DeepMolecules: a web server for predicting enzyme and transporter-small molecule interactions

DeepMolecules is an easily accessible web server for predicting protein-small molecule interactions. It integrates four state-of-the-art models: ESP and SPOT for identifying substrates of enzymes and transporters, respectively, TurNuP for predicting enzyme turnover numbers kcat, and a model for predicting Michaelis constants KM. These models use deep learning-generated numerical representations of the proteins and small molecules as input features for gradient-boosted decision tree models, achieving high predictive performance. The web interface accepts protein amino acid sequences and small molecules in SMILES, InChI, or KEGG ID formats, supporting single submissions and batch submissions via Excel files. Beyond its predictive capabilities, DeepMolecules provides a structured interface to experimental data on known interactions and kinetic parameters, offering a comprehensive view of protein-small molecule relationships. Freely accessible at https://www.DeepMolecules.org, the web server supports applications in metabolic engineering, drug discovery, and biocatalyst optimization by identifying potential substrates and quantifying their catalytic properties.