Wang Feng, Feng Xiaochen, Guo Xiao, Xu Lei, Xie Liangxu, Chang Shan
Changzhou University Huaide College, Taizhou, China.
School of Computer Science and Artificial Intelligence, Aliyun School of Big Data, Changzhou University, Changzhou, China.
Front Genet. 2021 Aug 5;12:709500. doi: 10.3389/fgene.2021.709500. eCollection 2021.
The application of deep learning in the field of drug discovery brings the development and expansion of molecular generative models along with new challenges in this field. One of challenges in molecular generation is how to produce new reasonable molecules with desired pharmacological, physical, and chemical properties. To improve the similarity between the generated molecule and the starting molecule, we propose a new molecule generation model by embedding Long Short-Term Memory (LSTM) and Attention mechanism in CycleGAN architecture, LA-CycleGAN. The network layer of the generator in CycleGAN is fused head and tail to improve the similarity of the generated structure. The embedded LSTM and Attention mechanism can overcome long-term dependency problems in treating the normally used SMILES input. From our quantitative evaluation, we present that LA-CycleGAN expands the chemical space of the molecules and improves the ability of structure conversion. The generated molecules are highly similar to the starting compound structures while obtaining expected molecular properties during cycle generative adversarial network learning, which comprehensively improves the performance of the generative model.
深度学习在药物发现领域的应用带来了分子生成模型的发展与拓展，同时也给该领域带来了新的挑战。分子生成中的挑战之一是如何生成具有所需药理、物理和化学性质的新的合理分子。为了提高生成分子与起始分子之间的相似度，我们通过在循环生成对抗网络（CycleGAN）架构中嵌入长短期记忆（LSTM）和注意力机制，提出了一种新的分子生成模型，即LA-CycleGAN。CycleGAN中生成器的网络层进行了首尾融合，以提高生成结构的相似度。嵌入的LSTM和注意力机制能够克服处理常用SMILES输入时的长期依赖问题。通过定量评估，我们表明LA-CycleGAN扩展了分子的化学空间，提高了结构转换能力。在循环生成对抗网络学习过程中，生成的分子与起始化合物结构高度相似，同时获得了预期的分子性质，全面提升了生成模型的性能。
