The quality of oranges is grounded on their appearance and diameter.  Appearance refers to the skin’s smoothness and surface cleanliness; diameter refers to the transverse diameter size.  They are visual attributes that visual perception technologies can automatically identify.  Nonetheless, the current orange quality assessment needs to address two issues: 1) There are no image datasets for orange quality grading; 2) It is challenging to effectively learn the fine-grained and distinct visual semantics of oranges from diverse angles.  This study collected 12 522 images from 2 087 oranges for multi-grained grading tasks.  In addition, it presented a visual learning graph convolution approach for multi-grained orange quality grading, including a backbone network and a graph convolutional network (GCN).  The backbone network’s object detection, data augmentation, and feature extraction can remove extraneous visual information.  GCN was utilized to learn the topological semantics of orange feature maps.  Finally, evaluation results proved that the recognition accuracy of diameter size, appearance, and fine-grained orange quality were 99.50, 97.27, and 97.99%, respectively, indicating that the proposed approach is superior to others.

   The glycoprotein 5 (GP5) of porcine reproductive and respiratory syndrome virus (PRRSV) is a multi-functional protein that plays important roles in virus assembly, entry and viral anti-host responses. In the present study, we investigated the cellular binding partners of GP5 by using lentivirus transduction coupled with immunoprecipitation and mass spectrometry. There were about 40 cellular proteins identified with high Confidence Icons by MS/MS. Ingenuity Pathway Analysis (IPA) indicated that these proteins could be assigned to different functional classes and networks. Furthermore, we validated some of the interactions by co-immunoprecipitation (Co-IP) and confocal microscopy, including those with mitofilin, a mitochondrial inner membrane protein that might be involved in PRRSV or GP5-induced apoptosis, and calnexin, a protein chaperone that might facilitate the folding and maturation of GP5. The interactome data contribute to understand the role and molecular mechanisms of GP5 in PRRSV pathogenesis.

SOM encodes a nucleus-localized CCCH-type zinc finger protein and negatively regulates seed germination in Arabidopsis thaliana. We have previously demonstrated that ectopic expression of SlABI3, an important transcription factor in abscisic acid (ABA) signaling pathway, resulted in alteration of SlSOM expression patterns in both leaf and seed of tomato. In this study, we aimed to elucidate the function of tomato SlSOM in regarding to seed germination and seedling development. Here, we constructed SlSOM over-expression vector pBI121-SOM driven by CaMV 35S promoter, and the recombinant plasmid was incorporated into wild-type tomato by the method of Agrobacterium tumefaciens-mediated transformation. The result showed that over-expression of SlSOM conferred enhanced responses to exogenous ABA application during seed germination and seedling development. In addition, ectopic expression of SlSOM resulted in the alteration of expression level of ABA/GA (gibberellins) metabolic genes, such as SlABA1, SlCYP707A1, SlGA3ox2, and SlGA2ox4, in both leaf and seed. The ABA anabolic gene SlABA1 and the GA catabolic gene SlGA2ox4 were up-regulated while the ABA catabolic gene SlCYP707A1 and the GA anabolic gene SlGA3ox2 were down-regulated. Compared to wild type, the expression level of SlABI5 was increased by about 40–50% in transgenic seeds while adding exogenous ABA treatment. These results support the notion that SlSOM inhibits seed germination by regulating ABA/GA metabolic genes and SlABI5 expression in Solanum lycopersicum.

The sense and antisense fragments of the soluble starch synthase (SSIII) gene and the intron fragment of somatic embryogenesis receptor-like kinase (SERK1) gene were cloned from potato using PCR techniques. The RNAi plant expression vectors pBI-SSIII-RNAi and pBIC-SSIII-RNAi were constructed which containing fusion fragment of “sense fragment-intron-antisense fragment” driven by the constitutive expression promoter CaMV 35S and the tuber-specific expression promoter CIPP, respectively. The putative transgenic plants of potato cultivars Kexin-1 and Kexin-4 were obtained using Agrobacterium-mediated transformation method. PCR assay showed that the interference fragment of SSIII gene was integrated into potato genome. The RT-PCR analysis showed that the expression of SSIII gene was repressed apparently on the transcription level. Starch granules of the transgenic potato plants were different in morphology and became cracked in starch granule centre compared with the non-transgenic control plants. The amylose content of starch was increased by 2.68-29.05%, amylopectin to amylose ratio of starch had declined significantly, and the phosphorus content of the starch of the transgenic plants was reduced 9.94-58.36% compared with control plants. The results could provide certain foundation for improvement of potato starch quality.