De Novo Drug Design with Joint Transformers
This work addresses the problem of efficient drug discovery for pharmaceutical researchers, but it appears incremental as it builds on existing Transformer and optimization techniques.
The paper tackled the challenge of generating novel molecules with improved target properties in de novo drug design by proposing a Joint Transformer model, which outperformed other SMILES-based optimization methods.
De novo drug design requires simultaneously generating novel molecules outside of training data and predicting their target properties, making it a hard task for generative models. To address this, we propose Joint Transformer that combines a Transformer decoder, Transformer encoder, and a predictor in a joint generative model with shared weights. We formulate a probabilistic black-box optimization algorithm that employs Joint Transformer to generate novel molecules with improved target properties and outperforms other SMILES-based optimization methods in de novo drug design.