Structure-based chemical ontology improves chemometric prediction of antibacterial essential oils.

Plants are valuable resources for drug discovery as they produce diverse bioactive compounds. However, the chemical diversity makes it difficult to predict the biological activity of plant extracts via conventional chemometric methods. In this research, we propose a new computational model that integrates chemical composition data with structure-based chemical ontology. For a model validation, two training datasets were prepared from literature on antibacterial essential oils to classify active/inactive oils. Random forest classifiers constructed from the data showed improved prediction performance in both test datasets. Prior feature selection using hierarchical information criterion further improved the performance. Furthermore, an antibacterial assay using a standard strain of Staphylococcus aureus revealed that the classifier correctly predicted the activity of commercially available oils with an accuracy of 83% (= 10/12). The results of this study indicate that machine learning of chemical composition data integrated with chemical ontology can be a highly efficient approach for exploring bioactive plant extracts.

In vitro and in silico prediction of antibacterial interaction between essential oils via graph embedding approach.

Essential oils contain a variety of volatile metabolites, and are expected to be utilized in wide fields such as antimicrobials, insect repellents and herbicides. However, it is difficult to foresee the effect of oil combinations because hundreds of compounds can be involved in synergistic and antagonistic interactions. In this research, it was developed and evaluated a machine learning method to classify types of (synergistic/antagonistic/no) antibacterial interaction between essential oils. Graph embedding was employed to capture structural features of the interaction network from literature data, and was found to improve in silico predicting performances to classify synergistic interactions. Furthermore, in vitro antibacterial assay against a standard strain of Staphylococcus aureus revealed that four essential oil pairs (Origanum compactum-Trachyspermum ammi, Cymbopogon citratus-Thujopsis dolabrata, Cinnamomum verum-Cymbopogon citratus and Trachyspermum ammi-Zingiber officinale) exhibited synergistic interaction as predicted. These results indicate that graph embedding approach can efficiently find synergistic interactions between antibacterial essential oils.

Virtual screening of antimicrobial plant extracts by machine-learning classification of chemical compounds in semantic space.

Plant extract is a mixture of diverse phytochemicals, and considered as an important resource for drug discovery. However, large-scale exploration of the bioactive extracts has been hindered by various obstacles until now. In this research, we have introduced and evaluated a new computational screening strategy that classifies bioactive compounds and plants in semantic space generated by word embedding algorithm. The classifier showed good performance in binary (presence/absence of bioactivity) classification for both compounds and plant genera. Furthermore, the strategy led to the discovery of antimicrobial activity of essential oils from Lindera triloba and Cinnamomum sieboldii against Staphylococcus aureus. The results of this study indicate that machine-learning classification in semantic space can be a highly efficient approach for exploring bioactive plant extracts.