Identification of Oil Tea (Camellia oleifera C.Abel) Cultivars Using EfficientNet-B4 CNN Model with Attention Mechanism

Cultivar identification is a basic task in oil tea (Camellia oleifera C.Abel) breeding, quality analysis, and an adjustment in the industrial structure. However, because the differences in texture, shape, and color under different cultivars of oil tea are usually inconspicuous and subtle, the identification of oil tea cultivars can be a significant challenge. The main goal of this study is to propose an automatic and accurate method for identifying oil tea cultivars. In this study, a new deep learning model is built, called EfficientNet-B4-CBAM, to identify oil tea cultivars. First, 4725 images containing four cultivars were collected to build an oil tea cultivar identification dataset. EfficientNet-B4 was selected as the basic model of oil tea cultivar identification, and the Convolutional Block Attention Module (CBAM) was integrated into EfficientNet-B4 to build EfficientNet-B4-CBAM, thereby improving the focusing ability of the fruit areas and the information expression capability of the fruit areas. Finally, the cultivar identification capability of EfficientNet-B4-CBAM was tested on the testing dataset and compared with InceptionV3, VGG16, ResNet50, EfficientNet-B4, and EfficientNet-B4-SE. The experiment results showed that the EfficientNet-B4-CBAM model achieves an overall accuracy of 97.02% and a kappa coefficient of 0.96, which is higher than that of other methods used in comparative experiments. In addition, gradient-weighted class activation mapping network visualization also showed that EfficientNet-B4-CBAM can pay more attention to the fruit areas that play a key role in cultivar identification. This study provides new effective strategies and a theoretical basis for the application of deep learning technology in the identification of oil tea cultivars and provides technical support for the automatic identification and non-destructive testing of oil tea cultivars.

Screening the Key Region of Sunlight Regulating the Flavonoid Profiles of Young Shoots in Tea Plants (Camellia sinensis L.) Based on a Field Experiment

Both UV and blue light have been reported to regulate the biosynthesis of flavonoids in tea plants; however, the respective contributions of the corresponding regions of sunlight are unclear. Additionally, different tea cultivars may respond differently to altered light conditions. We investigated the responses of different cultivars (‘Longjing 43’, ‘Zhongming 192’, ‘Wanghai 1’, ‘Jingning 1’ and ‘Zhonghuang 2’) to the shade treatments (black and colored nets) regarding the biosynthesis of flavonoids. For all cultivars, flavonol glycosides showed higher sensitivity to light conditions compared with catechins. The levels of total flavonol glycosides in the young shoots of different tea cultivars decreased with the shade percentages of polyethylene nets increasing from 70% to 95%. Myricetin glycosides and quercetin glycosides were more sensitive to light conditions than kaempferol glycosides. The principal component analysis (PCA) result indicated that shade treatment greatly impacted the profiles of flavonoids in different tea samples based on the cultivar characteristics. UV is the crucial region of sunlight enhancing flavonol glycoside biosynthesis in tea shoots, which is also slight impacted by light quality according to the results of the weighted correlation network analysis (WGCNA). This study clarified the contributions of different wavelength regions of sunlight in a field experiment, providing a potential direction for slightly bitter and astringent tea cultivar breeding and instructive guidance for practical field production of premium teas based on light regimes.

Haplotype-resolved genome assembly provides insights into evolutionary history of the tea plant Camellia sinensis

Tea is an important global beverage crop and is largely clonally propagated. Despite previous studies on the species, its genetic and evolutionary history deserves further research. Here, we present a haplotype-resolved assembly of an Oolong tea cultivar, Tieguanyin. Analysis of allele-specific expression suggests a potential mechanism in response to mutation load during long-term clonal propagation. Population genomic analysis using 190 Camellia accessions uncovered independent evolutionary histories and parallel domestication in two widely cultivated varieties, var. sinensis and var. assamica. It also revealed extensive intra- and interspecific introgressions contributing to genetic diversity in modern cultivars. Strong signatures of selection were associated with biosynthetic and metabolic pathways that contribute to flavor characteristics as well as genes likely involved in the Green Revolution in the tea industry. Our results offer genetic and molecular insights into the evolutionary history of Camellia sinensis and provide genomic resources to further facilitate gene editing to enhance desirable traits in tea crops.

Genetic basis of high aroma and stress tolerance in the oolong tea cultivar genome

Tea plants (Camellia sinensis) are commercially cultivated in >60 countries, and their fresh leaves are processed into tea, which is the most widely consumed beverage in the world. Although several chromosome-level tea plant genomes have been published, they collapsed the two haplotypes and ignored a large number of allelic variations that may underlie important biological functions in this species. Here, we present a phased chromosome-scale assembly for an elite oolong tea cultivar, “Huangdan”, that is well known for its high levels of aroma. Based on the two sets of haplotype genome data, we identified numerous genetic variations and a substantial proportion of allelic imbalance related to important traits, including aroma- and stress-related alleles. Comparative genomics revealed extensive structural variations as well as expansion of some gene families, such as terpene synthases (TPSs), that likely contribute to the high-aroma characteristics of the backbone parent, underlying the molecular basis for the biosynthesis of aroma-related chemicals in oolong tea. Our results uncovered the genetic basis of special features of this oolong tea cultivar, providing fundamental genomic resources to study evolution and domestication for the economically important tea crop.

Integrated Metabolome and Transcriptome Analyses Reveal Etiolation-Induced Metabolic Changes Leading to High Amino Acid Contents in a Light-Sensitive Japanese Albino Tea Cultivar

Plant albinism causes the etiolation of leaves because of factors such as deficiency of chloroplasts or chlorophylls. In general, albino tea leaves accumulate higher free amino acid (FAA) contents than do conventional green tea leaves. To explore the metabolic changes of etiolated leaves (EL) in the light-sensitive Japanese albino tea cultivar “Koganemidori,” we performed integrated metabolome and transcriptome analyses by comparing EL with green leaves induced by bud-sport mutation (BM) or shading treatments (S-EL). Comparative omics analyses indicated that etiolation-induced molecular responses were independent of the light environment and were largely influenced by the etiolation itself. Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment and pathway analyses revealed the downregulation of genes involved in chloroplast development and chlorophyll biosynthesis and upregulation of protein degradation-related pathways, such as the ubiquitin-proteasome system and autophagy in EL. Metabolome analysis showed that most quantified FAAs in EL were highly accumulated compared with those in BM and S-EL. Genes involved in the tricarboxylic acid (TCA) cycle, nitrogen assimilation, and the urea cycle, including the drastically downregulated Arginase-1 homolog, which functions in nitrogen excretion for recycling, showed lower expression levels in EL. The high FAA contents in EL might result from the increased FAA pool and nitrogen source contributed by protein degradation, low N consumption, and stagnation of the urea cycle rather than through enhanced amino acid biosynthesis.

Screening tea hybrid with abundant anthocyanins and investigating the effect of tea processing on foliar anthocyanins in tea

Anthocyanins are important bioactive supplements that are consumed from multiple foods and beverage products. Screening tea cultivars producing a high level of anthocyanins can help to enrich the edible bioactive supplements. ‘Zijuan’ (ZJ) is a tea cultivar growing purple shoots rich in anthocyanins, but it is susceptible to freezing winter and sprouts late in spring. Hybridisation using ‘ZJ’ as the female parent and an early sprouting cultivar ‘Wuniuzao’ as the male parent was carried out, and four hybrids with purple leaves were obtained. The quality of anthocyanins, catechins, caffeine and amino acids in shoots with three leaves and a bud of the purple leaf hybrids obtained were determined based on the field investigation on sprouting time in spring, winter resistance and leaf yield. It showed that hybrid ‘B-2’ sprouted earlier in the spring, contained a higher level of anthocyanins and also showed good performance in winter resistance than its female parent ‘ZJ’. It also showed that black tea processing induced a marked decrease in foliar anthocyanins, but green tea processing had little effect on the foliar anthocyanins. Purple tea leaves should be prepared into unfermented green tea instead of fermented black tea to preserve the high level of anthocyanins in the final tea products.