Structure-Aware Compound-Protein Affinity Prediction via Graph Neural Networks with Group Lasso Regularization

📰 ArXiv cs.AI

Learn to predict compound-protein affinity using graph neural networks with group Lasso regularization for improved drug discovery

advanced Published 23 Jun 2026

Action Steps

Build a graph neural network model to predict compound-protein affinity
Apply group Lasso regularization to the model to improve explainability
Configure the model to handle limited compound-protein interaction data
Test the model on a dataset of compound-protein interactions
Compare the performance of the model with other state-of-the-art methods

Who Needs to Know This

Data scientists and researchers in the pharmaceutical industry can benefit from this approach to accelerate drug discovery and improve molecular representation learning

Key Insight

💡 Graph neural networks with group Lasso regularization can improve the accuracy and explainability of compound-protein affinity prediction

Key Takeaways

Learn to predict compound-protein affinity using graph neural networks with group Lasso regularization for improved drug discovery

Full Article

Title: Structure-Aware Compound-Protein Affinity Prediction via Graph Neural Networks with Group Lasso Regularization

Abstract:
arXiv:2507.03318v3 Announce Type: replace-cross Abstract: Explainable artificial intelligence approaches accelerate drug discovery by improving molecular representation learning, identifying key molecular structures, and rationalizing drug property prediction. However, developing end-to-end explainable models for target-specific structure-activity relationship modeling remains challenging because compound-protein interaction data are often limited for individual targets, and small changes in che

Read full paper → ← Back to Reads