Enzyme specificity prediction using cross attention graph neural networks

"Enzymes are the molecular machines of life, and a key property that governs their function is substrate specificitythe ability of an enzyme to recognize and selectively act on particular substrates. This specificity originates from the three-dimensional (3D) structure of the enzyme active site and complicated transition state of the reaction1,2. Many enzymes can promiscuously catalyze reactions or act on substrates beyond those for which they were originally evolved1,3-5. However, millions of known enzymes still lack reliable substrate specificity information, impeding their practical applications and comprehensive understanding of the biocatalytic diversity in nature."

"Herein, we developed a cross-attention-empowered SE(3)-equivariant graph neural network architecture named EZSpecificity for predicting enzyme substrate specificity, which was trained on a comprehensive tailor-made database of enzyme-substrate interactions at sequence and structural levels. EZSpecificity outperformed the existing machine learning models for enzyme substrate specificity prediction, as demonstrated by both an unknown substrate and enzyme database and seven proof-of-concept protein families. Experimental validation with eight halogenases and 78 substrates revealed that EZSpecificity achieved a 91.7% accuracy in identif"

Enzyme substrate specificity derives from active-site three-dimensional structure and complex reaction transition states, while many enzymes exhibit substrate promiscuity. Millions of enzymes lack reliable substrate specificity annotations, limiting biocatalytic application and understanding of natural enzymatic diversity. A cross-attention SE(3)-equivariant graph neural network named EZSpecificity was developed and trained on a comprehensive, tailor-made database combining sequence and structural enzyme-substrate interaction data. EZSpecificity outperformed prior machine learning models on datasets containing unknown substrates and enzymes and across seven protein families. Experimental validation on eight halogenases with 78 substrates produced 91.7% prediction accuracy, demonstrating practical predictive capability for enzyme engineering and annotation.

Read at www.nature.com