Search Results (13,618)

Background/Objectives: Plant architecture is a critical determinant of high-density tolerance and yield potential in maize (Zea mays L.), yet the genetic networks orchestrating these complex traits require deeper elucidation. Methods: In this study, we utilized a Multi-parent Advanced Generation Inter-cross (MAGIC) population comprising 935 recombinant inbred lines (RILs) derived from 16 diverse elite founders. A comprehensive phenotypic characterization of six pivotal architectural traits—plant height (PH), ear height (EH), ear leaf length (LL), ear leaf width (LW), tassel main axis length (TL), and tassel branch number (TBN)—was conducted across three distinct agro-ecological environments. Results: Phenotypic analysis revealed substantial natural variation and high broad-sense heritability (H² ranging from 60% to 86%), with TBN exhibiting the most pronounced variability. Correlation architecture demonstrated a strong coupling between vertical growth traits (PH and EH, r = 0.73), while lateral leaf expansion (LW) and tassel complexity (TBN) showed significant genetic independence. Using a mixed linear model (MLM) for genome-wide association studies (GWAS), we identified 21 significant SNP–trait associations, including distinct chromosomal clusters on chromosome 8 for EH and chromosome 7 for TBN. By integrating genomic intervals with tissue-specific expression profiling, 23 core candidate genes were prioritized. Notably, Zm00001d042528 (FAS1), involved in chromatin assembly, was implicated in modulating meristematic cell division for plant stature. Other key regulators included Zm00001d020537 (O5) and Zm00001d025360 (F-box protein), which were associated with reproductive organ development and leaf elongation, respectively. Conclusions: These results indicate that maize plant architecture is regulated by a modular genetic framework, with specific loci independently regulating canopy structure and source–sink components. It should be noted that the findings of this study are based solely on statistical models identifying significant associations between genetic loci and phenotypes; the biological regulatory functions of the candidate genes have not yet been experimentally validated. Nevertheless, this study provides new insights into the molecular mechanisms underlying maize morphogenesis and lays a solid theoretical foundation for molecular design breeding aimed at developing high-yielding varieties tolerant of high planting densities. Full article

A hybrid modelling framework is proposed to predict endpoint sulphur content in the ladle furnace (LF) refining process by embedding metallurgical expert knowledge into interpretable machine learning (ML). Industrial process data were extracted from the Level-2 (L2) system of a steel plant, and a desulphurisation dataset comprising 5169 heats with 29 process variables was constructed using a knowledge-guided time window from the joint satisfaction of refining conditions to the final argon-blowing stage. After data cleaning, normalisation and correlation-based feature selection, four algorithms—Random Forest (RF), Extreme Gradient Boosting (XGBoost), Support Vector Machine (SVM) and Artificial Neural Network (ANN)—were trained and compared on a representative cluster of steel grades identified by K-means. The ANN model achieved a coefficient of determination (R²) of 0.7752, a root mean square error (RMSE) of 0.0027 wt%, a mean absolute error (MAE) of 0.0017 wt% and a hit rate (HR, ±0.0025 wt% for S) of 76.40% on the test set. SHapley Additive exPlanations (SHAP) indicate that limestone addition, slag basicity, argon flow rate, refining time and initial sulphur content dominantly govern sulphur removal. The expert-knowledge-guided, interpretable framework provides quantitative support for specification-conforming endpoint sulphur control while mitigating over-desulphurisation and reagent consumption. Full article

Background: Breast cancer (BC) is one of the most diagnosed malignancies and a leading cause of cancer-related mortality among women worldwide, thereby posing a substantial threat to women’s health worldwide. However, clinically robust diagnostic biomarkers with high sensitivity and specificity, as well as well-validated molecular targets for targeted therapy, remain limited. Methods: BC transcriptomic data from seven GEO datasets and the TCGA-BRCA cohort (n = 1231) were integrated for analysis. After batch-effect correction, candidate genes were screened through DEA, WGCNA, and PPI networks analysis. An ensemble machine learning (ML) framework incorporating 127 algorithmic combinations was constructed, and SHAP analysis was applied to identify hub genes. Further analyses included functional enrichment, immune infiltration, miRNA regulatory network analysis, and SMR analysis. The expression patterns were validated using single-cell transcriptome data. Drug repositioning analysis and AI-assisted virtual screening were performed to prioritize compounds with favorable drug-like properties. The predicted binding modes of candidate compounds with CHEK1 were assessed by molecular docking. Results: Thirty core genes were obtained through differential expression, WGCNA, and PPI screening. Integrated ML (127 algorithms) determined the optimal model (AUC = 0.919), and SHAP identified nine feature genes, among which CHEK1 and KIF23 showed preliminary diagnostic potential across four external cohorts (AUC: 0.625–0.938). Functional enrichment indicated that both are enriched in the cell cycle and p53 pathways, closely associated with BRCA1/ATR; immune infiltration revealed significant correlations with macrophages and CD8⁺ T cells, with hsa-miR-15a-5p and hsa-miR-607 being common upstream regulatory miRNAs. SMR analysis supported a causal relationship between CHEK1 expression and BC genetic susceptibility (p_SMR < 0.05, p_HEIDI > 0.05); single-cell analysis confirms its heterogeneous expression. AI-assisted virtual screening identified 25 A-grade computational candidate compounds from 171 candidates. Molecular docking suggested that Olaparib and LY294002 can form favorable interactions with the CHEK1 active pocket. Conclusions: The study identified CHEK1 as a key diagnostic gene for BC through 127 ML algorithms and SMR causal inference. By combining AI-assisted virtual screening and molecular docking, computational candidate compounds targeting CHEK1 were prioritized. These findings represent hypothesis-generating in silico predictions and require experimental validation before any therapeutic conclusions can be drawn. Full article

COVID-19 still poses a global public health challenge, exerting pressure on radiology services. Chest X-ray (CXR) imaging is widely used for respiratory assessment due to its accessibility and cost-effectiveness. However, its interpretation is often challenging because of subtle radiographic features and inter-observer variability. Although recent deep learning (DL) approaches have shown strong performance in automated CXR classification, their black-box nature limits interpretability. This study proposes an explainable deep learning framework for COVID-19 detection from chest X-ray images. The framework incorporates anatomically guided preprocessing, including lung-region isolation, contrast-limited adaptive histogram equalization (CLAHE), bone suppression, and feature enhancement. A novel four-channel input representation was constructed by combining lung-isolated soft-tissue images with frequency-domain opacity maps, vessel enhancement maps, and texture-based features. Classification was performed using a modified Xception-based convolutional neural network, while Gradient-weighted Class Activation Mapping (Grad-CAM) was employed to provide visual explanations and enhance interpretability. The framework was evaluated on the publicly available COVID-19 Radiography Database, achieving an accuracy of 95.3%, an AUC of 0.983, and a Matthews Correlation Coefficient of approximately 0.83. Threshold optimisation improved sensitivity, reducing missed COVID-19 cases while maintaining high overall performance. Explainability analysis showed that model attention was primarily focused on clinically relevant lung regions. Full article

Soil fumigation effectively mitigates replanting obstacles induced by intensive cultivation, yet its non-targeted biocidal effects can suppress beneficial microbial activity, potentially compromising agricultural sustainability. Microbial inoculation, as a strategy to supplement beneficial microorganisms, is often employed to restore soil microbial communities. However, in practice, commonly used exogenous microbial consortia exhibit poor adaptability in non-native environments, frequently resulting in limited efficacy. To address this limitation, we propose an ecological intervention based on the reintroduction of indigenous cultivable microorganisms: cultivable microbial communities were isolated from healthy adjacent soils and inoculated into fumigated soils affected by replanting obstacles. The experimental soil consisted of black soil under continuous cropping, collected from Northeast China. The three treatments were continuous cropping soil (control), fumigated continuous cropping soil and fumigated continuous cropping soil after inoculation of indigenous cultivable microorganisms. Using high-throughput sequencing and agronomic–chemical analyses, combined with cross-domain networks and procrustes analysis, we systematically assessed the ecological effects of this approach on microbial restoration and the alleviation of replanting obstacles. The results showed that indigenous cultivable microorganism inoculation significantly increased the richness of bacterial and fungal communities in fumigated soils within 21 days, extending microbial richness and diversity. Furthermore, inoculation accelerated the reconstruction of dominant microbial community structures, with the relative abundance of dominant species reaching up to 80%. Positive synergistic interactions between bacteria and fungi increased by approximately 10%, enhancing network stability. Key bacterial taxa, such as Paenibacillus and Mycobacterium, were significantly correlated with available potassium and phosphorus content, while Micromonospora, Massilia, and Flavisolibacter influenced plant fresh weight, total nitrogen, and potassium accumulation. Key fungal taxa, such as Cryptococcus and Phialemonium, were significantly associated with soil organic matter stability, maize photosynthetic efficiency, plant dry weight, and total phosphorus content. This study confirms the ecological adaptability and functionality of indigenous cultivable microorganisms in soil ecosystem restoration, offering a low-risk, highly effective localized intervention strategy for sustainable agriculture. Full article

Accurate prediction of vibration responses in hydraulic structures during flood discharge is essential for ensuring safe and stable operation. This study develops a hybrid deep learning model that combines Convolutional Neural Networks (CNN), Bidirectional Long Short-Term Memory (BiLSTM), and a Channel Attention (CA) mechanism, optimized through Bayesian Optimization (BO), to predict dam gantry crane beam displacements. Time-lagged Pearson correlation and Maximum Information Coefficient (MIC) are applied to select the informative input features. The CNN-BiLSTM-CA model captures both spatial patterns and temporal dependencies in vibration signals. BO tunes model hyperparameters, while Partial Dependence (PD) analysis provides insight into how these parameters affect prediction accuracy. The model is validated using vibration data from an arch dam in Southwest China during flood discharge. Results show that CNN parameters have a greater impact on prediction accuracy than BiLSTM parameters, underscoring the importance of spatial feature extraction. Ablation studies confirm each component’s contribution. Compared with existing methods, the proposed model achieves superior accuracy with a Root Mean Square Error (RMSE) of 5.49, Mean Absolute Error (MAE) of 4.34, and correlation coefficient (R) of 99.42%. This framework provides a reliable and interpretable tool for predicting structural vibrations in hydraulic engineering under complex discharge conditions. Full article

Simple trigger logic is commonly used in actual wind farms to monitor unit conditions, which face problems such as a high false-alarm rate and overlapping alarms. In addition, the characteristics of SCADA data, such as large quantity, complexity, and variable correlation, lead to insufficient accuracy of fault diagnosis. To address this problem, an improved fault diagnosis method based on a Multi-Channel Attention Mechanism Convolutional Neural Network (MCAMCNN) is proposed. Firstly, feature analysis is performed after preprocessing SCADA data to fully explore the coupling characteristics between data, and a dataset is established. Then, the proposed fault diagnosis model is used for feature screening. Innovatively, a structure combining double-layer multi-scale convolution and multi-channel attention is adopted to extract multi-domain features and dynamically calibrate the weights of feature channels. Fault classification is realized after adaptive fusion of features by Efficient Channel Attention (ECA). Finally, experiments are designed based on real data from an onshore wind farm in China, which verify that the method is timely and accurate in fault diagnosis, with significantly improved accuracy and F1-score, and has obvious advantages over comparative methods. Full article

Complexity in engineered systems presents one of the most persistent challenges in modern development since it is driving cost overruns, schedule delays, and outright project failures. Yet while architectural complexity has been studied, the structural complexity embedded within requirements specifications remains poorly understood and inadequately quantified. This gap is consequential: requirements fundamentally drive system design, and complexity introduced at this stage propagates through architecture, implementation, and integration. To address this gap, we build on Natural Language Processing methods that extract structural networks from textual requirements. Using these extracted structures, we conduct a controlled experiment employing molecular integration tasks as structurally isomorphic proxies for requirements integration—leveraging the topological equivalence between molecular graphs and requirement networks while eliminating confounding factors such as domain expertise and semantic ambiguity. Our results demonstrate that spectral measures predict integration effort with correlations exceeding 0.95, while structural metrics achieve correlations above 0.89. Notably, density-based metrics show no significant predictive validity. These findings indicate that eigenvalue-derived measures capture cognitive and effort dimensions that simpler connectivity metrics cannot. As a result, this research bridges a critical methodological gap between architectural complexity analysis and requirements engineering practice, providing a validated foundation for applying these metrics to requirements engineering, where similar structural complexity patterns may predict integration effort. Full article

Mastitis, a disease associated with milk production with multiple etiologies, causes significant economic losses among dairy farmers worldwide. This study aimed to detect mastitis using thermal images of the udder obtained during the milking phase from 500 Holstein dairy cows with the aid of an Artificial Neural Network (ANN). Mastitis levels were classified based on the California Mastitis Test (CMT) scores using somatic cell count (SCC) as the output variable. The dataset was divided into training (70%), validation (15%), and test (15%) subsets. RGB (Red, Green, Blue) thermal images were used to construct the input matrices. The model achieved correlation coefficients (R) of 0.91, 0.97, and 0.97 for the training, validation, and test datasets, respectively. The close agreement between validation and test performances indicates the absence of overfitting and demonstrates strong generalization capability of the proposed model. These findings suggest that artificial neural networks combined with thermal imaging can provide high-quality and reliable results for mastitis detection. Full article

Infrared and visible image fusion is a critical technology for enhancing the all-weather perception capabilities of autonomous driving systems. However, the inherent physical parallax of vehicle-mounted sensors combined with motion-induced vibrations makes it difficult to achieve strict alignment between the source images. Direct fusion of such misaligned pairs leads to ghosting artifacts, which significantly compromises driving safety. To address this challenge, this paper proposes a cascaded deep fusion framework tailored for autonomous driving scenarios. A dual-modal perception dataset is first constructed, incorporating realistic physical parallax and non-rigid deformations. Subsequently, a decoupled strategy is established, characterized by geometric correction followed by semantic fusion: the Static-Feature Recursive Registration (SFRR) network is utilized to explicitly correct the spatial misalignments caused by parallax, thereby establishing geometric consistency; then, the Hierarchical Invertible Block Fusion (HIBF) network achieves lossless integration of cross-modal features by combining spatial frequency separation with invertible interaction techniques. Experimental results demonstrate that the proposed method outperforms representative algorithms across several metrics, including Mutual Information (MI), Visual Information Fidelity (VIF), Structural Similarity (SSIM), and Correlation Coefficient (CC), producing high-quality fused images with clear structural definitions. Full article

Fractured reservoir characterization is a complex and challenging task due to its depositional nature and high uncertainty in the spatial distribution of fractures, typically when well data is limited, and interpolation algorithms are employed. This paper introduces an alternative workflow designed to enhance fracture modeling between well locations by incorporating seismic attributes, using publicly released data from the Teapot Dome Field. The paper’s objective is to create a fracture model for the Tensleep reservoir in the Teapot Dome Anticline by employing seismic attributes sensitive to fault and fracture features, while also demonstrating the limitations of interpolation-based models such as Gaussian simulation. The approach uses artificial neural networks to predict fracture intensity by analyzing seismic data and well logs, training supervised probabilistic artificial networks to identify the seismic attributes that most closely correlate with the fracture intensity property derived from well log data. The validated network successfully transformed the 3D seismic data into 3D fracture intensity data, achieving a high correlation coefficient between the selected seismic attributes and the training wells. The research findings are extremely valuable because they help address the lack of information on fractures, improve reservoir management, and optimize well placement. Full article

Chronic lung allograft dysfunction (CLAD) remains the principal limitation to long-term survival after lung transplantation (LT). Early molecular alterations within the graft may precede clinically overt functional decline, but their biological significance remains incompletely defined. In this single-center exploratory pilot study, 16 bilateral lung transplant recipients underwent bronchoalveolar lavage (BAL) sampling at 7 days, 15 days, and 3 months post-transplantation. BAL-derived microRNA (miRNA) profiles were analyzed longitudinally and correlated with long-term clinical outcomes, including CLAD development and phenotypic classification into bronchiolitis obliterans syndrome (BOS) or restrictive allograft syndrome (RAS), over extended follow-up (mean 98 months). Distinct early miRNA signatures were detectable within the first weeks after transplantation and were associated with divergent long-term clinical trajectories. Specific miRNAs, namely let-7e-5p and miR-30d-3p, were associated with subsequent CLAD, whereas differential expression patterns distinguished trajectories toward BOS or RAS. Enrichment analyses highlighted networks related to innate immune activation, hypoxia, tissue remodeling, and PI3K–mTOR signaling. Notably, the occurrence of acute rejection did not differ significantly between patients who developed CLAD and those who remained stable. These findings, although preliminary, suggest that early BAL-derived miRNA profiles may reflect biologically distinct graft states associated with long-term CLAD phenotypes. Full article

End-to-end encrypted (E2EE) messaging and the growing use of cryptocurrency create an attribution gap for digital investigators because message content is unavailable and wallet activity is often decoupled from subscriber identities, which makes it difficult to link communication behaviors with wallet activity. We propose a lawful and metadata-driven forensic attribution framework called the Data-Source Association Framework (DSAF). The DSAF links encrypted communication behavior with cryptocurrency wallet activity by correlating only legally obtainable network metadata that are observable under lawful interception (LI) with on-chain traces. By integrating information from communication behaviors and wallet activity, the framework aims to narrow the person–application–wallet attribution gap. The framework integrates two components, where one performs encrypted-application classification using transport-layer signals and flow-level features and the other conducts wallet–identity association by applying controlled decoding to intercepted traffic and extracting relevant transaction traces. Both components operate under a minimum-field schema that is aligned with Taiwanese LI procedures. We implemented the workflow and evaluated it using controlled experiments across multiple wallets and assets, reporting Wilson 95% confidence intervals (CIs). We achieved 91.4% accuracy (181/198) in end-to-end association under a confidence threshold, with high performance across wallet types, including Monero and TronLink. Full article

Acoustic divergence is widely recognized as a key driver of speciation and niche differentiation in vocal animals. In echolocating horseshoe bats (Rhinolophus), the larynx is specialized for producing high-duty-cycle signals used in foraging, navigation, and species recognition. While the ecological role of echolocation is established, the molecular mechanisms regulating laryngeal frequency remain unclear. We compared the laryngeal transcriptomes of three closely related, sympatric Rhinolophus species with distinct resting frequencies (RFs): R. episcopus (~46 kHz), R. siamensis (~66 kHz), and R. osgoodi (~85 kHz). This comparison identified 511 differentially expressed genes. High-frequency species upregulated genes involved in cytoskeletal dynamics and muscle contraction, such as cell adhesion molecules and motor proteins, while low-frequency species upregulated genes related to cellular homeostasis and metabolic maintenance. Weighted gene co-expression network analysis revealed two RF-correlated modules: a high-frequency module enriched in aerobic respiration and carbon metabolism and a low-frequency module enriched in lipid metabolism. Protein–protein interaction analysis identified ACTC1, vital for muscle contraction, as a hub gene. Evolutionary analysis showed that ACTC1 is highly conserved, with no significant positive selection, indicating that transcriptional regulation, rather than coding-sequence divergence, is the primary driver of the observed functional differences. These findings suggest that RF variation likely results from transcriptional remodeling in laryngeal superfast muscles. This study provides the first transcriptomic evidence linking laryngeal gene expression with acoustic divergence and offers new insights into the genetic basis of bat echolocation. Full article

Long non-coding RNAs (lncRNAs) are key regulators of gene expression and play critical roles in cancer-related signaling networks. Dysregulation of antagonistic lncRNAs may contribute to hepatocarcinogenesis and disease progression. This study investigated the clinical significance and predictive value of two biologically antagonistic lncRNAs, UFC1 and PTENP1, as circulating biomarkers for hepatocellular carcinoma (HCC) in an Egyptian cohort. Expression levels of these lncRNAs were quantified in 100 HCC patients and 100 age- and sex-matched healthy controls. UFC1 was significantly upregulated (~2.9-fold), while PTENP1 was markedly downregulated (~4-fold) in HCC patients, with a strong inverse correlation (r = −0.609, p < 0.001). Both lncRNAs demonstrated higher diagnostic accuracy compared to alpha-fetoprotein (AFP); combining them with AFP further enhanced overall performance. UFC1 expression was increased progressively with advancing fibrosis grade and Barcelona Clinic Liver Cancer (BCLC) stage, while PTENP1 levels diminished with BCLC stage. Logistic regression confirmed UFC1 as an independent risk factor and PTENP1 as a protective factor for HCC. In conclusion, the blood-based UFC1/PTENP1 panel exhibits promising diagnostic accuracy and is associated with disease severity, surpassing AFP. Their fibrosis-associated dysregulation suggests a role in early hepatocarcinogenesis. This antagonistic lncRNA signature represents a potential, non-invasive tool for HCC detection and risk stratification, meriting further clinical validation. Full article