Chilling injury is a physiological disorder caused by cold storage in peaches and nectarines. The main symptom of chilling injury is mealiness/wooliness, described as a lack of juice in fruit flesh. In this work, we studied two nectarine varieties (Andes Nec-2 and Andes Nec-3) with contrasting susceptibility to mealiness after cold storage. A non-targeted metabolomic analysis was conducted by GC-MS to understand if changes in metabolite abundance are associated with nectarine mealiness induced by cold storage. Multivariate analyses indicated that in unripe nectarines, cold storage promoted a higher accumulation of amino acids in both varieties. Interestingly, for ripe nectarines, cold storage induced an accumulation of fewer amino acids in both varieties and showed an increased abundance of sugars and organic acids. A pathway reconstruction of primary metabolism revealed that in ripe nectarines, cold storage disrupted metabolite abundance in sugar metabolism and the TCA cycle, leading to a differential accumulation of amino acids, organic acids, and sugars in mealy and juicy nectarines.

Little cherry disease (LChD), is one of the most important viral diseases of cherry worldwide. It is associated to two different viral species, Little cherry virus 1 (LChV-1) and Little cherry virus 2 (LChV-2). Productivity impact of LChD is reflected in the decrease in yield and fruit quality (Ruiz-Garcia et al. 2016). For LChV-1 (genus Velarivirus, family Closteroviridae) there is no known insect vector to date, thus, its presence worldwide is mainly associated to the propagation of infected plants. In 2015-2016, during southern hemisphere spring-summer vegetative season, a survey was carried out for virus and viroid detection in the main cherry producing regions in Chile. RT-PCR analyses did not show the presence of LChD-associated viruses using previously reported specific primer pairs (Rott and Jelkmann, 2001). Nineteen samples whose symptoms did not match with the detected viruses, were selected for NGS analyses. Small RNA extracts were prepared according to Giampetruzzi et al. (2012). Libraries wer...

Identifying blueberry characteristics such as the wax bloom is an important task that not only helps in phenotyping (for novel variety development) but also in classifying berries better suited for commercialization. Deep learning techniques for image analysis have long demonstrated their capability for solving image classification problems. However, they usually rely on large architectures that could be difficult to implement in the field due to high computational needs. This paper presents a small (only 1502 parameters) Bayesian–CNN ensemble architecture that can be implemented in any small electronic device and is able to classify wax bloom content in images. The Bayesian model was implemented using Keras image libraries and consists of only two convolutional layers (eight and four filters, respectively) and a dense layer. It includes a statistical module with two metrics that combines the results of the Bayesian ensemble to detect potential misclassifications. The first metric is based on the Euclidean distance (${\mathcal{L}}_2$) between Gaussian mixture models while the second metric is based on a quantile analysis of the binary class predictions. Both metrics attempt to establish whether the model was able to find a good prediction or not. Three experiments were performed: first, the Bayesian–CNN ensemble model was compared with state-of-the-art small architectures. In experiment 2, the metrics for detecting potential misclassifications were evaluated and compared with similar techniques derived from the literature. Experiment 3 reports results while using cross validation and compares performance considering the trade-off between accuracy and the number of samples considered as potentially misclassified (not classified). Both metrics show a competitive performance compared to the state of the art and are able to improve the accuracy of a Bayesian–CNN ensemble model from $96.98\%$ to $98.72\pm 0.54\%$ and $98.38\pm 0.34\%$ for the ${\mathcal{L}}_2$ and $r^2$ metrics, respectively.