RESUMO
Multispectral imaging, combined with stoichiometric values, was used to construct a prediction model to measure changes in dietary fiber (DF) content in Chinese cabbage leaves across different growth periods. Based on all the spectral bands (365-970 nm) and characteristic spectral bands (430, 880, 590, 490, 690 nm), eight quantitative prediction models were established using four machine learning algorithms, namely random forest (RF), backpropagation neural network, radial basis function, and multiple linear regression. Finally, a quantitative prediction model of RF learning algorithm is constructed based on all spectral bands, which has good prediction accuracy and model robustness, prediction performance with R2 of 0.9023, root mean square error (RMSE) of 2.7182 g/100 g, residual predictive deviation (RPD) of 3.1220 > 3.0. In summary, this model efficiently detects changes in DF content across different growth periods of Chinese cabbage, which offers technical support for vegetable sorting and grading in the field.
Assuntos
Algoritmos , Brassica , Redes Neurais de Computação , Verduras , Aprendizado de MáquinaRESUMO
Eggplant (Solanum melongena L.) is a highly nutritious and economically important vegetable crop. However, the fruit peel of eggplant often shows poor coloration owing to low-light intensity during cultivation, especially in the winter. The less-photosensitive varieties produce anthocyanin in low light or even dark conditions, making them valuable breeding materials. Nevertheless, genes responsible for anthocyanin biosynthesis in less-photosensitive eggplant varieties are not characterized. In this study, an EMS mutant, named purple in the dark (pind), was used to identify the key genes responsible for less-photosensitive coloration. Under natural conditions, the peel color and anthocyanin content in pind fruits were similar to that of wildtype '14-345'. The bagged pind fruits were light purple, whereas those of '14-345' were white; and the anthocyanin content in the pind fruit peel was significantly higher than that in '14-345'. Genetic analysis revealed that the less-photosensitive trait was controlled by a single dominant gene. The candidate gene was mapped on chromosome 10 in the region 7.72 Mb to 11.71 Mb. Thirty-five differentially expressed genes, including 12 structural genes, such as CHS, CHI, F3H, DFR, ANS, and UFGT, and three transcription factors MYB113, GL3, and TTG2, were identified in pind using RNA-seq. Four candidate genes EGP21875 (myb domain protein 113), EGP21950 (unknown protein), EGP21953 (CAAX amino-terminal protease family protein), and EGP21961 (CAAX amino-terminal protease family protein) were identified as putative genes associated with less-photosensitive anthocyanin biosynthesis in pind. These findings may clarify the molecular mechanisms underlying less-photosensitive anthocyanin biosynthesis in eggplant.