De Novo Molecular Generation with Stacked Adversarial Model
This work addresses the time-consuming and complex task of de novo drug design for pharmaceutical research, but it is incremental as it builds upon existing adversarial autoencoder methods.
The paper tackled the problem of generating novel drug molecules with desired biological properties by proposing a stacked adversarial model that extends an existing adversarial autoencoder approach. The result showed that the model generates more valid molecules and molecules more similar to known drugs, with promising performance demonstrated on the LINCS L1000 dataset.
Generating novel drug molecules with desired biological properties is a time consuming and complex task. Conditional generative adversarial models have recently been proposed as promising approaches for de novo drug design. In this paper, we propose a new generative model which extends an existing adversarial autoencoder (AAE) based model by stacking two models together. Our stacked approach generates more valid molecules, as well as molecules that are more similar to known drugs. We break down this challenging task into two sub-problems. A first stage model to learn primitive features from the molecules and gene expression data. A second stage model then takes these features to learn properties of the molecules and refine more valid molecules. Experiments and comparison to baseline methods on the LINCS L1000 dataset demonstrate that our proposed model has promising performance for molecular generation.