Metabolomics applications for plant-based foods origin tracing, cultivars identification and processing: Feasibility and future aspects.

Metabolomics, the systematic study of metabolites, is dedicated to a comprehensive analysis of all aspects of plant-based food research and plays a pivotal role in the nutritional composition and quality control of plant-based foods. The diverse chemical compositions of plant-based foods lead to variations in sensory characteristics and nutritional value. This review explores the application of the metabolomics method to plant-based food origin tracing, cultivar identification, and processing methods. It also addresses the challenges encountered and outlines future directions. Typically, when combined with other omics or techniques, synergistic and complementary information is uncovered, enhancing the classification and prediction capabilities of models. Future research should aim to evaluate all factors affecting food quality comprehensively, and this necessitates advanced research into influence mechanisms, metabolic pathways, and gene expression.

Metric learning for image-based flower cultivars identification.

BACKGROUND: The study of plant phenotype by deep learning has received increased interest in recent years, which impressive progress has been made in the fields of plant breeding. Deep learning extremely relies on a large amount of training data to extract and recognize target features in the field of plant phenotype classification and recognition tasks. However, for some flower cultivars identification tasks with a huge number of cultivars, it is difficult for traditional deep learning methods to achieve better recognition results with limited sample data. Thus, a method based on metric learning for flower cultivars identification is proposed to solve this problem. RESULTS: We added center loss to the classification network to make inter-class samples disperse and intra-class samples compact, the script of ResNet18, ResNet50, and DenseNet121 were used for feature extraction. To evaluate the effectiveness of the proposed method, a public dataset Oxford 102 Flowers dataset and two novel datasets constructed by us are chosen. For the method of joint supervision of center loss and L2-softmax loss, the test accuracy rate is 91.88%, 97.34%, and 99.82% across three datasets, respectively. Feature distribution observed by T-distributed stochastic neighbor embedding (T-SNE) verifies the effectiveness of the method presented above. CONCLUSIONS: An efficient metric learning method has been described for flower cultivars identification task, which not only provides high recognition rates but also makes the feature extracted from the recognition network interpretable. This study demonstrated that the proposed method provides new ideas for the application of a small amount of data in the field of identification, and has important reference significance for the flower cultivars identification research.

Genetic variability evaluation and cultivar identification of tetraploid annual ryegrass using SSR markers.

Annual ryegrass (Lolium multiflorum) is a widely used cool-season turf and forage grass with high productivity and ornamental characteristics. However, the abundant intra-cultivar genetic variability usually hampers the application of conventional techniques for cultivar identification. The objectives of this study were to: (1) describe an efficient strategy for identification of six tetraploid annual ryegrass cultivars and (2) investigate the genetic diversity based on SSR markers. A total of 242 reliable bands were obtained from 29 SSR primer pairs with an average of 8.3 bands for each primer pair and the average value of polymorphic information content (PIC) was 0.304. The result of analysis of molecular variance (AMOVA) revealed that 81.99% of the genetic variation occurred in within-cultivars and 18.01% among-cultivars. The principal coordinate analysis (PCoA) showed that the first two principal axes explain 8.57% (PC1) and 6.05% (PC2) of total variation, respectively. By using multi-bulk strategy based on different filtering thresholds, the results suggested that bands frequency of 40% could be used as a reliable standard for cultivar identification in annual ryegrass. Under this threshold, 12 SSR primer pairs (00-04A, 02-06G, 02-08C, 03-05A, 04-05B, 10-09E, 12-01A, 13-02H, 13-12D, 14-06F, 15-01C and 17-10D) were detected for direct identification of six tetraploid annual ryegrass cultivars, which could be incorporated into conservation schemes to protect the intellectual property of breeders, ensure purity for consumers, as well as guarantee effective use of cultivars in future.