ESM-Ezy: a deep learning strategy for the mining of novel multicopper oxidases with superior properties

ESM-Ezy is a deep learning enzyme mining strategy that uses the ESM-1b protein language model and semantic space similarity calculations to discover novel multicopper oxidases (MCOs) with superior catalytic properties from the UniProt database. The strategy achieved a 44% success rate in identifying MCOs that outperform query enzymes in at least one catalytic property.