EnzyREx: deep learning enables reaction-based comprehensive enzyme screening

Abstract Background Enzymes accelerate biochemical reactions in living organisms, thus playing an important role in metabolism. Although metabolic pathway databases are growing, many metabolic reactions, termed orphan enzymes, have not been annotated to gene sequences, which hinders functional annotation in genomic analysis. Moreover, protein databases contain many proteins of unknown function. Owing to this gap between known proteins and enzymatic reactions, various proteins of unknown function may be orphan enzymes; however, available tools cannot adequately predict these links. Results In this study, we developed DeepRES, an AI-based framework for comprehensive enzyme screening, to explore novel enzyme candidates from proteins of unknown function for reactions of interest. DeepRES implements enzyme screening via two steps: classification of enzymes and non-enzymes and prediction of catalytic capabilities for enzyme‒reaction pairs. The two deep learning models comprising DeepRES showed comparable or superior performance to that of existing software. We performed screening of 1,255 orphan enzymes involved in the microbiome using DeepRES and successfully identified candidate proteins for 897 orphan enzymes. We then used those candidates as references for genomic analysis and explored novel biosynthetic gene clusters from microbial genomes to obtain promising candidate gene clusters, including those related to anthocyanin degradation. Conclusions Comprehensive enzyme screening via DeepRES, which is the first computational tool designed to associate orphan enzymes with proteins of unknown function, is expected to facilitate high-throughput identification of orphan enzyme-encoding genes. Furthermore, DeepRES can be easily integrated into the current genomic analysis pipeline to extend the functional annotation.