Deep Learning Enables Rapid Identification of Mycotoxin-Degrading Enzymes

30 June 2023, Version 1
This content is a preprint and has not undergone peer review at the time of posting.


The identification of functional enzymes for the catalysis of specific biochemical reactions is a major bottleneck in the de novo design of biosynthesis and biodegradation pathways. Conventional methods based on microbial screening and functional metagenomics require long verification periods and incur high experimental costs; recent data-driven methods are only applicable to a few common substrates. To enable rapid and high-throughput identification of enzymes for complex and less-studied substrates, we propose a robust enzyme promiscuity prediction model based on positive unlabeled learning, which shortens the time needed for new enzyme discovery from several years to 29 days. Using this model, we identified 15 new degrading enzymes specific for the mycotoxins ochratoxin A and zearalenone, of which six could degrade > 90% mycotoxin content within 3 h. We anticipate that this model will become indispensable for the identification of new functional enzymes, thereby advancing the fields of synthetic biology, metabolic engineering, and pollutant biodegradation.


synthetic biology
machine learning
food safety


Comments are not moderated before they are posted, but they can be removed by the site moderators if they are found to be in contravention of our Commenting Policy [opens in a new tab] - please read this policy before you post. Comments should be used for scholarly discussion of the content in question. You can find more information about how to use the commenting feature here [opens in a new tab] .
This site is protected by reCAPTCHA and the Google Privacy Policy [opens in a new tab] and Terms of Service [opens in a new tab] apply.
Comment number 1, Dachuan Zhang: Feb 21, 2024, 01:48

officially published version: