Prediction and design of protease enzyme specificity using a structure-aware graph convolutional network
Open Access
- 20 September 2023
- journal article
- research article
- Published by National Academy of Sciences in Proceedings of the National Academy of Sciences
- Vol. 120 (39)
Abstract
Site-specific proteolysis by the enzymatic cleavage of small linear sequence motifs is a key posttranslational modification involved in physiology and disease. The ability to robustly and rapidly predict protease–substrate specificity would also enable targeted proteolytic cleavage by designed proteases. Current methods for predicting protease specificity are limited to sequence pattern recognition in experimentally derived cleavage data obtained for libraries of potential substrates and generated separately for each protease variant. We reasoned that a more semantically rich and robust model of protease specificity could be developed by incorporating the energetics of molecular interactions between protease and substrates into machine learning workflows. We present Protein Graph Convolutional Network (PGCN), which develops a physically grounded, structure-based molecular interaction graph representation that describes molecular topology and interaction energetics to predict enzyme specificity. We show that PGCN accurately predicts the specificity landscapes of several variants of two model proteases. Node and edge ablation tests identified key graph elements for specificity prediction, some of which are consistent with known biochemical constraints for protease:substrate recognition. We used a pretrained PGCN model to guide the design of protease libraries for cleaving two noncanonical substrates, and found good agreement with experimental cleavage results. Importantly, the model can accurately assess designs featuring diversity at positions not present in the training data. The described methodology should enable the structure-based prediction of specificity landscapes of a wide variety of proteases and the construction of tailor-made protease editors for site-selectively and irreversibly modifying chosen target proteins.Keywords
Funding Information
- National Science Foundation (CHE2226816)
- HHS | National Institutes of Health (T32 GM008339)
- RosettaCommons (REU)
This publication has 60 references indexed in Scilit:
- PROSPER: An Integrated Feature-Based Tool for Predicting Protease Substrate Cleavage SitesPLOS ONE, 2012
- Developing a powerful In Silico tool for the discovery of novel caspase-3 substrates: a preliminary screening of the human proteomeBMC Bioinformatics, 2012
- GPS-CCD: A Novel Computational Program for the Prediction of Calpain Cleavage SitesPLOS ONE, 2011
- Alternate States of Proteins Revealed by Detailed Energy Landscape MappingJournal of Molecular Biology, 2011
- Drug resistance against HCV NS3/4A inhibitors is defined by the balance of substrate recognition versus inhibitor bindingProceedings of the National Academy of Sciences, 2010
- Pripper: prediction of caspase cleavage sites from whole proteomesBMC Bioinformatics, 2010
- Engineering next generation proteasesCurrent Opinion in Biotechnology, 2009
- NeuroPred: a tool to predict cleavage sites in neuropeptide precursors and provide the masses of the resulting peptidesNucleic Acids Research, 2006
- GraBCas: a bioinformatics tool for score-based prediction of Caspase- and Granzyme B-cleavage sites in protein sequencesNucleic Acids Research, 2005
- The P1′ specificity of tobacco etch virus proteaseBiochemical and Biophysical Research Communications, 2002