*** Disclaimer: This blog post represents some shameless self-promotion. ***

I am delighted to announce that our most recent work, DeLinker, was recently published in the Journal of Chemical Information and Modeling (link).

DeLinker is a deep learning method based on graph neural networks that proposes linkers between molecular fragments. Crucially, DeLinker is a first step at incorporating 3D structural knowledge directly into the generation process.

In our paper, we showed the application of DeLinker to fragment linking, scaffold hopping, and PROTAC design, and demonstrated substantial outperformance over a database baseline.

We have open-sourced the code on GitHub (link) and welcome any feedback and suggestions.

We are currently working on extending DeLinker to new design problems, and improving our model. We also hope to release additional examples of a simplified workflow to make using our method more accessible.

If you like our work or found it helpful, you can cite it as:
Imrie F, Bradley AR, van der Schaar M, Deane CM. Deep Generative Models for 3D Linker Design. Journal of Chemical Information and Modeling. 2020

BibTex:
@Article{Imrie2020,
author={Imrie, Fergus and Bradley, Anthony R. and van der Schaar, Mihaela and Deane, Charlotte M.},
title={Deep Generative Models for 3D Linker Design},
journal={Journal of Chemical Information and Modeling},
year={2020},
month={Mar},
day={20},
publisher={American Chemical Society},
issn={1549-9596},
doi={10.1021/acs.jcim.9b01120},
url={https://doi.org/10.1021/acs.jcim.9b01120}
}