AI Article Synopsis
- Deep generative models, particularly generative adversarial networks (GANs), are powerful tools for drug molecular generation, but they face training challenges like instability and model collapse.
- The proposed method, STAGAN, addresses these issues by introducing a new gradient penalty for the discriminator and implementing a batch normalization layer in the generator.
- STAGAN demonstrated improved performance by generating a higher number of valid and unique molecules compared to previous models, indicating its effectiveness in enhancing stability during the training process.
Article Abstract
With the wide application of deep learning in Drug Discovery, deep generative model has shown its advantages in drug molecular generation. Generative adversarial networks can be used to learn the internal structure of molecules, but the training process may be unstable, such as gradient disappearance and model collapse, which may lead to the generation of molecules that do not conform to chemical rules or a single style. In this paper, a novel method called STAGAN was proposed to solve the difficulty of model training, by adding a new gradient penalty term in the discriminator and designing a parallel layer of batch normalization used in generator. As an illustration of method, STAGAN generated higher valid and unique molecules than previous models in training datasets from QM9 and ZINC-250K. This indicates that the proposed method can effectively solve the instability problem in the model training process, and can provide more instructive guidance for the further study of molecular graph generation.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.compbiomed.2023.107691 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!