Application of SAR methods toward inhibition of bacterial peptidoglycan metabolizing enzymes
Structure activity relationship (SAR) methods are applied for a study of inhibition of peptidoglycan metabolizing enzymes, which could represent new antibacterial targets. In this study, we exploit experimental data of inhibition of Mur A and Mur B enzymes for classification of large set of chemical...
Saved in:
Published in | Journal of chemometrics Vol. 32; no. 4 |
---|---|
Main Authors | , , |
Format | Journal Article |
Language | English |
Published |
Chichester
Wiley Subscription Services, Inc
01.04.2018
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Structure activity relationship (SAR) methods are applied for a study of inhibition of peptidoglycan metabolizing enzymes, which could represent new antibacterial targets. In this study, we exploit experimental data of inhibition of Mur A and Mur B enzymes for classification of large set of chemicals. Based on inhibitory potency of compounds and their structures from the literature, we developed classification models for new, potential inhibitors of Mur A and Mur B enzymes. The best model for Mur A has the following performance measures for the validation set: 0.85, 0.75, and 0.80, for sensitivity, specificity, and normalized Matthews correlation coefficient, respectively. The same measures of the best Mur B model are 0.94, 0.75, and 0.86. Such models could represent valuable computational tools for theoretic predictions of compounds' activities against specific targets. Additionally, application of such models, like any other computational tools, significantly reduces time and costs in the early phase of drug design.
Artificial neural network–based classification models were developed by using public experimental dataset of Mur A and Mur B inhibitors. Genetic optimization was applied for selection of descriptors. Structure‐activity relationship of active/nonactive compounds, interpreted based on selected descriptors, showed negative correlation between drug‐likeness and most of the active compounds. New information about influencing structural properties, provided in the present study, can contribute to design compounds with higher potency, considering also drug‐likeness, which seems to be the most problematic. |
---|---|
ISSN: | 0886-9383 1099-128X |
DOI: | 10.1002/cem.3007 |