Bidirectional Molecule Generation with Recurrent Neural Networks
Bidirectional Molecule Generation with Recurrent Neural Networks
复制标题
DOI：
10.1021/acs.jcim.9b00943
复制
发表时间：
2020-03-23
影响因子：
5.6
通讯作者：
Schneider, Gisbert
中科院分区：
文献类型：
--
作者：
Grisoni, Francesca;Moret, Michael;Schneider, Gisbert
递归神经网络（RNN）能够使用简化的分子输入线输入系统（SMILES）化学结构的字符串表示来生成从头分子设计。基于RNN的结构生成通常是单向执行的，从左到右增长SMILES字符串。然而，一个小分子并没有自然的开始或结束，而SMILES字符串本质上是分子图的非单义表示。这些属性激发了双向结构生成。在这里，双向生成RNN的SMILES为基础的分子设计。为此，实现了两种已建立的双向方法，并介绍了一种新的SMILES字符串生成和数据扩充方法-双向交替学习分子设计（BIMODAL）。这三种双向策略与用于SMILES字符串生成的单向前向RNN方法进行了比较，包括（i）新奇，（ii）支架多样性和（iii）计算机生成分子的化学生物学相关性。结果积极倡导基于SMILES的分子从头设计的双向策略，对于测试条件下的大多数标准，BIMODAL显示出上级结果优于单向前向RNN。方法和预训练模型的代码可以在URL https://github.com/ETHmodlab/BIMODAL上找到。
Recurrent neural networks (RNNs) are able to generate de novo molecular designs using simplified molecular input line entry systems (SMILES) string representations of the chemical structure. RNN-based structure generation is usually performed unidirectionally, by growing SMILES strings from left to right. However, there is no natural start or end of a small molecule, and SMILES strings are intrinsically nonunivocal representations of molecular graphs. These properties motivate bidirectional structure generation. Here, bidirectional generative RNNs for SMILES-based molecule design are introduced. To this end, two established bidirectional methods were implemented, and a new method for SMILES string generation and data augmentation is introduced-the bidirectional molecule design by alternate learning (BIMODAL). These three bidirectional strategies were compared to the unidirectional forward RNN approach for SMILES string generation, in terms of the (i) novelty, (ii) scaffold diversity, and (iii) chemical-biological relevance of the computer-generated molecules. The results positively advocate bidirectional strategies for SMILES-based molecular de novo design, with BIMODAL showing superior results to the unidirectional forward RNN for most of the criteria in the tested conditions. The code of the methods and the pretrained models can be found at URL https://github.com/ETHmodlab/BIMODAL.