Bacterial biofilm plays a pivotal role in chronic Staphylococcus aureus (S. aureus) infection and its inhibition may represent an important strategy to develop novel therapeutic agents. The scientific community is continuously searching for natural and “green alternatives” to chemotherapeutic drugs, including essential oils (EOs), assuming the latter not able to select resistant strains, likely due to their multicomponent nature and, hence, multitarget action. Here it is reported the biofilm production modulation exerted by 61 EOs, also investigated for their antibacterial activity on S. aureus strains, including reference and cystic fibrosis patients’ isolated strains. The EOs biofilm modulation was assessed by Christensen method on five S. aureus strains. Chemical composition, investigated by GC/MS analysis, of the tested EOs allowed a correlation between biofilm modulation potency and putative active components by means of machine learning algorithms application. Some EOs inhibited biofilm growth at 1.00% concentration, although lower concentrations revealed different biological profile. Experimental data led to select antibiofilm EOs based on their ability to inhibit S. aureus biofilm growth, which were characterized for their ability to alter the biofilm organization by means of SEM studies.

Previous studies relating to prolonged and fractionated distillation procedures highlighted essential oils’ (EOs) chemical composition to be significantly dependent on the extraction duration and harvesting time. As a continuation, a hydrodistillation procedure was applied to ripe fruit material of fennel, Foeniculum vulgare Miller (Apiaceae), collected from three localities in Montenegro (Podgorica, Nikšić, and Kotor) to furnish a total of 12 EOs. Liquid and vapor phases of the samples were analyzed by Gas Chromatography/Mass Spectrometry and Headspace-Gas Chromatography/Mass Spectrometry techniques, and 18 compounds have been identified. Although both quantitative and qualitative differences between the samples were notable, the phenylpropanoids anethole (ANE) and estragole and the monoterpenoids α-terpineol (TER) and fenchone (FEN) could be singled out as the most abundant constituents. The EOs from Podgorica belong to the most common ANE-rich chemotype, while the predominance of the monoterpenoid fraction is characteristic of the samples from Nikšić and Kotor. The latter is particularly rich in TER (up to 56.5%), with significant amounts of FEN and ANE. This chemical profile could represent a new chemotype of fennel EO. Vapor phases contained mainly monoterpenoids, with increased amounts of FEN and TER, while the number of phenylpropanoids was significantly decreased.

Scientific investigation on essential oils composition and the related biological profile are continuously growing. Nevertheless, only a few studies have been performed on the relationships between chemical composition and biological data. Herein, the investigation of 61 assayed essential oils is reported focusing on their inhibition activity against Microsporum spp. including development of machine learning models with the aim of highlining the possible chemical components mainly related to the inhibitory potency. The application of machine learning and deep learning techniques for predictive and descriptive purposes have been applied successfully to many fields. Quantitative composition–activity relationships machine learning-based models were developed for the 61 essential oils tested as Microsporum spp. growth modulators. The models were built with in-house python scripts implementing data augmentation with the purpose of having a smoother flow between essential oils’ chemical compositions and biological data. High statistical coefficient values (Accuracy, Matthews correlation coefficient and F₁ score) were obtained and model inspection permitted to detect possible specific roles related to some components of essential oils’ constituents. Robust machine learning models are far more useful tools to reveal data augmentation in comparison with raw data derived models. To the best of the authors knowledge this is the first report using data augmentation to highlight the role of complex mixture components, in particular a first application of these data will be for the development of ingredients in the dermo-cosmetic field investigating microbial species considering the urge for the use of natural preserving and acting antimicrobial agents.