LigGPT: Molecular Generation using a Transformer-Decoder Model

11 May 2021, Version 1
This content is a preprint and has not undergone peer review at the time of posting.


Application of deep learning techniques for the de novo generation of molecules, termed as inverse molecular design, has been gaining enormous traction in drug design. The representation of molecules in SMILES notation as a string of characters enables the usage of state of the art models in Natural Language Processing, such as the Transformers, for molecular design in general. Inspired by Generative Pre-Training (GPT) model that have been shown to be successful in generating meaningful text, we train a Transformer-Decoder on the next token prediction task using masked self-attention for the generation of druglike molecules in this study. We show that our model, LigGPT, outperforms other previously proposed modern machine learning frameworks for molecular generation in terms of generating valid, unique and novel molecules. Furthermore, we demonstrate that the model can be trained conditionally to optimize multiple properties of the generated molecules. We also show that the model can be used to generate molecules with desired scaffolds as well as desired molecular properties, by passing these structures as conditions, which has potential applications in lead optimization in addition to de novo molecular design. Using saliency maps, we highlight the interpretability of the generative process of the model.


Generative Modeling
Artificial Intelligence
Generative Pre-Training
Drug Design
Lead Optimization

Supplementary materials

liggpt si


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.