Rapid and accurate detection of stored grain insects is essential for minimizing insect damage. To address challenges of stored grain insect identification, an enhanced lightweight detection model was developed. The developed model integrated Channel-Transposed Attention (CTA) with the C3K module to improve fine-grained feature representation and reduce background interference. To further strengthen detection robustness under poor illumination, a novel image preprocessing component, named CPA-Enhancer, was embedded into the backbone network. This developed module adaptively adjusted image contrast and exposure to enhance feature visibility under dim and uneven light conditions. In addition, to overcome the number imbalance of insect images provided in the dataset, an Adaptive Threshold Focal Loss (ATFL) function was introduced. This function increased sensitivity to minor classes while maintaining overall model stability. To evaluate the performance of the developed model, subset and ablation experiments and comparison were conducted among different models under the same configuration and by employing an Edge device. The developed model attained a precision of 91.1%, recall of 93.0%, F1 score of 92.0%, and mean Average Precision (mAP) of 94.2% when all dataset was used. Ablation study verified the individual and synergized effectiveness of the CTA, CPA-Enhancer, and ATFL modules. Moreover, deployment evaluations on edge device confirmed its capability for real-time insect detection under resource-constrained field environments.

Urban traffic flow prediction is a critical task in Intelligent Transportation Systems, yet existing methods often struggle with capturing long-range spatial dependencies and preserving high-frequency signals. To address these challenges, this paper proposes LGM4TFP, a novel framework that incorporates a Graph Attention with High-frequency Enhancement (GAHE) module. GAHE integrates dynamic graph attention for spatial feature extraction and a spectral-domain high-frequency enhancement mechanism to alleviate the over-smoothing problem. Extensive experiments on four real-world datasets demonstrate that LGM4TFP consistently outperforms state-of-the-art models by 5–10% in RMSE, MAE, and MAPE. Ablation studies confirm the effectiveness of the proposed modules, and results show that the model maintains strong robustness across diverse prediction scenarios, highlighting its practical value for dynamic traffic management.

Advances in omics technologies provide unprecedented opportunities for systems biology, yet integrating multi-omics data remains challenging due to its complexity, heterogeneity, and the sparsity of prior knowledge networks. Here, we introduce a multi-omics data integration analysis (MODA) framework that fully incorporates prior knowledge to identify hub molecules and pathways, and elucidate biological mechanisms. By leveraging multiple machine learning approaches, MODA transforms raw omics data into a feature importance matrix that is mapped onto a biological knowledge graph to mitigate omics data noise. Then, it uses graph convolutional networks with attention mechanisms to capture intricate molecular relationships and rank molecules via a feature-selective layer. Ultimately, MODA transcends the limitations of predefined pathway annotations by employing an overlapping community detection algorithm to extract core functional modules that are involved in multiple pivotal disease pathways. Systematic evaluations show that MODA outperforms seven existing multi-omics integration methods in classification performance while maintaining biological interpretability. Moreover, MODA achieves superior stability in pan-cancer datasets. Application to the multi-omics datasets of prostate cancer reveals a key role for carnitine and palmitoylcarnitine, regulated by BBOX1 in the progression of prostate cancer. Population samples and in vitro experiments further validate these findings. With high data utilization efficiency and low computational cost, MODA serves as a robust tool for uncovering novel disease mechanisms and advancing precision medicine.

The rapid growth of high-dimensional omics datasets in biomedical research has created an urgent need for computational frameworks that are both robust and adaptable to diverse data complexities. Although a wide range of specialized tools and algorithms are available, researchers often rely on trial-and-error approaches to select suitable analytical workflows, compromising both efficiency and reproducibility. In this study, we systematically benchmarked hundreds of algorithms-preprocessing combinations across three common biomedical data challenges, including small sample sizes, missing values, and class imbalance. Our results show that tree-based models (e.g. Gradient Boosting Decision Tree, XGBoost, and Random Forest) consistently perform well in scenarios involving small-sample and missing-data, while partial least squares discriminant analysis (PLS-DA) is more effective in addressing imbalanced classes. Unsupervised cluster methods such as K-means and Density-Based Spatial Clustering of Applications with Noise (DBSCAN) remain robust under moderate missingness, but their performance declines when missingness exceeds 10%. To support data-driven decision-making, we developed SysML, a web-based platform that recommends data-adaptive workflows based on dataset-specific characteristics. Validated on multiple real-world biomedical datasets, SysML demonstrated improvements in both model performance and workflow efficiency. Our findings underscore that adaptive data preprocessing, rather than algorithm choice alone, is critical for achieving reliable and reproducible machine learning applications in biomedicine.

In industrial automatic product quality inspection, visual anomaly detection is paramount. While unsupervised anomaly detection methods based on reconstruction have shown promising results, particularly in anomaly localization, these methods still suffer from challenges such as overfitting of pseudo-anomalous distribution by reconstruction networks and difficulty in distinguishing near-distribution anomalies by discriminative networks. In this paper, we propose a novel Anomalous Feature Restriction and Difference-Aware Enhancement Network (RE-Net), which aims to constrain abnormal features while enhancing the minute discrepancies between normal and abnormal features. This network comprises two key modules: the Abnormal Feature Restriction Module (AFRM) and the Difference-Aware Enhancement Module (DAEM). AFRM first explicitly constrains abnormal features by utilizing normal features in the reconstructed subnetwork to prevent the network from overfitting pseudo-abnormal distributions while ensuring the consistency of normal regions. Upon achieving a normal reconstruction from an anomalous input, DAEM is then used to enhance the perception of the difference between normal and abnormal in the discriminant subnetwork, thereby effectively improving the detection ability of highly camouflaged near-distribution anomalies. A series of comparative experiments on textured objects in the MVTec AD dataset show that our method achieves better anomaly detection results, reaching 99.9% image-level AUROC and 98.76% pixel-level AUROC.

News Discourse Profiling is a discourse task that aims to recognize the semantic role of each sentence in an article. Within this task, the model not only requires comprehending the news content but also needs to analyze the logical relation in a discourse, posing a great challenge to traditional deep learning techniques. Recently, large language model (LLM) technology has demonstrated significant potential for enhancing the task of news discourse profiling. These models, characterized by their vast number of parameters, excel in logical reasoning and contextual understanding, allowing them to grasp the intricate details and relationships within the text. When paired with the effective chain-of-thought (CoT) technique, LLMs have shown impressive performance in many complex reasoning tasks. However, the discourse structure significantly differentiates between news, thus it is difficult to analyze all news with a unified fixed CoT. In this paper, We propose an adaptive CoT technique for the News Discourse Profiling task, namely Easy-to-Hard Self-Comparative Chain-of- Thought (ESC-CoT). ESC-CoT formulates the task as a multiple-iteration process, i.e., ESC-CoT handles the easiest part at the current iteration and gradually transfers to more complex parts, which can reduce the risk of early error propagation. To alleviate error propagation along the reasoning chain, ESC-CoT compares the conflicting results from different CoT processes, analyzing the context and meaning of sentences more deeply, thereby improving LLM's reasoning ability and reducing the possibility of error. Experiment results demonstrate that ESC-CoT substantially surpasses the traditional news discourse profiling methods. Compared with state-of-the-art (SOTA) methods on two benchmark datasets, the ESC-CoT technique shows an improvement of 7.8 and 19.6 on F1 score, respectively.

BACKGROUND: Plant secondary metabolites are highly valued for their applications in pharmaceuticals, nutrition, flavors, and aesthetics. It is of great importance to elucidate plant secondary metabolic pathways due to their crucial roles in biological processes during plant growth and development. However, understanding plant biosynthesis and degradation pathways remains a challenge due to the lack of sufficient information in current databases. To address this issue, we proposed a transfer learning approach using a pre-trained hybrid deep learning architecture that combines Graph Transformer and convolutional neural network (GTC) to predict plant metabolic pathways. RESULTS: GTC provides comprehensive molecular representation by extracting both structural features from the molecular graph and textual information from the SMILES string. GTC is pre-trained on the KEGG datasets to acquire general features, followed by fine-tuning on plant-derived datasets. Four metrics were chosen for model performance evaluation. The results show that GTC outperforms six other models, including three previously reported machine learning models, on the KEGG dataset. GTC yields an accuracy of 96.75%, precision of 85.14%, recall of 83.03%, and F1_score of 84.06%. Furthermore, an ablation study confirms the indispensability of all the components of the hybrid GTC model. Transfer learning is then employed to leverage the shared knowledge acquired from the KEGG metabolic pathways. As a result, the transferred GTC exhibits outstanding accuracy in predicting plant secondary metabolic pathways with an average accuracy of 98.30% in fivefold cross-validation and 97.82% on the final test. In addition, GTC is employed to classify natural products. It achieves a perfect accuracy score of 100.00% for alkaloids, while the lowest accuracy score of 98.42% for shikimates and phenylpropanoids. CONCLUSIONS: The proposed GTC effectively captures molecular features, and achieves high performance in classifying KEGG metabolic pathways and predicting plant secondary metabolic pathways via transfer learning. Furthermore, GTC demonstrates its generalization ability by accurately classifying natural products. A user-friendly executable program has been developed, which only requires the input of the SMILES string of the query compound in a graphical interface.