Learning Multimodal Graph-to-Graph Translation for Molecular Optimization
This work addresses molecular optimization for drug discovery or materials science, presenting a novel method for diverse translations but is incremental in improving over existing graph-based approaches.
The paper tackles molecular optimization by framing it as a graph-to-graph translation problem, learning to map molecules to improved versions with better properties, and demonstrates that their model outperforms previous state-of-the-art baselines on multiple tasks.
We view molecular optimization as a graph-to-graph translation problem. The goal is to learn to map from one molecular graph to another with better properties based on an available corpus of paired molecules. Since molecules can be optimized in different ways, there are multiple viable translations for each input graph. A key challenge is therefore to model diverse translation outputs. Our primary contributions include a junction tree encoder-decoder for learning diverse graph translations along with a novel adversarial training method for aligning distributions of molecules. Diverse output distributions in our model are explicitly realized by low-dimensional latent vectors that modulate the translation process. We evaluate our model on multiple molecular optimization tasks and show that our model outperforms previous state-of-the-art baselines.