Sc2Mol: a scaffold-based two-step molecule generator with variational autoencoder and transformer

Zhirui Liao, Lei Xie, Hiroshi Mamitsuka, Shanfeng Zhu

Abstract: Finding molecules with desired pharmaceutical properties is crucial in drug discovery. Generative models can be an efficient tool to find desired molecules through the distribution learned by the model to approximate given training data. Existing generative models (i) do not consider backbone structures (scaffolds), resulting in inefficiency or (ii) need prior patterns for scaffolds, causing bias. Scaffolds are reasonable to use, and it is imperative to design a generative model without any prior scaffold patterns.