The
hallmark reaction of P450 monooxygenase involves activation
of C–H bond and the production of a hydroxyl. P450s tailoring
natural product could further oxidize the hydroxyl to carboxylic acid.
However, heterogeneously expressed plant P450s display poor chemo-
and regioselectivity in microbes, restricting the efficient biosynthesis
of related natural products. CYP72A63 is a P450 enzyme previously
used for the biosynthesis of glycyrrhetinic acid, and its poor selectivity
resulted in oxidation of 11-oxo-β-amyrin to a mixture of rare
licorice triterpenoids (glycyrrhetol, glycyrrhetaldehyde, glycyrrhetinic
acid, and 29-OH-11-oxo-β-amyrin). In this study, we have identified
key residues, which influence the enzyme–substrate hydrophobic
interaction, in controlling the chemo- and regioselectivity of the
enzyme and engineered the enzyme toward selectivity oxidation to hydroxyl
and carboxylic acid. Moreover, tuning the redox partner of the P450
leads to selective production of glycyrrhetaldehyde, a good starting
point for further modification. In this study, controlling the catalytic
property of plant P450s prove to be of great use in the synthesis
of desired licorice triterpenoids, which can be used in biosynthesis
of other terpenoid natural products.
User interest modeling is critical for personalized news recommendation. Existing news recommendation methods usually learn a single user embedding for each user from their previous behaviors to represent their overall interest. However, user interest is usually diverse and multi-grained, which is difficult to be accurately modeled by a single user embedding. In this paper, we propose a news recommendation method with hierarchical user interest modeling, named HieRec. Instead of a single user embedding, in our method each user is represented in a hierarchical interest tree to better capture their diverse and multi-grained interest in news. We use a three-level hierarchy to represent 1) overall user interest; 2) user interest in coarse-grained topics like sports; and 3) user interest in fine-grained topics like football. Moreover, we propose a hierarchical user interest matching framework to match candidate news with different levels of user interest for more accurate user interest targeting. Extensive experiments on two real-world datasets validate our method can effectively improve the performance of user modeling for personalized news recommendation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.