Apple fruit quality is primarily determined by Vitamin C (VC), Soluble Saccharides (SSs), Titratable Acid (TA), and the Soluble Saccharides/Titratable Acid (SSs/TA). This study aims to establish a prediction model based on the Back Propagation (BP) neural network by analyzing the intrinsic relationships between these quality indicators and the photosynthetic physiological characteristics of fruit trees, providing a new method for the precise prediction and regulation of fruit quality. Using ‘Fuji’ apple as the material, fruit quality indicators, leaf photosynthetic parameters, canopy structure indicators, and carbon–water–nitrogen metabolism indicators were systematically measured. Correlation analysis was employed to identify key influencing factors, BP neural network models with different hidden layer structures were constructed, and the optimal feature subset was screened through feature importance analysis, single-factor sensitivity analysis, and ablation experiments, ultimately establishing a simplified and efficient prediction model. Pn, Gs, SPCI, and DUE showed significant positive correlations with VC, SS, and SS/TA, whereas N and NLT were significantly positively correlated with TA content. SUE was identified as a common core driving factor for VC, SS, and SS/TA. The BP neural network demonstrated strong predictive performance for the four quality indicators, with the optimal model achieving validation set R² values of 0.87, 0.86, 0.86, and 0.89, respectively. The simplified model developed through feature screening exhibited further improved performance: the validation set R² for the VC prediction model increased to 0.93, while MAE and MAPE decreased by 32% and 35%, respectively. Photosynthetic characteristics and nitrogen metabolism status of the fruit trees serve as key physiological foundations determining apple quality. The quality prediction model based on the BP neural network achieved high accuracy, and its predictive performance was significantly enhanced after feature refinement, providing an effective tool for precise apple quality prediction and smart orchard management.

Saline–alkali stress is an important environmental factor affecting the growth and development of plants. Plants affected by saline–alkali stress can mitigate the damage by regulating the content of osmoregulatory substances such as soluble sugars. Elucidating the regulatory mechanism of the changes in sugar fractions in jujube fruits under saline–alkali stress is crucial for the development of the jujube fruit industry in saline areas. In this study, we investigated the effects of saline–alkali stress on the development and sugar contents of jujube fruits by subjecting jujube trees to low- and high-saline–alkali stress treatments. The result showed that low saline–alkali stress increased the content of each sugar component and total sugar, whereas high saline–alkali stress suppressed their contents. In the early developmental stage, the fruit mainly accumulated fructose and glucose, whereas in the late stage, it accumulated mainly sucrose. We screened various genes, namely trehalose 6-phosphate phosphatase gene (LOC107418410), α-amylase gene (LOC107428855), α-glucosidase gene (LOC107418468), sucrose synthase gene (LOC107416188), and β-amylase gene (LOC107430415, LOC107406235), all of which were highly correlated with sucrose content in saline–alkali stress, indicating that the starch and sucrose metabolic pathways of jujube fruit are the key pathways regulating sugar accumulation in response to saline–alkali stress. To summarize, this study provides a system-level perspective on the dynamic transcriptional regulation of jujube fruits under saline–alkali stress. Additionally, the study preliminarily screened key differentially expressed genes that affect sugar accumulation in response to saline–alkali stress, providing a theoretical basis for the scientific regulation of jujube fruit quality.

Fruit size is a major factor determining yield, quality, and consumer acceptability. fw2.2 (fruit weight-2.2) is a primary quantitative trait locus that was the first to be cloned, accounting for 30% of the variation in tomato fruit size. The various homologs of fw2.2 (fw2.2-like) have been identified in many plants and belong to a large family. To date, there has been no report that has carried out a comprehensive identification of fw2.2-like members in pear. In this study, a total of 14 fw2.2-like genes were identified in the pear (Pyrus bretschneideri Rehd) genome and designated as PbFWL1-14. All of the PbFWL genes were unevenly distributed on nine chromosomes, and each chromosome contained between one and four genes. All PbFWL proteins contained more than two conserved motifs, and PbFWL genes contained more than one intron, and the genes of the same subfamily seemed to have a similar intron gene structure. According to the neighbor-joining phylogenetic tree, a total of 78 fw2.2/CNR (cell number regulator) from five plant species, including pear, maize, tomato, peach, rice, and physalis, could be divided into seven subgroups, and PbFWL proteins were mainly distributed in subgroups 1, 3, 4, 5, and 6. The Ka/Ks analysis also revealed that the fw2.2-like gene family of pear may have been subjected to strong purifying selection pressure during its evolution. A cis-element analysis found that many cis-elements responsive to hormones and stress were discovered in promotion regions for all PbFWLs. When combining real-time quantitative PCR analysis detection results, PbFWL1/2/5 were found to be the most likely candidate genes for regulating pear fruit size.

The fw2.2 (fruit weight 2.2) gene negatively regulates cell division and significantly influences fruit size, but its regulatory mechanisms in pears remain unclear. Here, we investigated how pear FWL (fw2.2-like) genes control cell division using Duli pear, Korla fragrant pear, and Yali pear. During the cell division phase, fluorescence in situ hybridization (FISH) revealed stronger expression of FWL1 and FWL5 in smaller fruits compared to larger ones, with both genes localized in the core and flesh tissues. Gene silencing experiments demonstrated that silencing of FWL5 leads to a significant increase in the number of cells, with a concomitant enlargement of the fruit. Yeast two-hybrid screening identified 147 proteins interacting with FWL5, showing substantial overlap with FWL1 interactors. Key candidates included metallothionein-like protein (MT) and Ole-e-1, with the latter displaying a positive correlation with fruit size during cell division. Bimolecular fluorescence complementation (BiFC) confirmed direct interactions between Ole-e-1 and both FWL1/FWL5. Functional analysis indicated the Ole-e-1 gene family has diverse roles in pear development. We propose that Ole-e-1 interacts with FWL genes to modulate cell division, thereby determining final fruit size. This study uncovers a novel regulatory axis linking cell cycle control and fruit size in pears.