Proximity Graph Networks: Predicting Ligand Affinity with Message Passing Neural Networks

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


Message-passing neural networks (MPNNs) on molecular graphs generate continuous and differentiable encodings of small molecules with state-of-the-art performance on protein-ligand complex scoring tasks. Here, we describe the Protein-Graph Network (PGN) package, an open-source toolkit that constructs ligand-receptor graphs based on atom proximity and allows users to rapidly apply and evaluate MPNN architectures for a broad range of tasks. We demonstrate the utility of PGN by introducing benchmarks for affinity and docking score prediction tasks. Graph networks generalize better than fingerprint-based models and perform strongly for the docking score prediction task. Overall, MPNNs with Proximity Graph data structures augment the prediction of ligand-receptor complex properties when ligand-receptor data are available.


deep learning
message passing neural network
drug discovery
affinity prediction
virtual screening
protein-ligand interface
atom graph
open source

Supplementary materials

Supporting Information
Code availability, Supporting Methods, Supporting Tables S1-S15, SI Figures 1-6, and Supplemental References.

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.