Fruit Disease Research Articles

DINOV2-FCS: a model for fruit leaf disease classification and severity prediction

IntroductionThe assessment of the severity of fruit disease is crucial for the optimization of fruit production. By quantifying the percentage of leaf disease, an effective approach to determining the severity of the disease is available. However, the current prediction of disease degree by machine learning methods still faces challenges, including suboptimal accuracy and limited generalizability.MethodsIn light of the growing application of large model technology across a range of fields, this study draws upon the DINOV2 visual large vision model backbone network to construct the DINOV2-Fruit Leaf Classification and Segmentation Model (DINOV2-FCS), a model designed for the classification and severity prediction of diverse fruit leaf diseases. DINOV2-FCS employs the DINOv2-B (distilled) backbone feature extraction network to enhance the extraction of features from fruit disease leaf images. In fruit leaf disease classification, for the problem that leaf spots of different diseases have great similarity, we have proposed Class-Patch Feature Fusion Module (C-PFFM), which integrates the local detailed feature information of the spots and the global feature information of the class markers. For the problem that the model ignores the fine spots in the segmentation process, we propose Explicit Feature Fusion Architecture (EFFA) and Alterable Kernel Atrous Spatial Pyramid Pooling (AKASPP), which improve the segmentation effect of the model.ResultsTo verify the accuracy and generalizability of the model, two sets of experiments were conducted. First, the labeled leaf disease dataset of five fruits was randomly divided. The trained model exhibited an accuracy of 99.67% in disease classification, an mIoU of 90.29%, and an accuracy of 95.68% in disease severity classification. In the generalizability experiment, four disease data sets were used for training and one for testing. The mIoU of the trained model reached 83.95%, and the accuracy of disease severity grading was 95.24%.DiscussionThe results demonstrate that the model exhibits superior performance compared to other state-of-the-art models and that the model has strong generalization capabilities. This study provides a new method for leaf disease classification and leaf disease severity prediction for a variety of fruits. Code is available at https://github.com/BaiChunhui2001/DINOV2-FCS.

Plum pox virus: An overview of the potyvirus behind sharka, a harmful stone fruit disease

Plum pox virus: An overview of the potyvirus behind sharka, a harmful stone fruit disease

Chickpea NCR13 disulfide cross-linking variants exhibit profound differences in antifungal activity and modes of action.

Small cysteine-rich antifungal peptides with multi-site modes of action (MoA) have potential for development as biofungicides. In particular, legumes of the inverted-repeat lacking clade express a large family of nodule-specific cysteine-rich (NCR) peptides that orchestrate differentiation of nitrogen-fixing bacteria into bacteroids. These NCRs can form 2 or 3 intramolecular disulfide bonds and a subset of these peptides with high cationicity exhibits antifungal activity. However, the importance of intramolecular disulfide pairing and MoA against fungal pathogens for most of these plant peptides remains to be elucidated. Our study focused on a highly cationic chickpea NCR13, which has a net charge of +8 and contains six cysteines capable of forming three disulfide bonds. NCR13 expression in Pichia pastoris resulted in formation of two peptide folding variants, NCR13_PFV1 and NCR13_PFV2, that differed in the pairing of two out of three disulfide bonds despite having an identical amino acid sequence. The NMR structure of each PFV revealed a unique three-dimensional fold with the PFV1 structure being more compact but less dynamic. Surprisingly, PFV1 and PFV2 differed profoundly in the potency of antifungal activity against several fungal plant pathogens and their multi-faceted MoA. PFV1 showed significantly faster fungal cell-permeabilizing and cell entry capabilities as well as greater stability once inside the fungal cells. Additionally, PFV1 was more effective in binding fungal ribosomal RNA and inhibiting protein translation in vitro. Furthermore, when sprayed on pepper and tomato plants, PFV1 was more effective in reducing disease symptoms caused by Botrytis cinerea, causal agent of gray mold disease in fruits, vegetables and flowers. In conclusion, our work highlights the significant impact of disulfide pairing on the antifungal activity and MoA of NCR13 and provides a structural framework for design of novel, potent antifungal peptides for agricultural use.

VOZ‐dependent priming of salicylic acid‐dependent defense against Rhizopus stolonifer by β‐aminobutyric acid requires the TCP protein TCP2 in peach fruit

SUMMARYVascular plant one‐zinc finger (VOZ) transcription factors (TFs) play crucial roles in plant immunity. Nevertheless, how VOZs modulate defense signaling in response to elicitor‐induced resistance is not fully understood. Here, the defense elicitor β‐aminobutyric acid (BABA) resulted in the visible suppression of Rhizopus rot disease of peach fruit caused by Rhizopus stolonifer. Defense priming by BABA was notably associated with increased levels of salicylic acid (SA) and SA‐dependent gene expression. Data‐independent acquisition proteomic analysis revealed that two VOZ proteins (PpVOZ1 and PpVOZ2) were substantially upregulated in BABA‐induced resistance (BABA‐IR). Furthermore, the interaction of PpVOZ1 and PpVOZ2 and their potential target of the TEOSINTE‐BRANCHED1/CYCLOIDEA/PCF (TCP)‐family protein PpTCP2 screened from protein–protein interaction networks was confirmed by yeast two‐hybrid (Y2H), luciferase complementation imaging and glutathione S‐transferase pull‐down assays. Furthermore, subcellular localization, yeast one‐hybrid, electrophoretic mobility shift assay and dual‐luciferase reporter assays demonstrated that nuclear localization of both PpVOZ1 and PpVOZ2 was critical for their contribution to BABA‐IR, as these proteins potentiated the PpTCP2‐mediated transcriptional activation of isochorismate synthase genes (ICS1/2). The overexpression of both PpVOZ1 and PpVOZ2 could activate the transcription of SA‐dependent genes and provide disease resistance in transgenic Arabidopsis. In contrast, the ppvoz1cas9 and ppvoz2cas9 loss‐of‐function mutations and the voz1cas9 voz2cas9 double mutation attenuated BABA‐IR against R. stolonifer. Therefore, the three identified positive TFs, PpVOZ1, PpVOZ2, and PpTCP2, synergistically contribute to the BABA‐activated priming of systemic acquired resistance in postharvest peach fruit by a VOZ‐TCP‐ICS regulatory module.

Postharvest Immersion in Slightly Acidic Electrolyzed Water Improves Guava Storability by Regulating Phenylpropane Metabolism.

Postharvest guava fruit are at high risk of decay and spoilage, which extremely restrains the further advancement of guava industry in China. Currently, slightly acidic electrolyzed water (SAEW) has been shown to be potent in maintaining the storability of fruits and vegetables. Accordingly, this work was designed to figure out the effectiveness of SAEW on storability maintenance in postharvest guavas via regulating the phenylpropane metabolism. On the harvest day, fresh guavas were immersed in distilled water or SAEW (available chlorine concentration: 30 mg L-1) for 10 min, followed by storage for 15 d (25 °C, 80% RH). Results showed that, in comparation with the control guavas, SAEW-treated guavas exhibited lower levels of fruit disease index, malondialdehyde, and cell membrane permeability, while showing higher levels of fruit firmness and commercially acceptable fruit rate, as evidenced by enhanced contents of titratable acid, total soluble solids, vitamin C, total soluble sugar, and reducing sugar. Moreover, SAEW treatment improved the activities of disease-resistance enzymes and the contents of sinapic acid, p-coumaric acid, ferulic acid, caffeic acid, and lignin. The above data revealed that SAEW treatment-enhanced storability of guavas was attributed to the increased disease-resistance enzyme activities and disease-resistance substance contents, which improved the fruit disease resistance and slowed down the disease occurrence.

Impact of GRAS compounds applied by ultrasonic nebulization on decay control and quality parameters in Persian lime.

The application of generally recognized as safe (GRAS) substances for postharvest fungal control of fruit is an alternative to the conventional use of synthetic fungicides. In this study, two GRAS compounds were applied by ultrasonic nebulization (USN) to lime fruit for the control of Penicillium italicum, the cause of blue mold. Lime fruits were treated with sodium bicarbonate (1, 2, 3% w/v), acetic acid (0.5, 1, 1.5% w/v) and sterile distilled water by USN for 5, 10-15min. The effect of the USN treatments was evaluated in vitro, selecting the agent with the best effect. In vivo, the incidence and severity of blue mold disease and lime fruit quality parameters were evaluated. Although sodium bicarbonate inhibited P. italicum in vitro tests, USN treatments with acetic acid significantly inhibited 75.4% of mycelial growth and 100% of P. italicum germination. USN treatments (1% and 1.5% acetic acid) reduced disease incidence and severity (preventive and curative tests) on fruit stored at 25°C; however, at 15°C there was no significant difference with respect to USN of sterile distilled water. Lime quality parameters were not adversely affected by USN treatments with acetic acid. The application of 1 or 1.5% acetic acid by USN appears to be a promising option for the control of blue mold disease in Persian lime fruits.

Functionalized chalcogenide thin films for early detection of plant diseases via spore detection

This study investigates the functionalization of Ge-Se-Te chalcogenide thin films using various organosilane precursors, including TEOS, OTES, APTES, ImPTES and MPTMS, to render them more hydrophilic or hydrophobic, or impart surface charges. The integrity of the deposited hybrid layers was confirmed by proton Nuclear Magnetic Resonance spectroscopy after alkaline depolymerization of test samples. The modified surfaces were characterized by Water Contact Angle measurements, Scanning Electron Microscopy and Atomic Force Microscopy. The ability of these functionalized surfaces to immobilize individual or mixed spores of two different varieties, Venturia inaequalis and Penicillium expansum, both responsible for fruit tree diseases, was evaluated. The two spore varieties behaved similarly, whether alone or mixed. Neither spore variety adhered to very hydrophilic surfaces. While the percentage of immobilized Venturia inaequalis spores increased with the surface hydrophobicity, Penicillium expansum spores were not immobilized on highly hydrophobic surfaces. Venturia inaequalis spores, characterized by a very negative zeta potential, were very well immobilized on positively charged surfaces. Consequently, the best immobilization percentage for this spore variety was obtained for the surface functionalized with ImPTES, a precursor characterized by a stable positive charge of imidazolium group. Penicillium expansum spores were less sensitive to positive charges due to their less negative zeta potential. The highest immobilization percentage for this spore variety was obtained with the precursor TEOS. One explanation could be the formation of hydrogen bonds.

Antifungal efficacy and biofumigation potential of hydrophobic deep eutectic solvents: Postharvest treatment against Monilinia fructicola and Botrytis Cinerea.

Hydrophobic Deep Eutectic Solvents (HDES), as a subclass of Natural Deep Eutectic Solvents (NADES), present a green-chemistry alternative to toxic chemicals. As HDES are based on terpenoids, these solvents could potentially be effective antifungal agents against phytopathogens Monilinia fructicola and Botrytis cinerea that frequently cause diseases in sweet cherry fruit. To contribute to the disease prevention and management goals, as a part of this study, 30 different HDES were tested in the vapor phase, at identical concentrations of 25%, 50%, and 100%. In vitro experiments were conducted on Potato Dextrose Agar medium (PDA), while in planta experiments were carried out in hermetically sealed containers with inoculated sweet cherry fruits. All tested HDES demonstrated efficacy in suppressing the growth of M. fructicola colonies (66 - 100%) and B. cinerea colonies (37 - 100%). According to the Area Under the Disease Progress Curve (AUDPC), all HDES exhibited high efficacy in preventing disease occurrence in cherry fruits by the tested phytopathogens. This research provides the first insights into the antifungal potential of HDES in the vapor phase, with promising applications as biofumigants that minimize harmful impacts on the food - human - environment complex.

Effects of Perillaldehyde and Polyamines on Defense Mechanisms of Sweet Potatoes against Ceratocystis fimbriata.

Sweet potato (Ipomoea batatas) serves as a significant food and economic crop worldwide. However, its production and safety are jeopardized by black rot, a disease caused by Ceratocystis fimbriata. Although polyamines (PAs) are common biological growth factors, their function in the storage of fruits and vegetables remains poorly understood. This study examines the physiological roles of both exogenous and endogenous PAs in C. fimbriata, particularly their metabolism via gene knockout techniques. Additionally, we assessed how exogenous PAs affect sweet potato storage resistance. Our findings reveal that PAs are crucial in managing oxidative and cell wall stress in C. fimbriata. At high concentrations, PAs displayed cytotoxic effects through the upregulation of nitric oxide synthase (TAH18). Furthermore, exogenous PAs significantly enhanced the defense mechanisms of sweet potatoes during storage. The concurrent use of perillaldehyde (PAE), a natural antibacterial compound, additionally decreased the incidence of black rot in sweet potatoes. This study provides a novel strategy and theoretical basis for the prevention and control of fungal diseases in stored fruits and vegetables.

Mold in, mold out: Harvest bins harbor viable inoculum that can be reduced using novel sanitation methods to manage blue mold decay of apples

Postharvest diseases account for major economic losses worldwide, while also contributing to food waste and loss. Blue mold, caused by Penicillium expansum, is one of the most prevalent postharvest diseases of pome fruit. This necrotrophic fungal pathogen is mycotoxigenic and presents a danger to food safety via the production of patulin. In addition, fungicide resistance threatens blue mold management strategies, creating a need for the development of novel control strategies. The apple storage/processing industry uses wood and plastic harvest bins to harvest and store apples for weeks, months, and even up to 1 year. Although it has been hypothesized that apple harvest bins can serve as a viable inoculum source to incite decay, there is no experimental evidence that has conclusively demonstrated this concept. In this study, we report the presence of Penicillium spp. in apple storage bins (plastic) in the mid-Atlantic USA and developed small scale methods to test 1) if harvest bins can serve as a source of inoculum for blue mold decay and 2) evaluate novel bin sanitation methods as preventative and curative applications. We demonstrated that apple harvest bin materials can serve as a source of inoculum when in direct contact with wounded apples. Additionally, it was shown that UV-C irradiation, sodium hypochlorite, and 2-phenylethanol effectively reduce inoculum viability on plastic materials in a curative fashion. It is envisioned that these findings can aid in the development of large-scale bin sanitation strategies and their applications have great potential to impact a broader range of postharvest pathogens and stored commodities.

Performance Analysis of Various Deep Transfer Learning Models for Bacterial Blight Disease Detection and Classification in Pomegranate Fruits

Background: Detecting and classifying diseases in pomegranate fruit using computer vision remains a challenging task due to the presence of numerous diseases. Recent research findings suggest that models based on Convolutional Neural Networks (CNNs) have shown significant enhancements in accuracy when it comes to classifying images of fruits and leaves. The fungal infection responsible for the disease swiftly propagates through the soil, infiltrating the roots of pomegranate plants. Presently, the sole method to halt its spread entails farmers conducting thorough inspections and promptly eliminating infected plants, an uphill task. Methods: The present study introduces a classification PomeNetV1 model for identifying pomegranate fruit diseases employing CNN and transfer learning techniques. For executing this system, the dataset is created by taking the images directly from the farms in Ballari, Bengaluru, Bagalakote, etc. The proposed pomegranate fruit disease dataset contains 5099 images of five categories: Alternaria, Anthracnose, Bacterial Blight, Cercospora and Healthy. The system under consideration utilizes TensorFlow as its framework for developing deep learning models. Result: This paper evaluates ten different pre-trained models using a transfer learning approach and a proposed novel PomeNetV1 model for classification. All pre-trained models achieved over 99% classification accuracy. However, the PomeNetV1 model stands out with an impressive 99.80% accuracy, making it the most efficient for detecting healthy and bacterial blight diseases compared to others. Surpassing existing models like Vasumathi et al., 2021 deep CNN model with at least 1.63% accuracy, the PomeNetV1 model offers a feasible solution for detecting bacterial blight in pomegranate crops.

Nitric oxide-mediated PpRAP2.2 regulates the transcription of PpRbohA/D to enhance resistance to Monilinia fructicola in peach fruit

Nitric oxide (NO), a critical signaling molecule, plays key roles in plant cell physiological processes, particularly in redox system. To investigate the resistance of exogenous NO to brown rot (Monilinia fructicola) in peach fruit during storage, postharvest peaches were treated with NO and c-PTIO (an NO scavenger), exploring the mechanism of NO enhancing disease resistance in peach fruit through reactive oxygen species (ROS) metabolism. The results indicated that NO significantly inhibited brown rot in postharvest peach fruit, evidenced by reduced disease incidence and smaller lesion diameters. Additionally, exogenous NO treatment decreased the expression of respiratory burst oxidase homologs (PpRbohs), which is a crucial factor in ROS metabolism. The transcription factor PpRAP2.2 was identified through yeast one-hybrid (Y1H) screening with the promoter of PpRbohD. The expression pattern of PpRAP2.2 was closely associated with superoxide anion (O2-) content and peach fruit disease resistance. PpRAP2.2, a nuclear-localized transcription factor, activated the expression of PpRbohA and PpRbohD by directly binding to their promoter. The virus-induced gene silencing (VIGS) assay showed that silencing of PpRAP2.2 facilitated peach disease resistance by reducing the transcription of PpRbohA and PpRbohD. Furthermore, the overexpression of PpRAP2.2 resulted in a significant reduction in disease incidence and conidiophores in transgenic tomatoes relative to control group under M. fructicola, suggesting that PpRAP2.2 effectively enhanced the resistance of tomatoes to M. fructicola. These results indicate that PpRAP2.2 enhances NO-mediated disease resistance in peach by regulating the expression of PpRbohA and PpRbohD. These finding provide a basis for further studies on function and regulatory mechanisms of peach fruit disease resistance.

A botanical nanoemulsion against phytopathogenic fungi Colletotrichum sp. and Fusarium oxysporum: Preparation, in vitro and in vivo bioassay

A botanical nanoemulsion (NE) comprised of cinnamaldehyde (from Cinnamomum cassia oil) and annonaceous acetogenin (AAs) (from Annona squamocin seeds extract) was fabricated using sonication. The nanoemulsion was tested for their in vitro and in vivo antifungal activity against Colletotrichum sp. and Fusarium oxysporum the disease-causal agents in fruit and vegetable crops. The best average of nanoemulsion hydrodynamic diameter was 245.3 nm, and the polydispersity index (PI) was 0.499 based on DLS measurement. Zeta potential of the nanoemulsion was determined to be −44.2 mV, indicating the stability of the droplets. In vitro antifungal bioassay of the nanoemulsion showed the best inhibition against Colletotrichum sp. by 53.9 % when tested at a dilution rate of 1:100 (v/v). For F. oxysporum, the nanomaterial also inhibited mycelial growth by 91.6 % at the same dilution rate. When tested at dilution rates of 1:200 and 1:400 (v/v), the nanoemulsions caused moderate and weak inhibitions from 30.9 % to 52.8 % for all fungi. In vivo experiment, the nano-emulsion at 1:200 (v/v) dilution demonstrated an antifungal efficacy of 57.1 % (after 4 days) and 49.6 % (after 7 days) of testing. Besides, the mechanism of action has also been elucidated through molecular interaction models between the main compounds with eburicol 14α-demethylase. Our research indicates that botanical nanoemulsion containing cinnamon oil and AAs have a remarkable potential to suppress phytopathogenic fungi and prevent the spread of fungal diseases in tropical fruits and vegetables such as tomato and other crops of Solanaceae family.

Domain‐independent adaptive histogram‐based features for pomegranate fruit and leaf diseases classification

AbstractDisease identification for fruits and leaves in the field of agriculture is important for estimating production, crop yield, and earnings for farmers. In the specific case of pomegranates, this is challenging because of the wide range of possible diseases and their effects on the plant and the crop. This study presents an adaptive histogram‐based method for solving this problem. Our method describe is domain independent in the sense that it can be easily and efficiently adapted to other similar smart agriculture tasks. The approach explores colour spaces, namely, Red, Green, and Blue along with Grey. The histograms of colour spaces and grey space are analysed based on the notion that as the disease changes, the colour also changes. The proximity between the histograms of grey images with individual colour spaces is estimated to find the closeness of images. Since the grey image is the average of colour spaces (R, G, and B), it can be considered a reference image. For estimating the distance between grey and colour spaces, the proposed approach uses a Chi‐Square distance measure. Further, the method uses an Artificial Neural Network for classification. The effectiveness of our approach is demonstrated by testing on a dataset of fruit and leaf images affected by different diseases. The results show that the method outperforms existing techniques in terms of average classification rate.

Antimicrobial, Antifungal, and Insecticidal Activities of Scolymus Grandiflorus Essential Oil Rich in Davanoid Compounds

Background: This study explores the antimicrobial, antifungal, and insecticidal properties of Scolymus grandiflorus essential oil, examining its potential uses in the fields of pharmacology and agriculture. Materials and Methods: The essential oil obtained by hydrodistillation was studied by GC and GC/MS. The antibacterial capacity of the essential oil was determined against two Gram-positive and three Gram-negative bacterial species. The antifungal activity of the essential oil was investigated against two fungi responsible for many fruit and vegetable diseases. The insecticidal activity of essential oil was evaluated against larvae, pupae, and adult flies of Ceratitis capitata. Results: The GC and GC-MS analysis of the essential oil of the roots of S. grandiflorus revealed the predominant presence of davanoids, representing more than 80% of its chemical composition. The results of the disc diffusion test showed significant antimicrobial activity. The essential oil inhibited the growth of Salmonella typhi (25 mm), Staphylocoque aureus (18 mm), and Escherichia coli (17 mm), with inhibition diameters comparable to those of gentamicin. The essential oil significantly inhibited mycelial growth, with up to 98% inhibition for Fusarium solani and 73% for Alternaria alternata at 8 μL/mL. Insecticidal activity was most pronounced on adult flies, followed by pupae and finally larvae. Conclusion: Tests on the essential oils of S. grandiflorus revealed promising characteristics as insecticidal, antifungal, and antimicrobial agents. These results could be used in the development of new solutions to control pathogens responsible for plant diseases and mycotoxin-producing organisms.

Cleaved Amplified Polymorphic Sequence Markers in Horticultural Crops: Current Status and Future Perspectives

DNA markers have broad applications, including marker-assisted selection (MAS) for breeding new cultivars. Currently, single nucleotide polymorphisms (SNPs) have become a preferred choice of markers for molecular geneticists and breeders. They offer many advantages, such as high abundance and coverage in the genome, codominant inheritance, locus specificity, and flexibility for high-throughput genotyping/detection formats, and they are relatively inexpensive. The availability of reference genome sequences enables precise identification of candidate genes and SNPs associated with a trait of interest through quantitative trait loci (QTL) mapping and genome-wide association studies (GWAS). Such SNPs can be converted into markers for their application in MAS in crop breeding programs. Cleaved amplified polymorphic sequence (CAPS) markers amplify short genomic sequences around the polymorphic endonuclease restriction site. This review provides insight into the recent advancements made in the development and application of CAPS markers in several horticultural plants. We discussed many new tools that aid faster and more accurate design of CAPS markers from the whole genome resequencing (WGRS) data. The developed CAPS markers offer immense application in germplasm screening and field trials, genomic loci mapping, identifying candidate genes, and MAS of important horticultural traits such as disease resistance, fruit quality and morphology, and genetic purity.

Effects of Ambient pH on the Growth and Development, Pathogenicity, and Diacetoxyscirpenol Accumulation of Muskmelon Fruit Caused by Fusarium sulphureum.

Ambient pH, an important environmental factor, affects the growth, pathogenicity, and mycotoxin production of pathogenic fungus. Fusarium sulphureum is one of the predominant causal agents causing fusarium rot of muskmelon. In this study, we investigated the effects of ambient pH on fusarium rot development and diacetoxyscirpenol (DAS) accumulation in muskmelon infected with F. sulphureum, then analyzed the possible mechanisms in vitro and in vivo. The results suggested that ambient pH 6 was more conducive to the growth, pathogenicity, and mycotoxin production of F. sulphureum in vitro. Ambient pH 6 was also more favorable for secretion of cell wall-degrading enzymes for the pathogen to degrade the cell wall of the host plant and up-regulated the relative expression of genes involved in DAS biosynthesis, thus aggravating fruit disease and DAS accumulation. However, when the pH of the inoculated spore suspension was too acidic or too alkaline, the opposite results were observed.

A deep learning approach to detect diseases in pomegranate fruits via hybrid optimal attention capsule network

In 2022, the production rate of pomegranate is estimated at approximately 4.8 million metric tons. Unfortunately, these fruits are susceptible to many different kinds of diseases caused by bacterial, viral, and fungal infections. Such diseases can have a major negative impact on fruit quality, production, and the profitability of pomegranate cultivation. Nowadays, several machine learning and deep learning methods are used to identify pomegranate fruit diseases automatically and effectively. In post-harvest pomegranate fruit disease detection, deep learning has great potential to extract complex patterns and features from large datasets. This can improve disease identification accuracy, enabling more efficient disease control, lower crop losses, and better resource management. The proposed work introduces an intelligent deep learning-based approach for accurately detecting pomegranate diseases, begins with Improved Guided Image Filtering (Improved GIF) and resizing to pre-process fruit images, followed by feature extraction (shape, color, texture) using GLCM and GLRLM to streamline classification. Extracted features are then fed into a novel Hybrid Optimal Attention Capsule Network (Hybrid OACapsNet), which classifies the images as normal or diseased, conditions such as bacterial blight, heart rot, and scab. Our analysis indicates that the proposed classifier has a classification accuracy of 99.19 %, precision of 98.45 %, recall of 98.41 %, F1-score of 98.43 %, and specificity of 99.45 % compared to other techniques. So this approach offers a, which is a feasible solution for automated detection of diseases in fruits, thereby benefiting farmers and supporting their farming operations.

Evaluation of Yield, Fruit Chemistry, and Firmness of Seven Strawberry (Fragaria ×ananassa) Cultivars in an Eastern North Carolina Greenhouse

The combination of increasing costs, climate change, and disease- and pest-related issues present large challenges for the strawberry (Fragaria ×ananassa) industry in the United States. This is especially true for the Southeast, where rain, frost, and a range of foliar, fruit, and soil-borne diseases are prevalent, leading to significant losses every year. Simultaneously, niche winter markets open the opportunity to extend the harvest season, leading to an industry push to use protected culture strawberry production. Tabletop soilless strawberry greenhouse production has the advantage of avoiding soilborne issues while at the same time mitigating weather-related impacts on strawberry yield and quality. The use of long-day cultivars, originally bred for the Central Coast region of California, is currently the industry standard because of desired winter yields. However, short-day cultivars bred for Florida production might also have the potential to produce in winter. In this study, we evaluated the growth, yield, fruit chemistry, and fruit firmness of seven strawberry cultivars that are commonly grown in protected culture in North Carolina: Albion, Brilliance, Camino Real, Fronteras, Monterey, Florida Sensation, and Sweet Charlie. Experiments were conducted in a randomized complete block design in a commercial tabletop greenhouse in eastern North Carolina over two growing seasons (2022–23 and 2023–24). Our results showed that Florida cultivars Brilliance and Florida Sensation produced more consistently yields in winter compared with long-day cultivars Albion and Monterey and produced similar yields over the entire season. ‘Brilliance’ especially showed high fruit firmness across both years, and high sweetness in one of the two years. Additionally, the short-day cultivar Fronteras showed high yields in early spring and could serve as a late-season crop for direct-to-consumer producers. Our study showed that ‘Brilliance’ and ‘Florida Sensation’ could be alternatives to ‘Albion’, and that ‘Monterey’ can be used to produce a winter crop in a soilless tabletop production system in the Southeast.

Pan-transcriptome analysis provide insights into resistance and fruit quality breeding of pear (Pyrus pyrifolia)

Pyrus pyrifolia, commonly known as sand pear, is a key economic fruit tree in temperate regions and possesses highly diverse germplasm resources for pear quality improvement. However, research on the relationship between resistance and fruit quality traits during the breeding of fruit species like pear is limited. Pan-transcriptomes effectively capture genetic information from coding regions and reflect variations in gene expression between individuals. Here, we constructed a pan-transcriptome composed of 506 samples from different tissues of sand pear, and explored the intrinsic relationships among phenotypes and the selection for disease resistance during improvement based on expression presence/absence variation (ePAVs). The pan-transcriptome contains 156,744 transcripts, among which the novel transcripts show significant enrichment in the defense response. Interestingly, disease resistance genes are highly expressed in landraces of pear but have been selected against during the improvement of this perennial tree species. We found that genetically diverse landraces can be divided into two subgroups and inferred that they have undergone different dispersal processes. Through co-expression network analysis, we confirmed that the formation of stone cells in pears, the deposition of fruit anthocyanins, and the ability to resist stress are interrelated. They are jointly regulated by several modules, and the expression of regulatory genes has a significant correlation. Moreover, we identified candidate genes such as HKL1 that may affect sugar content and are missing from the reference genome. Our study provides insights into the associations between complex fruit traits, while providing a database resource for pear disease resistance and fruit quality breeding.