On the Choice of Active Site Sequences for Kinase-Ligand Affinity Prediction

Recent work showed that active site rather than full-protein-sequence information improves predictive performance in kinase-ligand binding affinity prediction. To refine the notion of an active site , we here propose and compare multiple definitions. We report significant evidence that our novel definition is superior to previous definitions and better models of ATP noncompetitive inhibitors. Moreover, we leverage the discontiguity of the active site sequence to motivate novel protein-sequence augmentation strategies and find that combining them further improves performance.

Automated summary

Recent work suggests that using active site information instead of full protein sequence improves the accuracy of predicting kinase-ligand binding affinity. In this study, we propose and compare multiple definitions of the active site, and find that our novel definition outperforms previous definitions and better models ATP noncompetitive inhibitors. Additionally, by leveraging the discontiguity of the active site sequence, we develop novel protein-sequence augmentation strategies that further enhance performance.