PromptSMILES: prompting for scaffold decoration and fragment linking in chemical language models

• Published in: Journal of cheminformatics Vol. 16; no. 1; pp. 77 - 15
• Main Authors: Thomas, Morgan, Ahmad, Mazen, Tresadern, Gary, de Fabritiis, Gianni
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 04.07.2024; BioMed Central Ltd; Springer Nature B.V; BMC
• Subjects: Analysis; Artificial intelligence; Chemical language models; Chemistry; Chemistry and Materials Science; Computational Biology/Bioinformatics; Computer Applications in Chemistry; Datasets; De novo molecule generation; Decoration; Documentation and Information in Chemistry; Drug development; Fragment linking; Language; Molecular modelling; Reinforcement learning; Scaffold decoration; Scaffold hopping; Scaffolds; Theoretical and Computational Chemistry; Training; Samoa (Nation); Scaffold hopping; Scaffold decoration; Fragment linking; Reinforcement learning; Chemical language models; Drug design; Artificial intelligence; De novo molecule generation
• ISSN: 1758-2946; 1758-2946
• DOI: 10.1186/s13321-024-00866-5

SMILES-based generative models are amongst the most robust and successful recent methods used to augment drug design. They are typically used for complete de novo generation, however, scaffold decoration and fragment linking applications are sometimes desirable which requires a different grammar, architecture, training dataset and therefore, re-training of a new model. In this work, we describe a simple procedure to conduct constrained molecule generation with a SMILES-based generative model to extend applicability to scaffold decoration and fragment linking by providing SMILES prompts, without the need for re-training. In combination with reinforcement learning, we show that pre-trained, decoder-only models adapt to these applications quickly and can further optimize molecule generation towards a specified objective. We compare the performance of this approach to a variety of orthogonal approaches and show that performance is comparable or better. For convenience, we provide an easy-to-use python package to facilitate model sampling which can be found on GitHub and the Python Package Index. Scientific contribution This novel method extends an autoregressive chemical language model to scaffold decoration and fragment linking scenarios. This doesn’t require re-training, the use of a bespoke grammar, or curation of a custom dataset, as commonly required by other approaches.