Discriminative structural approaches for enzyme active-site prediction

Tsuyoshi Kato,Nozomi Nagano

doi:10.1186/1471-2105-12-s1-s49

Abstract

BackgroundPredicting enzyme active-sites in proteins is an important issue not only for protein sciences but also for a variety of practical applications such as drug design. Because enzyme reaction mechanisms are based on the local structures of enzyme active-sites, various template-based methods that compare local structures in proteins have been developed to date. In comparing such local sites, a simple measurement, RMSD, has been used so far.ResultsThis paper introduces new machine learning algorithms that refine the similarity/deviation for comparison of local structures. The similarity/deviation is applied to two types of applications, single template analysis and multiple template analysis. In the single template analysis, a single template is used as a query to search proteins for active sites, whereas a protein structure is examined as a query to discover the possible active-sites using a set of templates in the multiple template analysis.ConclusionsThis paper experimentally illustrates that the machine learning algorithms effectively improve the similarity/deviation measurements for both the analyses.

Highlights

Predicting enzyme active-sites in proteins is an important issue for protein sciences and for a variety of practical applications such as drug design
Considering those facts, Nagano developed an enzyme reaction database, EzCatDB, which provides a hierarchic classification of enzyme reactions, RLCP, which clusters the same reaction types together based on the reaction type, the reactive site of the substrate, the catalytic mechanism, and the catalytic site of enzymes [5]
Active-site prediction is performed by comparing the active sites of templates with local sites in protein structures; if the local site structure is sufficiently similar to Unweighted Mean Deviation (UMD) Weighted Mean Deviation (WMD) mean of DALI scores (MDS) DALI Scorebased Discriminative Similarity (DSDS)

Summary

Introduction

Predicting enzyme active-sites in proteins is an important issue for protein sciences and for a variety of practical applications such as drug design. More recent reports suggest that such cases of active sites shared by analogous enzymes are not rare [3,4] Considering those facts, Nagano developed an enzyme reaction database, EzCatDB, which provides a hierarchic classification of enzyme reactions, RLCP, which clusters the same reaction types together based on the reaction type, the reactive site of the substrate, the catalytic mechanism, and the catalytic site of enzymes [5]. Both the homologous reaction and the analogous reaction can be clustered together in the RLCP classification if they share the same catalytic mechanism and the catalytic site of the same type [5]

Methods

Results

Conclusion