# A geometric graph-based deep learning model for drug-target affinity prediction

## TL;DR

This paper introduces DeepGGL, a deep learning model that improves drug-target binding affinity predictions using geometric graphs and attention mechanisms.

## Contribution

DeepGGL is a novel deep learning model that combines geometric graph learning with attention and residual connections for drug-target affinity prediction.

## Key findings

- DeepGGL outperformed existing models on CASF-2013 and CASF-2016 datasets.
- The model showed consistent accuracy on CSAR-NRC-HiQ and PDBbind v2019 holdout sets.
- It effectively captures atom-level interactions across multiple scales in protein-ligand complexes.

## Abstract

In structure-based drug design, accurately estimating the binding affinity between a candidate ligand and its protein receptor is a central challenge. Recent advances in artificial intelligence, particularly deep learning, have demonstrated superior performance over traditional empirical and physics-based methods for this task, enabled by the growing availability of structural and experimental affinity data. In this work, we introduce DeepGGL, a deep convolutional neural network that integrates residual connections and an attention mechanism within a geometric graph learning framework. By leveraging multiscale weighted colored bipartite subgraphs, DeepGGL effectively captures fine-grained atom-level interactions in protein-ligand complexes across multiple scales. We benchmarked DeepGGL against established models on CASF-2013 and CASF-2016, where it achieved state-of-the-art performance with significant improvements across diverse evaluation metrics. To further assess robustness and generalization, we tested the model on the CSAR-NRC-HiQ dataset and the PDBbind v2019 holdout set. DeepGGL consistently maintained high predictive accuracy, highlighting its adaptability and reliability for binding affinity prediction in structure-based drug discovery.

The online version contains supplementary material available at 10.1186/s12859-025-06347-2.