The rapid growth of uncharacterized enzymes and their functional diversity urge accurate and trustworthy computational functional annotation tools. However, current state-of-the-art models lack trustworthiness on the prediction of the multilabel classification problem with thousands of classes. Here, we demonstrate that a novel evidential deep learning model (named ECPICK) makes trustworthy predictions of enzyme commission (EC) numbers with data-driven domain-relevant evidence, which results in significantly enhanced predictive power and the capability to discover potential new motif sites. ECPICK learns complex sequential patterns of amino acids and their hierarchical structures from 20 million enzyme data. ECPICK identifies significant amino acids that contribute to the prediction without multiple sequence alignment. Our intensive assessment showed not only outstanding enhancement of predictive performance on the largest databases of Uniprot, Protein Data Bank (PDB) and Kyoto Encyclopedia of Genes and Genomes (KEGG), but also a capability to discover new motif sites in microorganisms. ECPICK is a reliable EC number prediction tool to identify protein functions of an increasing number of uncharacterized enzymes.

Bacteria possess diverse metabolic and genetic processes, resulting in the inability of certain bacteria to degrade trehalose. However, some bacteria do have the capability to degrade trehalose, utilizing it as a carbon source, and for defense against environmental stress. Trehalose, a disaccharide, serves as a carbon source for many bacteria, including some that are vital for pathogens. The degradation of trehalose is carried out by enzymes like trehalase (EC 3.2.1.28) and trehalose phosphorylase (EC 2.4.1.64/2.4.1.231), which are classified under the glycoside hydrolase families GH37, GH15, and GH65. Numerous studies and reports have explored the physiological functions, recombinant expression, enzymatic characteristics, and potential applications of these enzymes. However, further research is still being conducted to understand their roles in bacteria. This review aims to provide a comprehensive summary of the current understanding of trehalose degradation pathways in various bacteria, focusing on three key areas: (i) identifying different trehalose-degrading enzymes in Gram-positive and Gram-negative bacteria, (ii) elucidating the mechanisms employed by trehalose-degrading enzymes belonging to the glycoside hydrolases GH37, GH15, and GH65, and (iii) discussing the potential applications of these enzymes in different sectors. Notably, this review emphasizes the bacterial trehalose-degrading enzymes, specifically trehalases (GH37, GH15, and GH65) and trehalose phosphorylases (GH65), in both Gram-positive and Gram-negative bacteria, an aspect that has not been highlighted before.