Tianhao Yu et al., Enzyme function prediction using contrastive learning.Science 379,1358-1363(2023). DOI:10.1126/science.adf2465


Enzyme function annotation is a fundamental challenge, and numerous computational tools have been developed. However, most of these tools cannot accurately predict functional annotations, such as enzyme commission (EC) number, for less-studied proteins or those with previously uncharacterized functions or multiple activities. We present a machine learning algorithm named CLEAN (contrastive learning–enabled enzyme annotation) to assign EC numbers to enzymes with better accuracy, reliability, and sensitivity compared with the state-of-the-art tool BLASTp. The contrastive learning framework empowers CLEAN to confidently (i) annotate understudied enzymes, (ii) correct mislabeled enzymes, and (iii) identify promiscuous enzymes with two or more EC numbers—functions that we demonstrate by systematic in silico and in vitro experiments. We anticipate that this tool will be widely used for predicting the functions of uncharacterized enzymes, thereby advancing many fields, such as genomics, synthetic biology, and biocatalysis.


All data and code generated as part of this study are freely accessible in either the supplementary materials or open repositories. Code for model development and validation are freely accessible at Zenodo (43) and GitHub ( CLEAN is converted into an easy-to-use web server and made freely accessible at The following datasets curated in previous publications and databases were used: Price-149 (15) and New-392 (43).