到 X 的映射训练一个反向模型 g。之后，我们使用 g 将未标记的数据从 Y 反向翻译到 X 并获得更多的合成数据。最后，我们将合成数据与标记数据结合起来，并为主要任务训练一个模型。我们在分子性质改进和逆合成方面进行了实验，在四个分子生成任务和一个逆合成基准 USPTO-50k 上取得了最先进的结果。
我们的代码和数据可在 https://github.com/fyabc/BT4MolGen 上获得。
补充数据可在 Bioinformatics 在线获得。
