Explore the vast range of titles available.

Plant disease recognition is a critical technology for ensuring food security and advancing precision agriculture. However, challenges such as class imbalance, heterogeneous image quality, and limited model interpretability remain unresolved. In this study, we propose a Synergistic Dual-Augmentation and Class-Aware Hybrid (SDA-CAH) model designed to achieve robust and interpretable recognition of plant diseases. Our approach introduces two innovative augmentation strategies: (1) an optimized MixUp method that dynamically integrates class-specific features to enhance the representation of minority classes; and (2) a customized augmentation pipeline that combines geometric transformations with photometric perturbations to strengthen the model’s resilience against image variability. To address class imbalance, we further design a class-aware hybrid sampling mechanism that incorporates weighted random sampling, effectively improving the learning of underrepresented categories and optimizing feature distribution. Additionally, a Grad-CAM–based visualization module is integrated to explicitly localize lesion regions, thereby enhancing the transparency and trustworthiness of the predictions. We evaluate SDA-CAH on the PlantVillage dataset using a pretrained EfficientNet-B0 as the backbone network. Systematic experiments demonstrate that our model achieves 99.95% accuracy, 99.89% F1-score, and 99.89% recall, outperforming several strong baselines, including an optimized Xception (99.42% accuracy, 99.39% F1-score, 99.41% recall), standard EfficientNet-B0 (99.35%, 99.32%, 99.33%), and MobileNetV2 (95.77%, 94.52%, 94.77%). For practical deployment, we developed a web-based diagnostic system that integrates automated recognition with treatment recommendations, offering user-friendly access for farmers. Experimental evaluations indicate that SDA-CAH outperforms existing approaches in predictive accuracy and simultaneously defines a new paradigm for interpretable and scalable plant disease recognition, paving the way for next-generation precision agriculture.

Hepatocellular carcinoma (HCC) is a common malignant tumor in China. In the present study, we aimed to construct and verify a prediction model of recurrence in HCC patients using databases (TCGA, AMC and Inserm) and machine learning methods and obtain the gene signature that could predict early relapse of HCC. Statistical methods, such as feature selection, survival analysis and Chi-Square test in R software, were used to analyze and select mutant genes related to disease free survival (DFS), race and vascular invasion. In addition, whole-exome sequencing was performed on 10 HCC patients recruited from our center, and the sequencing results were compared with the databases. Using the databases and machine learning methods, the prediction model of recurrence was constructed and optimized, and the selected mutant genes were verified in the test group. The accuracy of prediction was 74.19%. Moreover, these 10 patients from our center were used to verify these mutant genes and the prediction model, and a success rate of 80% was achieved. Collectively, we discovered recurrence-related genes and established recurrence prediction model of recurrence for HCC patients, which could provide significant guidance for clinical prediction of recurrence.

The blue-eared pheasant (Crossoptilon auritum), a Near Threatened (NT) species endemic to China, is primarily distributed across the northeastern region of the Qinghai–Tibetan Plateau. To bridge the fine-scale spatiotemporal gap in blue-eared pheasant behavioral ecology, this study combines satellite telemetry, movement modeling, and field-based habitat assessments (vegetation, topography, human disturbance). This multidisciplinary approach reveals detailed patterns of their behavior throughout the breeding season. Using satellite-tracking data from six individuals (five males tracked at 4 h intervals; one female tracked hourly) in Wanglang National Nature Reserve (WLNNR), Sichuan Province during breeding seasons 2018–2019, we quantified their home ranges via Kernel Density Estimation (KDE) and examined the female movement patterns using a Hidden Markov Model (HMM). The results indicated male core (50% KDE: 21.93 ± 16.54 ha) and total (95% KDE: 158.30 ± 109.30 ha) home ranges, with spatial overlap among individuals but no significant temporal variation in home range size. Habitat selection analysis indicated that the blue-eared pheasants favored shrub-dominated areas at higher elevations (steep southeast-facing slopes), regions distant from human disturbance, and with abundant animal trails. We found that their movement patterns differed between sexes: the males exhibited higher daytime activity yet slower movement speeds, while the female remained predominantly near nests, making brief excursions before returning promptly. These results enhance our understanding of the movement ecology of blue-eared pheasants by revealing fine-scale breeding-season behaviors and habitat preferences through satellite-tracking. Such detailed insights provide an essential foundation for developing targeted conservation strategies, particularly regarding effective habitat management and zoning of human activities within the species’ range.

Background Adjuvant therapies are now considered standard care for high-risk melanoma patients. It is urgent to identify reliable biomarkers to select patients at high risk of relapse, who will derive more benefit from adjuvant therapy. Methods Targeted next-generation sequencing using a 437 cancer-related gene panel was performed on primary tumor samples from 55 patients in stage I-III melanoma and postsurgical plasma samples from 46 patients. Association analysis of clinico-genomic characteristics with disease-free survival was conducted. Results The median DFS was 39.2 months (rangement: 1.4–49.7 months). Patients receiving anti-PD-1 adjuvant therapy had a longer DFS than those receiving adjuvant interferon therapy (mDFS, NA vs. 21.3 months, HR 0.36 [95% CI: 0.13–1.03], P  = 0.047). No significant correlation of DFS with driver mutations in BRAF , NRAS and KIT was observed. Chromosomal instability score (CIS) was identified as an independent predictive factor of DFS following adjustment for clinical and genetic factors (HR 4.06 [95% CI: 1.28–12.89], P  = 0.017), with an inferior DFS observed in patients with high CIS compared with the CIS-low patients (mDFS, 14.3 vs. 49.7 months, HR 3.90 [95%CI: 1.40–11.00], P  = 0.005). In addition, patients with a maxVAF > 1% in the postsurgical ctDNA had a worse DFS compared with those with a maxVAF ≤1% (mDFS, 11.0 vs. 49.7 months, HR 3.70 [95% CI: 1.20–11.00], P  = 0.012). Finally, CIS and postsurgical ctDNA status were considered as independent factors for recurrence risk in stage I-III melanoma. Conclusion Identification of clinical and genetic biomarkers for recurrence risk prediction in resected melanoma may aid in clinical decision-making for early disease monitoring and optimal design of therapeutic strategies.

In the coastal wetland, nitrogen is a limiting element for plant growth and reproduction. However, nitrogen inputs increase annually due to the rise in nitrogen emissions from human activity in coastal wetlands. Nitrogen additions may alter the coastal wetlands’ soil properties, bacterial compositions, and plant growth. The majority of nitrogen addition studies, however, are conducted in grasslands and forests, and the relationship between soil properties, bacterial compositions, and plant growth driven by nitrogen addition is poorly understood in coastal marshes. We conducted an experiment involving nitrogen addition in the Phragmites australis population of the tidal marsh of the Yellow River Delta. Since 2017, four nitrogen addition levels (N0:0 g • m -2 • year -1 , N1:5 g • m -2 • year -1 , N2:20 g • m -2 • year -1 , N3:50 g • m -2 • year -1 ) have been established in the experiment. From 2017 to 2020, we examined soil properties and plant traits. In 2018, we also measured soil bacterial composition. We analyzed the effect of nitrogen addition on soil properties, plant growth, reproduction, and plant nutrients using linear mixed-effect models. Moreover, structural equation modeling (SEM) was utilized to determine the direct and indirect effects of nitrogen addition, soil properties, and bacterial diversity on plant growth. The results demonstrated that nitrogen addition significantly affected plant traits of P. australis . N1 and N2 levels generally resulted in higher plant height, diameter, leaf length, leaf breadth, and leaf TC than N0 and N3 levels. Nitrogen addition had significantly impacted soil properties, including pH, salinity, soil TC, and soil TS. The SEM revealed that nitrogen addition had a direct and positive influence on plant height. By modifying soil bacterial diversity, nitrogen addition also had an small indirect and positive impact on plant height. However, nitrogen addition had a great negative indirect impact on plant height through altering soil properties. Thus, nitrogen inputs may directly enhance the growth of P. australis at N1 and N2 levels. Nonetheless, the maximum nitrogen addition (N3) may impede P. australis growth by reducing soil pH. Therefore, to conserve the coastal tidal marsh, it is recommended that an excess of nitrogen input be regulated.

Currently, two main challenges in cancer immunotherapy commonly hinder the application of T cell receptor-modified T cell (TCR-T) therapy in the treatment of solid tumors, including the limited ability of T cells to infiltrate solid tumor tissues and the immunosuppressive signals that restrain the anti-tumor efficacy of T cells. In this study, we constructed NY-ESO-1-specific TCR-T and introduced polyethylene glycol-phospholipids (PEG-lipids) to stably modify NY-ESO-1 TCR-T with nonapeptide iRGD, aiming to enhance the penetrability of T cells in vivo, then we combined iRGD-modified NY-ESO-1 TCR-T (iRGD-NY-ESO-1 TCR-T) with PD-1 blockade to alleviate immunosuppressive signals. In result, it is suggested that stably modifying NY-ESO-1 TCR-T with iRGD is a simple and effective strategy to enable TCR-T to target and penetrate solid tumor tissues. Besides, the combination of iRGD-NY-ESO-1 TCR-T with PD-1 blockade presents a novel synergistic strategy for the treatment of refractory NY-ESO-1-positive solid tumors.

The construction of large reservoirs has modified the process of water and sediment transport downstream, resulting in changes in the morphology of the river cross-section. Changes in water and sand transport and cross-sectional morphology are reflected in the rating curve at the cross-section. This study analyzed the variations in the rating curve at the Huayuankou (HYK) section and their influencing factors, and conducted water level predictions based on this relationship. The findings revealed that while the annual mean water level has shown a declining tendency over the past 20 years, the annual mean discharge has shown a constant pattern. The rating curve at this stretch narrowed from a rope-loop type curve in its natural condition to a more stable single curve as a result of the construction of the dam upstream of the HYK section. The effect of pre-flood section morphology and the water–sediment process on the scattering degree of the rating curve is inverse; increasing roughness and hydraulic radius decreases scattering degree, while increasing sand content and sand transport rate increases scattering degree. Using the measured data from 2020 as an example, the feasibility of predicting cross-sectional water levels using the rating curve was verified. The prediction results were accurate when the flow was between 1000 and 2800 m 3 /s; However, when the flow was between 2800 and 4000 m 3 /s, the forecast results were typically slightly lower than the measured values. Overall, the method demonstrates good predictive accuracy. Insight from the method can be used to predict water levels to better inform decision making about water resources management, and flood emergency response in the lower Yellow River.

The construction of large-scale water diversion projects has effectively alleviated the current situation of the uneven distribution of water resources in China. However, due to the siltation of very fine sediment and organic matter on the side wall of an open channel, and the slow velocity of the side wall flow field, it is easy for epipelic algae to be produced, which affects water quality. Because prototype observation cannot be used to predict the series of flow in real time, and the calculation of the mathematical model is affected by parameter limitations, these two methods often cannot truly reflect the hydrodynamic characteristics of an open channel with epipelic algae. Therefore, by referring to the design parameters of the water diversion project channel, this study took the epipelic algae growing on the side wall of an open channel as the research object and used the scale of 1:30 to carry out a generalized flume experiment. Through the analysis of the physical characteristics of the prototype sample, and the simulation of the cohesive force between the oblique side wall and the epipelic algae, multi-group and multi-series hydrodynamic tests were carried out. The velocity distribution law and flow field distribution law were analyzed. The research results show that the presence of epipelic algae has a certain hindering effect on the flow velocity and significantly reduces the range of the peak velocity of the channel along the water depth. The position of the maximum velocity on the vertical line of the channel flow appears at the relative water depth of 0.6. In the case of small flow, the epipelic algae group only reduces the average flow rate of the channel by 5~6%; in the case of large flow, the effect of epipelic algae on the channel flow rate is minimal. This paper includes important scientific guiding significance and practical value for the regulation of water quantity and water quality safety, as well as the protection of long-distance projects.

Eutrophication resulting from anthropogenic activities has been recognized as a significant driver of changes in ecosystem functioning. Furthermore, it may exacerbate the top–down effect and thus exert an important impact on plant growth. To test this hypothesis, we conducted a 3-year manipulative field experiment to investigate the impacts of nitrogen addition and crab herbivory on the growth of Phragmites australis in the salt marsh of the Yellow River Delta. The results demonstrated that a 3-year nitrogen addition can significantly increase the total nitrogen and carbon content of P. australis leaves, thereby enhancing their nutritional value and palatability, as well as increasing the proportion of leaves consumed by crabs. Therefore, nitrogen addition together with crab herbivory had a significant negative effect on P. australis height, leaf length, and leaf breadth in the ambient crab and procedural crab cage treatment compared to the crab exclusion treatment. The structural equation modeling further substantiated these findings. The model revealed a direct and positive correlation between nitrogen addition and leaf nutrient content (path coefficient = 0.34). Additionally, it demonstrated a direct and positive relationship between leaf nutrient content and the proportion of leaves consumed by crabs (path coefficient = 0.22). Simultaneously, there was an observed negative correlation (path coefficient = − 0.37) between the proportion of leaves consumed by crabs and plant functional traits, represented by leaf length in the model, during 2018. Moreover, the crab exclusion treatment significantly reduced the proportion of leaves consumed by crabs and thus enhanced the P. australis individuals, leaf number, and biomass. Overall, crab herbivory had a significant detrimental top–down effect on the growth of P. australis , and nitrogen enrichment may exacerbate this top–down effect. The findings of our study highlight the combined adverse effects of nutrient enrichment and top–down on plant functional traits and plant growth. The findings of this study will contribute to a comprehensive understanding of the underlying factors influencing vegetation degradation in coastal wetland, thereby establishing a solid theoretical framework for the conservation and management of wetland ecosystems within the context of global environmental change.

Objective To investigate the correlation between peripheral blood CRP‐to‐lymphocyte ratio (CLR) and lactate dehydrogenase‐to‐albumin ratio (LAR) levels, prognosis, and the tumor microenvironment (TME) in patients with acral melanoma (AM), with a focus on tertiary lymphoid structures (TLS) and immune cell infiltration. Methods A retrospective cohort of 36 patients with acral melanoma was included. Clinical data and hematological parameters were collected. The maturity of TLS, the proportion of immune cells, and their spatial distribution within the TME were assessed using H&E staining and multiplex immunofluorescence. Kaplan–Meier survival curves and Cox regression models were employed to examine the association between these indicators and patient survival. Non‐parametric tests and Spearman's correlation analysis were used to compare CLR and LAR levels across patients with different TLS maturity and immune infiltration statuses. Results Elevated levels of CLR and LAR in the blood are associated with poorer prognosis in patients with acral melanoma. The levels of CLR and LAR vary across patients with TLS of different maturities, and these levels decrease as TLS maturity increases. Additionally, CLR and LAR levels are significantly correlated with the proportions of CD4+ and CD8+ T cells in TME, with higher levels of CLR and LAR being linked to reduced immune cell infiltration. Conclusion Elevated CLR and LAR levels are associated with poorer prognosis in AM patients, and this relationship is closely linked to the maturity of TLS and the extent of immune cell infiltration within the TME.