Transdermal microarrayed electroporation for enhanced cancer immunotherapy based on DNA vaccination.

Despite the tremendous clinical potential of nucleic acid-based vaccines, their efficacy to induce therapeutic immune response has been limited by the lack of efficient local gene delivery techniques in the human body. In this study, we develop a hydrogel-based organic electronic device (µEPO) for both transdermal delivery of nucleic acids and in vivo microarrayed cell electroporation, which is specifically oriented toward one-step transfection of DNAs in subcutaneous antigen-presenting cells (APCs) for cancer immunotherapy. The µEPO device contains an array of microneedle-shaped electrodes with pre-encapsulated dry DNAs. Upon a pressurized contact with skin tissue, the electrodes are rehydrated, electrically triggered to release DNAs, and then electroporate nearby cells, which can achieve in vivo transfection of more than 50% of the cells in the epidermal and upper dermal layer. As a proof-of-concept, the µEPO technique is employed to facilitate transdermal delivery of neoantigen genes to activate antigen-specific immune response for enhanced cancer immunotherapy based on a DNA vaccination strategy. In an ovalbumin (OVA) cancer vaccine model, we show that high-efficiency transdermal transfection of APCs with OVA-DNAs induces robust cellular and humoral immune responses, including antigen presentation and generation of IFN-γ+ cytotoxic T lymphocytes with a more than 10-fold dose sparing over existing intramuscular injection (IM) approach, and effectively inhibits tumor growth in rodent animals.

miR171-targeted SCARECROW-LIKE genes CsSCL2 and CsSCL3 regulate somatic embryogenesis in citrus.

Somatic embryogenesis (SE) is a key regeneration pathway in various biotechnology approaches to crop improvement, especially for economically important perennial woody crops like citrus. However, maintenance of SE capability has long been a challenge and becomes a bottleneck in biotechnology-facilitated plant improvement. In the embryogenic callus (EC) of citrus, we identified 2 csi-miR171c-targeted SCARECROW-LIKE genes CsSCL2 and CsSCL3 (CsSCL2/3), which exert positive feedback regulation on csi-miR171c expression. Suppression of CsSCL2 expression by RNA interference (RNAi) enhanced SE in citrus callus. A thioredoxin superfamily protein CsClot was identified as an interactive protein of CsSCL2/3. Overexpression of CsClot disturbed reactive oxygen species (ROS) homeostasis in EC and enhanced SE. Chromatin immunoprecipitation sequencing (ChIP-Seq) and RNA-Seq identified 660 genes directly suppressed by CsSCL2 that were enriched in biological processes including development-related processes, auxin signaling pathway, and cell wall organization. CsSCL2/3 bound to the promoters of regeneration-related genes, such as WUSCHEL-RELATED HOMEOBOX 2 (CsWOX2), CsWOX13, and Lateral Organ Boundaries Domain 40 (LBD40), and repressed their expression. Overall, CsSCL2/3 modulate ROS homeostasis through the interactive protein CsClot and directly suppress the expression of regeneration-related genes, thus regulating SE in citrus. We uncovered a regulatory pathway of miR171c-targeted CsSCL2/3 in SE, which shed light on the mechanism of SE and regeneration capability maintenance in citrus.

Efficient Defect Detection of Rotating Goods under the Background of Intelligent Retail.

Dynamic visual vending machines are rapidly growing in popularity, offering convenience and speed to customers. However, there is a prevalent issue with consumers damaging goods and then returning them to the machine, severely affecting business interests. This paper addresses the issue from the standpoint of defect detection. Although existing industrial defect detection algorithms, such as PatchCore, perform well, they face challenges, including handling goods in various orientations, detection speeds that do not meet real-time monitoring requirements, and complex backgrounds that hinder detection accuracy. These challenges hinder their application in dynamic vending environments. It is crucial to note that efficient visual features play a vital role in memory banks, yet current memory repositories for industrial inspection algorithms do not adequately address the problem of location-specific feature redundancy. To tackle these issues, this paper introduces a novel defect detection algorithm for goods using adaptive subsampling and partitioned memory banks. Firstly, Grad-CAM is utilized to extract deep features, which, in combination with shallow features, mitigate the impact of complex backgrounds on detection accuracy. Next, graph convolutional networks extract rotationally invariant features. The adaptive subsampling partitioned memory bank is then employed to store features of non-defective goods, which reduces memory consumption and enhances training speed. Experimental results on the MVTec AD dataset demonstrate that the proposed algorithm achieves a marked improvement in detection speed while maintaining accuracy that is comparable to state-of-the-art models.

Remote Photoplethysmography and Motion Tracking Convolutional Neural Network with Bidirectional Long Short-Term Memory: Non-Invasive Fatigue Detection Method Based on Multi-Modal Fusion.

Existing vision-based fatigue detection methods commonly utilize RGB cameras to extract facial and physiological features for monitoring driver fatigue. These features often include single indicators such as eyelid movement, yawning frequency, and heart rate. However, the accuracy of RGB cameras can be affected by factors like varying lighting conditions and motion. To address these challenges, we propose a non-invasive method for multi-modal fusion fatigue detection called RPPMT-CNN-BiLSTM. This method incorporates a feature extraction enhancement module based on the improved Pan-Tompkins algorithm and 1D-MTCNN. This enhances the accuracy of heart rate signal extraction and eyelid features. Furthermore, we use one-dimensional neural networks to construct two models based on heart rate and PERCLOS values, forming a fatigue detection model. To enhance the robustness and accuracy of fatigue detection, the trained model data results are input into the BiLSTM network. This generates a time-fitting relationship between the data extracted from the CNN, allowing for effective dynamic modeling and achieving multi-modal fusion fatigue detection. Numerous experiments validate the effectiveness of the proposed method, achieving an accuracy of 98.2% on the self-made MDAD (Multi-Modal Driver Alertness Dataset). This underscores the feasibility of the algorithm. In comparison with traditional methods, our approach demonstrates higher accuracy and positively contributes to maintaining traffic safety, thereby advancing the field of smart transportation.

A Lightweight Image Super-Resolution Reconstruction Algorithm Based on the Residual Feature Distillation Mechanism.

In recent years, the development of image super-resolution (SR) has explored the capabilities of convolutional neural networks (CNNs). The current research tends to use deeper CNNs to improve performance. However, blindly increasing the depth of the network does not effectively enhance its performance. Moreover, as the network depth increases, more issues arise during the training process, requiring additional training techniques. In this paper, we propose a lightweight image super-resolution reconstruction algorithm (SISR-RFDM) based on the residual feature distillation mechanism (RFDM). Building upon residual blocks, we introduce spatial attention (SA) modules to provide more informative cues for recovering high-frequency details such as image edges and textures. Additionally, the output of each residual block is utilized as hierarchical features for global feature fusion (GFF), enhancing inter-layer information flow and feature reuse. Finally, all these features are fed into the reconstruction module to restore high-quality images. Experimental results demonstrate that our proposed algorithm outperforms other comparative algorithms in terms of both subjective visual effects and objective evaluation quality. The peak signal-to-noise ratio (PSNR) is improved by 0.23 dB, and the structural similarity index (SSIM) reaches 0.9607.

A Comprehensive Analysis of Auxin Response Factor Gene Family in Melastoma dodecandrum Genome.

Auxin Response Factors (ARFs) mediate auxin signaling and govern diverse biological processes. However, a comprehensive analysis of the ARF gene family and identification of their key regulatory functions have not been conducted in Melastoma dodecandrum, leading to a weak understanding of further use and development for this functional shrub. In this study, we successfully identified a total of 27 members of the ARF gene family in M. dodecandrum and classified them into Class I-III. Class II-III showed more significant gene duplication than Class I, especially for MedARF16s. According to the prediction of cis-regulatory elements, the AP2/ERF, BHLH, and bZIP transcription factor families may serve as regulatory factors controlling the transcriptional pre-initiation expression of MedARF. Analysis of miRNA editing sites reveals that miR160 may play a regulatory role in the post-transcriptional expression of MeARF. Expression profiles revealed that more than half of the MedARFs exhibited high expression levels in the stem compared to other organs. While there are some specific genes expressed only in flowers, it is noteworthy that MedARF16s, MedARF7A, and MedARF9B, which are highly expressed in stems, also demonstrate high expressions in other organs of M. dodecandrum. Further hormone treatment experiments revealed that these MedARFs were sensitive to auxin changes, with MedARF6C and MedARF7A showing significant and rapid changes in expression upon increasing exogenous auxin. In brief, our findings suggest a crucial role in regulating plant growth and development in M. dodecandrum by responding to changes in auxin. These results can provide a theoretical basis for future molecular breeding in Myrtaceae.

General Analysis of Heat Shock Factors in the Cymbidium ensifolium Genome Provided Insights into Their Evolution and Special Roles with Response to Temperature.

Heat shock factors (HSFs) are the key regulators of heat stress responses and play pivotal roles in tissue development and the temperature-induced regulation of secondary metabolites. In order to elucidate the roles of HSFs in Cymbidium ensifolium, we conducted a genome-wide identification of CeHSF genes and predicted their functions based on their structural features and splicing patterns. Our results revealed 22 HSF family members, with each gene containing more than one intron. According to phylogenetic analysis, 59.1% of HSFs were grouped into the A subfamily, while subfamily HSFC contained only two HSFs. And the HSF gene families were differentiated evolutionarily between plant species. Two tandem repeats were found on Chr02, and two segmental duplication pairs were observed on Chr12, Chr17, and Chr19; this provided evidence for whole-genome duplication (WGD) events in C. ensifolium. The core region of the promoter in most CeHSF genes contained cis-acting elements such as AP2/ERF and bHLH, which were associated with plant growth, development, and stress responses. Except for CeHSF11, 14, and 19, each of the remaining CeHSFs contained at least one miRNA binding site. This included binding sites for miR156, miR393, and miR319, which were responsive to temperature and other stresses. The HSF gene family exhibited significant tissue specificity in both vegetative and floral organs of C. ensifolium. CeHSF13 and CeHSF15 showed relatively significant expression in flowers compared to other genes. During flower development, CeHSF15 exhibited markedly elevated expression in the early stages of flower opening, implicating critical regulatory functions in organ development and floral scent-related regulations. During the poikilothermic treatment, CeHSF14 was upregulated over 200-fold after 6 h of heat treatment. CeHSF13 and CeHSF14 showed the highest expression at 6 h of low temperature, while the expression of CeHSF15 and CeHSF21 continuously decreased at a low temperature. The expression patterns of CeHSFs further confirmed their role in responding to temperature stress. Our study may help reveal the important roles of HSFs in plant development and metabolic regulation and show insight for the further molecular design breeding of C. ensifolium.

Toward a low carbon path: Do E-commerce reduce CO2 emissions? Evidence from China.

To address global climate change, achieving carbon peak and carbon neutrality has become a global consensus. However, the means to simultaneously achieve carbon reduction and promote green economic development, particularly in developing countries, require further investigation. This study evaluates the impact of e-commerce on CO2 emissions. Through an examination of the effects of the National E-Commerce Demonstration City (NEDC) policy from 2006 to 2017, this paper reveals that e-commerce growth facilitated by the NEDC policy resulted in a 7.89% reduction in total CO2 emissions and a per capita reduction of 1.1146 tons in the pilot cities. Mechanism analysis demonstrates that the upgrading of industrial structure, development of digital finance, and the growth of innovation and entrepreneurship serve as primary pathways for this impact. The robustness of the findings is supported by parallel trend tests, placebo tests, and additional sensitivity analyses. Furthermore, the research reveals that the NEDC policy exhibits a more significant reduction in CO2 emissions in cities with higher levels of economic development and non-resource-based cities. Welfare analyses show that the NEDC policy has significant socio-economic effects. These findings provide new evidence on the environmental effects of the digital economy and offer insights into achieving carbon neutrality.

[Multisystem inflammatory syndrome in children in the context of coronavirus disease 2019 pandemic]. / æ–°åž‹å† çŠ¶ç— æ¯’æ„ŸæŸ“æµè¡ŒèƒŒæ™¯ä¸‹çš„å„¿ç«¥å¤šç³»ç»Ÿç‚Žç—‡ç»¼åˆå¾.

Multisystem inflammatory syndrome in children (MIS-C) is a complex syndrome characterized by multi-organ involvement that has emerged in the context of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) outbreak. The clinical presentation of MIS-C is similar to Kawasaki disease but predominantly presents with fever and gastrointestinal symptoms, and severe cases can involve toxic shock and cardiac dysfunction. Epidemiological findings indicate that the majority of MIS-C patients test positive for SARS-CoV-2 antibodies. The pathogenesis and pathophysiology of MIS-C remain unclear, though immune dysregulation following SARS-CoV-2 infection is considered a major contributing factor. Current treatment approaches for MIS-C primarily involve intravenous immunoglobulin therapy and symptomatic supportive care. This review article provides a comprehensive overview of the definition, epidemiology, pathogenesis, clinical presentation, diagnosis, treatment, and prognosis of MIS-C.

[Research on Position Verification of Multi-Leaf Collimator (MLC) and Dose Verification Based on Electronic Portal Imaging Device].

Objective: A quality control (QC) system based on the electronic portal imaging device (EPID) system was used to realize the Multi-Leaf Collimator (MLC) position verification and dose verification functions on Primus and VenusX accelerators. Methods: The MLC positions were calculated by the maximum gradient method of gray values to evaluate the deviation. The dose of images acquired by EPID were reconstructed using the algorithm combining dose calibration and dose calculation. The dose data obtained by EPID and two-dimensional matrix (MapCheck/PTW) were compared with the dose calculated by Pinnacle/TiGRT TPS for γ passing rate analysis. Results: The position error of VenusX MLC was less than 1 mm. The position error of Primus MLC was significantly reduced after being recalibrated under the instructions of EPID. For the dose reconstructed by EPID, the average γ passing rates of Primus were 98.86% and 91.39% under the criteria of 3%/3 mm, 10% threshold and 2%/2 mm, 10% threshold, respectively. The average γ passing rates of VenusX were 98.49% and 91.11%, respectively. Conclusion: The EPID-based accelerator quality control system can improve the efficiency of accelerator quality control and reduce the workload of physicists.

Acetylome reprograming participates in the establishment of fruit metabolism during polyploidization in citrus.

Polyploidization leads to novel phenotypes and is a major force in evolution. However, the relationship between the evolution of new traits and variations in the post-translational modifications (PTM) of proteins during polyploidization has not been studied. Acetylation of lysine residues is a common protein PTM that plays a critical regulatory role in central metabolism. To test whether changes in metabolism in citrus fruit is associated with the reprogramming of lysine acetylation (Kac) in non-histone proteins during allotetraploidization, we performed a global acetylome analysis of fruits from a synthetic allotetraploid citrus and its diploid parents. A total of 4,175 Kac sites were identified on 1,640 proteins involved in a wide range of fruit traits. In the allotetraploid, parental dominance (i.e. resemblance to one of the two parents) in specific fruit traits, such as fruit acidity and flavonol metabolism, was highly associated with parental Kac level dominance in pertinent enzymes. This association is due to Kac-mediated regulation of enzyme activity. Moreover, protein Kac probably contributes to the discordance between the transcriptomic and proteomic variations during allotetraploidization. The acetylome reprogramming can be partially explained by the expression pattern of several lysine deacetylases (KDACs). Overexpression of silent information regulator 2 (CgSRT2) and histone deacetylase 8 (CgHDA8) diverted metabolic flux from primary metabolism to secondary metabolism and partially restored a metabolic status to the allotetraploid, which expressed attenuated levels of CgSRT2 and CgHDA8. Additionally, KDAC inhibitor treatment greatly altered metabolism in citrus fruit. Collectively, these findings reveal the important role of acetylome reprogramming in trait evolution during polyploidization.

Theoretical Study on the Mechanism of the Hydrogenation of Azo (N═N) Bonds to Amines Catalyzed by Manganese.

The mechanism of the transition metal manganese complex Mn(PhPNN)(CO)2Br (CA-4) that catalyzed the hydrogenation of the azo (N═N) bond to amines has been investigated using the PBE0 function. The results show that the whole reaction involves three basic processes: (1) the addition of H2 to CA gives IN2, which can hydrogenate the azo (N═N) bond at the later stage; (2) hydrogenation of azobenzene by IN2, which gives 1,2-diphenylhydrazine (PhNHNHPh); and (3) hydrogenation of 1,2-diphenylhydrazine by IN2, which affords aniline (PhNH2). The results suggest that the hydrogenation of CA and hydrogenation of azobenzene by IN2 to afford PhNHNHPh are easy to occur due to the low barriers, and the overall rate-determining step is the formation of IN11 and PhNH2 by breaking the N-N bond in the stage of hydrogenation of 1,2-diphenylhydrazine by IN2, with an energy barrier of 39.1 kcal/mol. The computed results are in good agreement with the experimental results. The mechanism of the azobenzene reaction catalyzed by manganese was analyzed by charge and orbital analysis in detail. The theoretical results provide a deeper understanding of the mechanism and fully explain the experimental facts.

Transversus abdominis plane block vs quadratus lumborum block for postoperative analgesia in inguinal hernia repair: A systematic review and meta-analysis.

PURPOSE: The present review was designed to differentiate between the analgesic value of transversus abdominis plane block (TAP) vs the quadratus lumborum block (QLB) for patients undergoing inguinal hernia surgery. METHODS: PubMed, CENTRAL, Scopus, Embase, Google Scholar, Open gray, and a clinical trial registry were searched up to 18th February 2023 for randomized controlled trials (RCTs) comparing TAP and QLB for inguinal hernia repair. RESULTS: Six RCTs from India, Turkey, and Norway published between the years 2019 to 2023 were included. Anesthetic agents and dosages were similar for TAP and QLB groups in each study. On meta-analysis, pain scores were not statistically significant different between TAP and QLB at 3-6 h (MD: 0.46 95% CI: -0.11, 1.03 I2 = 86%), 12 h (MD: 1.34 95% CI: -0.12, 2.80 I2 = 97%), and 24 h (MD: 0.38 95% CI: -0.77, 1.53 I2 = 97%). Meta-analysis of total analgesic consumption showed a tendency of reduced analgesic consumption with QLB as compared to TAP but the difference was not significant (SMD: 0.69 95% CI: 0.00, 1.37 I2 = 83%). Data on complications was scarcely available. GRADE assessment of the evidence was low to moderate. CONCLUSION: Low to moderate-quality preliminary evidence suggests no difference in the analgesic efficacy of TAP and QLB for adult patients undergoing inguinal hernia repair. While there was a tendency for lower postoperative analgesic consumption with QLB, it needs to be verified by future studies.

Association between hyperuricemia and acute kidney injury in critically ill patients with sepsis.

BACKGROUND: Sepsis-related AKI is related to short-term mortality and poor long-term prognoses, such as chronic renal insufficiency, late development of end-stage renal disease, and long-term mortality. In this study, we aimed to investigate the association of hyperuricemia with acute kidney injury (AKI) in patients with sepsis. METHODS: The retrospective cohort study included 634 adult sepsis patients hospitalized in the intensive care unit (ICU) of the First Affiliated Hospital of Guangxi Medical University from March 2014 to June 2020 and the ICU of the Second Affiliated Hospital of Guangxi Medical University from January 2017 to June 2020. Based on the first serum uric acid level within 24 h of admission to the ICU, patients were divided into groups with or without hyperuricemia, and the incidence of AKI within seven days of ICU admission was compared between the two groups. The univariate analysis analyzed the effect of hyperuricemia on sepsis-related AKI, and the multivariable logistic regression model analysis was used. RESULTS: Among the 634 patients with sepsis, 163 (25.7%) developed hyperuricemia, and 324 (51.5%) developed AKI. The incidence of AKI in the groups with and without hyperuricemia was 76.7% and 42.3%, respectively, with statistically significant differences (2 = 57.469, P < 0.001). After adjusting for genders, comorbidities (coronary artery disease), organ failure assessment (SOFA) score on the day of admission, basal renal function, serum lactate, calcitonin, and mean arterial pressure, hyperuricemia was showed to be an independent risk factor for AKI in patients with sepsis (OR = 4.415, 95%CI 2.793 ~ 6.980, P < 0.001). For every 1 mg/dL increase in serum uric acid in patients with sepsis, the risk of AKI increased by 31.7% ( OR = 1.317, 95%CI 1.223 ~ 1.418, P < 0.001). CONCLUSION: AKI is a common complication in septic patients hospitalized in the ICU, and hyperuricemia is an independent risk factor for AKI in septic patients.

Lateral tibial intercondylar eminence is a reliable reference for alignment correction in high tibial osteotomy.

PURPOSE: The purpose of the study is to determine whether the lateral tibial intercondylar eminence (LTIE) is a reliable reference for alignment correction in high tibial osteotomy (HTO). METHODS: A total of 1954 consecutive standing whole-leg radiography (WLR) examinations of 1373 adult patients with knee osteoarthritis between 2012 and 2019 were reviewed retrospectively; 145 patients were included, 53 males and 92 females, with a mean age of 63.3 years. Virtual simulation of HTO was performed to measure weight-bearing line (WBL) percentages and hip-knee-ankle (HKA) angles when the WBL passed through the Fujisawa, top, bottom, upper 1/3, and middle points of the lateral slope of the LTIE, and the positional relationship between the Fujisawa point and the lateral slope of the LTIE was determined. RESULTS: When the WBL passed through the top, bottom, upper 1/3, and middle points of the lateral slope of the LTIE, the mean WBL percentages were 57.7% ± 2.1%, 74.6% ± 3.3%, 63.4% ± 2.1%, and 66.2% ± 2.3%, respectively, and the mean HKA angles were 182.1° ± 0.5°, 185.9° ± 0.8°, 183.3° ± 0.5°, and 184.0° ± 0.5°, respectively. When the WBL passed through the Fujisawa point, it was passing through 28.6% ± 12.7% of the width of the lateral slope (the top and bottom points were defined as 0% and 100%, respectively). When the WBL passed through the middle and upper 1/3 points of the lateral slope of the LTIE, the majority of cases (96.1%-100%) were within the limits of acceptability, as defined by the widely accepted standard of a postoperative HKA angle ranging from 183° to 186°. CONCLUSION: The upper 1/3 and middle points of the lateral slope of the LTIE are reliable references for guiding the alignment correction in HTO. In clinical application, if 62%-66% of the postoperative WBL percentage is the acceptable target range, the upper 1/3 point of the lateral slope of the LTIE may be a better alternative than the midpoint. If the postoperative HKA angle between 183° and 186° is acceptable, the midpoint of the lateral slope of the LTIE may be better than the upper 1/3 point. These findings are crucial for the accuracy of the traditional intraoperative alignment assessment techniques. LEVEL OF EVIDENCE: IV.

Multiple Facial Basal Cell Carcinoma With Xeroderma Pigmentosum.

Multiple basal cell carcinomas are rare in children and adolescents. Xeroderma pigmentosum (XP) is a rare autosomal recessive hereditary disease characterized by photosensitivity, changes in skin pigmentation, and early onset of skin cancer. XP is extremely rare in clinical practice, with only a few cases worldwide. XP is clinically incurable. The main goal of treating this disease is to diagnose as early as possible, educate patients to strictly avoid ultraviolet radiation for life, and follow up regularly to treat skin malignant tumors in time. The authors report a 15-year-old boy with facial multiple basal cell carcinoma with XP. Its medical history, clinical features, auxiliary examination, and surgical treatment process have great reference value for the in-depth understanding of the disease. The authors will discuss how to delay the progression of the disease and treat the existing lesions in different clinical stages of the disease in combination with the existing relevant literature.

Detection of Occluded Small Commodities Based on Feature Enhancement under Super-Resolution.

As small commodity features are often few in number and easily occluded by hands, the overall detection accuracy is low, and small commodity detection is still a great challenge. Therefore, in this study, a new algorithm for occlusion detection is proposed. Firstly, a super-resolution algorithm with an outline feature extraction module is used to process the input video frames to restore high-frequency details, such as the contours and textures of the commodities. Next, residual dense networks are used for feature extraction, and the network is guided to extract commodity feature information under the effects of an attention mechanism. As small commodity features are easily ignored by the network, a new local adaptive feature enhancement module is designed to enhance the regional commodity features in the shallow feature map to enhance the expression of the small commodity feature information. Finally, a small commodity detection box is generated through the regional regression network to complete the small commodity detection task. Compared to RetinaNet, the F1-score improved by 2.6%, and the mean average precision improved by 2.45%. The experimental results reveal that the proposed method can effectively enhance the expressions of the salient features of small commodities and further improve the detection accuracy for small commodities.

Recognition of Occluded Goods under Prior Inference Based on Generative Adversarial Network.

Aiming at the recognition of intelligent retail dynamic visual container goods, two problems that lead to low recognition accuracy must be addressed; one is the lack of goods features caused by the occlusion of the hand, and the other is the high similarity of goods. Therefore, this study proposes an approach for occluding goods recognition based on a generative adversarial network combined with prior inference to address the two abovementioned problems. With DarkNet53 as the backbone network, semantic segmentation is used to locate the occluded part in the feature extraction network, and simultaneously, the YOLOX decoupling head is used to obtain the detection frame. Subsequently, a generative adversarial network under prior inference is used to restore and expand the features of the occluded parts, and a multi-scale spatial attention and effective channel attention weighted attention mechanism module is proposed to select fine-grained features of goods. Finally, a metric learning method based on von Mises-Fisher distribution is proposed to increase the class spacing of features to achieve the effect of feature distinction, whilst the distinguished features are utilized to recognize goods at a fine-grained level. The experimental data used in this study were all obtained from the self-made smart retail container dataset, which contains a total of 12 types of goods used for recognition and includes four couples of similar goods. Experimental results reveal that the peak signal-to-noise ratio and structural similarity under improved prior inference are 0.7743 and 0.0183 higher than those of the other models, respectively. Compared with other optimal models, mAP improves the recognition accuracy by 1.2% and the recognition accuracy by 2.82%. This study solves two problems: one is the occlusion caused by hands, and the other is the high similarity of goods, thus meeting the requirements of commodity recognition accuracy in the field of intelligent retail and exhibiting good application prospects.

The Genome-Level Survey of the WOX Gene Family in Melastoma dodecandrum Lour.

Though conserved in higher plants, the WOX transcription factors play crucial roles in plant growth and development of Melastoma dodecandrum Lour., which shows pioneer position in land ecosystem formation and produces nutritional fruits. Identifying the WOX family genes in M. dodecandrum is imperative for elucidating its growth and development mechanisms. However, the WOX genes in M. dodecandrum have not yet been characterized. In this study, by identification 22 WOX genes in M. dodecandrum based on current genome data, we classified family genes into three clades and nine types with homeodomains. We highlighted gene duplications of MedWOX4, which offered evidences of whole-genome duplication events. Promoter analysis illustrated that cis-regulatory elements related to light and stress responses and plant growth were enriched. Expression pattern and RT-qPCR results demonstrated that the majority of WOX genes exhibited expression in the stem. MedWOX13s displayed highest expression across various tissues. MedWOX4s displayed a specific expression in the stem. Collectively, our study provided foundations for elucidating WOX gene functions and further molecular design breeding in M. dodecandrum.

Bioinformatic Assessment and Expression Profiles of the AP2/ERF Superfamily in the Melastoma dodecandrum Genome.

AP2/ERF transcription factors play crucial roles in various biological activities, including plant growth, development, and responses to biotic and abiotic stressors. However, limited research has been conducted on the AP2/ERF genes of Melastoma dodecandrum for breeding of this potential fruit crop. Leveraging the recently published whole genome sequence, we conducted a comprehensive assessment of this superfamily and explored the expression patterns of AP2/ERF genes at a genome-wide level. A significant number of genes, totaling 218, were discovered to possess the AP2 domain sequence and displayed notable structural variations among five subfamilies. An uneven distribution of these genes was observed on 12 pseudochromosomes as the result of gene expansion facilitated by segmental duplications. Analysis of cis-acting elements within promoter sites and 87.6% miRNA splicing genes predicted their involvement in multiple hormone responses and abiotic stresses through transcriptional and post-transcriptional regulations. Transcriptome analysis combined with qRT-PCR results indicated that certain candidate genes are involved in tissue formation and the response to developmental changes induced by IAA hormones. Overall, our study provides valuable insights into the evolution of ERF genes in angiosperms and lays a solid foundation for future breeding investigations aimed at improving fruit quality and enhancing adaptation to barren land environments.