Randomized SMILES strings improve the quality of molecular generative models
Randomized SMILES strings improve the quality of molecular generative models
复制标题
DOI：
10.1186/s13321-019-0393-0
复制
发表时间：
2019-11-21
影响因子：
8.6
通讯作者：
Engkvist, Ola
中科院分区：
文献类型：
--
作者：
Arus-Pous, Josep;Johansson, Simon Viet;Engkvist, Ola
用一组表示为独特（规范）SMILES字符串的分子训练的递归神经网络（RNN）已经显示出创建有效和有意义结构的大型化学空间的能力。在本文中，我们对使用不同大小（100万，10，000和1000）的GDB-13子集，不同的SMILES变体（规范，随机和DeepSMILES），两种不同的递归细胞类型（LSTM和GRU）以及不同的超参数组合训练的模型进行了广泛的基准测试。为了指导基准测试，开发了新的度量标准，定义了模型对训练集的泛化程度。生成的化学空间的均匀性，封闭性和完整性进行评估。结果表明，使用100万个随机SMILES（一种非唯一的分子串表示）训练的LSTM细胞的模型能够推广到比其他方法更大的化学空间，并且它们更准确地表示目标化学空间。具体来说，用随机化SMILES训练模型，该模型能够以准均匀概率从GDB-13生成几乎所有分子。使用较小样本训练的模型在使用随机SMILES模型训练时表现出更大的改进。此外，在从ChEMBL获得的分子上训练模型，并再次说明使用随机化SMILES的训练导致模型具有更好的药物样化学空间的表示。也就是说，与用标准SMILES训练的模型相比，用随机化SMILES训练的模型能够产生至少两倍数量的具有相同性质分布的独特分子。
Recurrent Neural Networks (RNNs) trained with a set of molecules represented as unique (canonical) SMILES strings, have shown the capacity to create large chemical spaces of valid and meaningful structures. Herein we perform an extensive benchmark on models trained with subsets of GDB-13 of different sizes (1 million, 10,000 and 1000), with different SMILES variants (canonical, randomized and DeepSMILES), with two different recurrent cell types (LSTM and GRU) and with different hyperparameter combinations. To guide the benchmarks new metrics were developed that define how well a model has generalized the training set. The generated chemical space is evaluated with respect to its uniformity, closedness and completeness. Results show that models that use LSTM cells trained with 1 million randomized SMILES, a non-unique molecular string representation, are able to generalize to larger chemical spaces than the other approaches and they represent more accurately the target chemical space. Specifically, a model was trained with randomized SMILES that was able to generate almost all molecules from GDB-13 with a quasi-uniform probability. Models trained with smaller samples show an even bigger improvement when trained with randomized SMILES models. Additionally, models were trained on molecules obtained from ChEMBL and illustrate again that training with randomized SMILES lead to models having a better representation of the drug-like chemical space. Namely, the model trained with randomized SMILES was able to generate at least double the amount of unique molecules with the same distribution of properties comparing to one trained with canonical SMILES.