Honey bee classification by wing geometric morphometrics entails the first step of manual annotation of 19 landmarks in the forewing vein junctions. This is a time-consuming and error-prone endeavor, with implications for classification accuracy. Herein, we developed a software called DeepWings© that overcomes this constraint in wing geometric morphometrics classification by automatically detecting the 19 landmarks on digital images of the right forewing. We used a database containing 7634 forewing images, including 1864 analyzed by F. Ruttner in the original delineation of 26 honey bee subspecies, to tune a convolutional neural network as a wing detector, a deep learning U-Net as a landmarks segmenter, and a support vector machine as a subspecies classifier. The implemented MobileNet wing detector was able to achieve a mAP of 0.975 and the landmarks segmenter was able to detect the 19 landmarks with 91.8% accuracy, with an average positional precision of 0.943 resemblance to manually annotated landmarks. The subspecies classifier, in turn, presented an average accuracy of 86.6% for 26 subspecies and 95.8% for a subset of five important subspecies. The final implementation of the system showed good speed performance, requiring only 14 s to process 10 images. DeepWings© is very user-friendly and is the first fully automated software, offered as a free Web service, for honey bee classification from wing geometric morphometrics. DeepWings© can be used for honey bee breeding, conservation, and even scientific purposes as it provides the coordinates of the landmarks in excel format, facilitating the work of research teams using classical identification approaches and alternative analytical tools.

Aromatic plants are a remarkable source of natural products. Aloysia citrodora Paláu (Verbenaceae), commonly known as lemon verbena, is a relevant source of essential oils with potential applications due to its lemony scent and bioactive properties. Studies carried out on this species have focused on the volatile composition of the essential oil obtained by Clevenger hydrodistillation (CHD), with little information available on alternative extraction methodologies or the biological properties of the oil. Therefore, this work aimed to compare the volatile composition, antioxidant activity, cytotoxicity, anti-inflammatory and antibacterial activities of the essential oil extracted by conventional hydrodistillation by Clevenger (CHD) and Microwave-Assisted Hydrodistillation (MAHD). Significant differences (p < 0.05) were observed for some compounds, including the two major ones, geranial (18.7–21.1%) and neral (15.3–16.2%). Better antioxidant activity was exhibited by the MAHD essential oil in DPPH radical scavenging and reducing power assays, while no differences were observed in the cellular antioxidant assay. The MADH essential oil also presented higher inhibition against four tumoral cell lines and exhibited lower cytotoxicity in non-tumoral cells as compared with Clevenger-extracted essential oil. In contrast, the latter showed higher anti-inflammatory activity. Both essential oils were able to inhibit the growth of eleven out of the fifteen bacterial strains tested.

DeepWings© is a software that uses machine learning to automatically classify honey bee subspecies by wing geometric morphometrics. Here, we tested the five subspecies classifier (A. m. carnica, Apis mellifera caucasia, A. m. iberiensis, Apis mellifera ligustica, and A. m. mellifera) of DeepWings© on 14,816 wing images with variable quality and acquired by different beekeepers and researchers. These images represented 2601 colonies from the native ranges of the M-lineage A. m. iberiensis and A. m. mellifera, and the C-lineage A. m. carnica. In the A. m. iberiensis range, 92.6% of the colonies matched this subspecies, with a high median probability (0.919). In the Azores, where the Iberian subspecies was historically introduced, a lower proportion (85.7%) and probability (0.842) were observed. In the A. m mellifera range, only 41.1 % of the colonies matched this subspecies, which is compatible with a history of C-derived introgression. Yet, these colonies were classified with the highest probability (0.994) of the three subspecies. In the A. m. carnica range, 88.3% of the colonies matched this subspecies, with a probability of 0.984. The association between wing and molecular markers, assessed for 1214 colonies from the M-lineage range, was highly significant but not strong (r = 0.31, p < 0.0001). The agreement between the markers was influenced by C-derived introgression, with the best results obtained for colonies with high genetic integrity. This study indicates the good performance of DeepWings© on a realistic wing image dataset.

The honey bee (Apis mellifera) is an ecologically and economically important species that provides pollination services to natural and agricultural systems. The biodiversity of the honey bee in parts of its native range is endangered by migratory beekeeping and commercial breeding. In consequence, some honey bee populations that are well adapted to the local environment are threatened with extinction. A crucial step for the protection of honey bee biodiversity is reliable differentiation between native and nonnative bees. One of the methods that can be used for this is the geometric morphometrics of wings. This method is fast, is low cost, and does not require expensive equipment. Therefore, it can be easily used by both scientists and beekeepers. However, wing geometric morphometrics is challenging due to the lack of reference data that can be reliably used for comparisons between different geographic regions. Here, we provide an unprecedented collection of 26,481 honey bee wing images representing 1,725 samples from 13 European countries. The wing images are accompanied by the coordinates of 19 landmarks and the geographic coordinates of the sampling locations. We present an R script that describes the workflow for analyzing the data and identifying an unknown sample. We compared the data with available reference samples for lineage and found general agreement with them. The extensive collection of wing images available on the Zenodo website can be used to identify the geographic origin of unknown samples and therefore assist in the monitoring and conservation of honey bee biodiversity in Europe.