Back

EzMechanism: An Automated Tool to Propose Catalytic Mechanisms of Enzyme Reactions

Ribeiro, A. J. M.; Riziotis, I. G.; Tyzack, J. D.; Borkakoti, N.; Thornton, J. M.

2022-09-06 bioinformatics
10.1101/2022.09.05.506575 bioRxiv
Show abstract

A rich literature dedicated to understanding the reaction mechanisms of hundreds of enzymes has emerged over time from the works of experimental and computational researchers. This body of information can now be the starting point for an entirely novel approach to studying enzyme mechanisms using knowledge-based prediction methods. Here, we present such a method, EzMechanism, (pronounced as "Easy Mechanism") which is able to automatically generate mechanism proposals for a given active site. It works by searching the chemical reaction space available to the enzyme using a set of newly created biocatalytic rules based on knowledge from the literature. EzMechanism aims to complement existing methods for studying enzyme mechanisms by facilitating and improving the hypotheses generating step. We show that EzMechanism works by validating it against 56 enzymes with a known mechanism and identify the limited coverage of the current ruleset as the main target for further improvement.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.