The MITE data standard/repository stores information on tailoring enzymes - enzymes that modify immature natural products. Each MITE entry contains information on a single enzyme: its reaction(s), substrate specificities, known substrate-product pairs, and more. The MITE dataset can be used for machine learning applications, as knowledgebase, or as parts catalog for synthetic biology.
MITE is a data repository for and created by the scientific community. To grow, it depends on submissions by you, the user. If you work on tailoring enzymes, please consider contributing to the MITE data repository - it's easy!