Due to the surging of cost, artificial intelligence-assisted de novo drug design has supplanted conventional methods and become an emerging option for drug discovery. Although there have arisen many successful examples of applying generative models to the molecular field, these methods struggle to deal with conditional generation that meet chemists' practical requirements which ask for a controllable process to generate new molecules or optimize basic molecules with appointed conditions. To address this problem, a Recurrent Molecular-Generative Pretrained Transformer model is proposed, supplemented by LocalRNN and Residual Attention Layer Transformer, referred to as RM-GPT. RM-GPT rebuilds GPT model's architecture by incorporating LocalRNN and Residual Attention Layer Transformer so that it is able to extract local information and build connectivity between attention blocks. The incorporation of Transformer in these two modules enables leveraging the parallel computing advantages of multi-head attention mechanisms while extracting local structural information effectively. Through exploring and learning in a large chemical space, RM-GPT absorbs the ability to generate drug-like molecules with conditions in demand, such as desired properties and scaffolds, precisely and stably. RM-GPT achieved better results than SOTA methods on conditional generation.
Keywords: De novo drug design; Generative pre-training model; Molecular generation; Recurrent neural networks; Residual attention mechanism; Transformer.
Copyright © 2024 Elsevier B.V. All rights reserved.