Table of Contents Author Guidelines Submit a Manuscript
Evidence-Based Complementary and Alternative Medicine
Volume 2015, Article ID 561024, 9 pages
Research Article

Application of Artificial Intelligence to the Prediction of the Antimicrobial Activity of Essential Oils

Center for Pharmacognosy and Phytotherapy, Department of Pharmaceutical and Biological Chemistry, School of Pharmacy, University of London, 29-39 Brunswick Square, London WC1N 1AX, UK

Received 22 March 2015; Revised 8 August 2015; Accepted 23 August 2015

Academic Editor: Filippo Maggi

Copyright © 2015 Mathieu Daynac et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.


Essential oils (EOs) are vastly used as natural antibiotics in Complementary and Alternative Medicine (CAM). Their intrinsic chemical variability and synergisms/antagonisms between its components make difficult to ensure consistent effects through different batches. Our aim is to evaluate the use of artificial neural networks (ANNs) for the prediction of their antimicrobial activity. Methods. The chemical composition and antimicrobial activity of 49 EOs, extracts, and/or fractions was extracted from NCCLS compliant works. The fast artificial neural networks (FANN) software was used and the output data reflected the antimicrobial activity of these EOs against four common pathogens: Staphylococcus aureus, Escherichia coli, Candida albicans, and Clostridium perfringens as measured by standardised disk diffusion assays. Results. ANNs were able to predict >70% of the antimicrobial activities within a 10 mm maximum error range. Similarly, ANNs were able to predict 2 or 3 different bioactivities at the same time. The accuracy of the prediction was only limited by the inherent errors of the popular antimicrobial disk susceptibility test and the nature of the pathogens. Conclusions. ANNs can be reliable, fast, and cheap tools for the prediction of the antimicrobial activity of EOs thus improving their use in CAM.