UniZyme: A Unified Protein Cleavage Site Predictor Enhanced with Enzyme Active-Site Knowledge
This work addresses the problem of enzyme-catalyzed protein cleavage site prediction for researchers and developers in the fields of drug development, enzyme design, and biological mechanism understanding.
The authors tackled the problem of predicting protein cleavage sites across diverse enzymes and achieved high accuracy with their UniZyme model, which can generalize to novel enzymes. UniZyme demonstrates its effectiveness in predicting cleavage sites for a range of proteolytic enzymes, including unseen ones.
Enzyme-catalyzed protein cleavage is essential for many biological functions. Accurate prediction of cleavage sites can facilitate various applications such as drug development, enzyme design, and a deeper understanding of biological mechanisms. However, most existing models are restricted to an individual enzyme, which neglects shared knowledge of enzymes and fails generalize to novel enzymes. Thus, we introduce a unified protein cleavage site predictor named UniZyme, which can generalize across diverse enzymes. To enhance the enzyme encoding for the protein cleavage site prediction, UniZyme employs a novel biochemically-informed model architecture along with active-site knowledge of proteolytic enzymes. Extensive experiments demonstrate that UniZyme achieves high accuracy in predicting cleavage sites across a range of proteolytic enzymes, including unseen enzymes. The code is available in https://anonymous.4open.science/r/UniZyme-4A67.