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

06 March 2024, Version 1
This content is a preprint and has not undergone peer review at the time of posting.


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 architecture, a different 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. This approach enables the unification of de novo generation, scaffold decoration, and fragment linking into one chemical language model, without the need to use a bespoke grammar, curate a custom dataset or train a separate model. 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.


Chemical language model
Scaffold hopping
Scaffold decoration
Fragment linking
Reinforcement learning
De novo molecule generation
Artificial intelligence
Drug design

Supplementary weblinks


Comments are not moderated before they are posted, but they can be removed by the site moderators if they are found to be in contravention of our Commenting Policy [opens in a new tab] - please read this policy before you post. Comments should be used for scholarly discussion of the content in question. You can find more information about how to use the commenting feature here [opens in a new tab] .
This site is protected by reCAPTCHA and the Google Privacy Policy [opens in a new tab] and Terms of Service [opens in a new tab] apply.