Gene fusions are critical oncogenic drivers and therapeutic targets in diverse cancers. Long-read ribonucleic acid sequencing (RNA-seq) offers an unprecedented opportunity to resolve the full-length structure of fusion isoforms, but its high intrinsic error rates pose significant challenges to the precise identification of true fusion events. Here, we developed GFSeeker, an innovative splicing-graph-based computational framework for accurate gene fusion detection from long-read RNA-seq. GFSeeker employs a unique pipeline based on a splicing graph reference and a dual re-alignment validation to effectively overcome data noise from high error rates. Benchmarking across simulated, non-tumor, and cancer cell line datasets demonstrated GFSeeker's state-of-the-art performance, achieving 6%-15% higher F1 score compared to existing methods. Notably, GFSeeker successfully identified the known fusion event, MATN2-POP1, in the MCF-7 cancer cell line, missed by other tools, highlighting its superior sensitivity in resolving complex fusion events. These results validate GFSeeker as a powerful and reliable tool for gene fusion discovery, heralding its significant potential to advance cancer research and precision diagnostics.

Structural variations (SVs) are genomic rearrangements larger than 50 bp, that are widely present in the human genome and are associated with various complex diseases. Existing long-read-based SV detection tools often rely on fixed rules or heuristic algorithms, which can oversimplify the complexity of SV signatures. Therefore, these methods usually lack flexibility and cannot fully capture SV signals, leading to reduced accuracy and robustness. To address these issues, we propose SVHunter, a transformer-based method for long-read SV detection. SVHunter combines convolutional neural networks and transformers to capture both local and global SV signatures, enabling accurate identification of SVs. Additionally, SVHunter employs the mean shift clustering algorithm, which dynamically adjusts bandwidth parameters to accommodate different types of SVs without requiring a preset number of clusters, thus allowing precise breakpoint clustering. Validation across multiple sequencing platforms and datasets demonstrates that SVHunter excels at detecting various types of SVs, with a notable reduction in the false discovery rate. This highlights considerable strong potential for both research and clinical applications.

This study proposes an intelligent scheduling system for high-altitude photovoltaic power generation, utilizing a hybrid optimization approach that combines the Long-nosed Raccoon Optimization Algorithm (COA) and the Black-winged Kite Optimization Algorithm (BKA) (COA-BKA). The goal is to enhance scheduling accuracy, stability, and response speed under the unique environmental conditions of high-altitude regions, such as fluctuating light intensity, extreme temperatures, and dynamic load demands. In experimental comparisons with traditional algorithms like Particle Swarm Optimization (PSO) and Genetic Algorithm (GA), COA-BKA achieved a scheduling accuracy of 0.98, outperforming PSO (0.92) and GA (0.90). COA-BKA also demonstrated superior convergence speed, reaching the optimal solution by the 50th iteration, while PSO and GA required more iterations (80 and 100, respectively). Additionally, COA-BKA completed scheduling in just 4.5 s, significantly faster than PSO (6.3 s) and GA (7.2 s). The system effectively handled fluctuating light intensity and load demand changes, showcasing its robust adaptability. These results suggest that COA-BKA provides a highly efficient and stable solution for intelligent scheduling in high-altitude photovoltaic power systems, improving operational efficiency and reducing costs, while offering significant advancements for real-time optimization in smart grids.

With the development of deep learning techniques and object detectors, the performance of object detection has been rapidly improved. However, since tiny objects contain only a small number of pixels and lack appearance information, this creates difficulties for detector recognition. Although existing research has improved detection performance by fusing different feature layers to enhance feature information of objects, this also leads to the problem of mixed feature information, especially for tiny objects where features are easily covered, which exacerbates the difficulty of recognition. To solve the above problems, we propose a contextual feature enhancement network (CFENet), which is an efficient framework built on anchor-based object detectors. In CFENet, to effectively utilize contextual information around an object to enhance the detection of tiny objects, we use poolFormer to build a backbone to extract object features. To alleviate the feature blending problem caused by feature fusion, we propose a feature suppression module (FSM) that effectively suppresses background information and redundant features to enhance tiny object features. In addition, we utilize the improved Gaussian Wasserstein distance loss to modify the loss function to obtain high-quality bounding boxes, and we further manipulate the shallow feature layer of the output and then add a detection head to enhance the detection of tiny objects. We have conducted extensive experiments on the public datasets AI-TOD, VisDrone, and DOTA to demonstrate the effectiveness of our approach.

Hyperspectral image change detection (HSI-CD) is an important remote sensing technique for identifying fine-grained land-cover change. Deep learning methods such as convolutional neural networks (CNNs) and transformers have achieved good performance in HSI-CD. However, due to the pseudo-changes caused by imaging conditions, the spectral change characteristics within each pixel often exhibit uncertainties. In this study, differing from the traditional deep learning methods, we aimed to relate the abovementioned spectral change uncertainty to the perspective of the quantum state and built a dual-branch hybrid quantum neural network for HSI-CD (QSCDNet). The quantum branch consists of several 2-D quantum spectral change convolutional blocks (QSCCBs). These blocks provide a wider variety of expression forms of the spectral change, independent of the pseudo-change impact, through a parameterized quantum circuit (PQC), to better extract the change information of the spectral features. The CNN branch is designed based on a channel attention network architecture to provide traditional network change features. The output features of the quantum network branch and the CNN branch are then fused based on a cross-domain change feature fusion module (CDFM). The impact of the number of QSCCBs was also analyzed to verify the effectiveness of increasing the depth of the quantum network structure. The proposed method was tested on three public HSI-CD datasets and compared with the state-of-the-art methods to validate its potential in the field of HSI-CD.

Utilizing spaceborne precipitation radar (SR) to evaluate ground-based weather radar (GR) reflectivity consistency is essential for the early detection of performance issues. However, existing SR versus GR matching methods often overlook some error sources, such as insufficient beam coverage and nonuniform precipitation. This study introduces enhanced methods for SR versus GR matching, including beam blocking identification, precipitation uniformity assessment, and improved time matching. Validation was performed using the FY-3G satellite’s precipitation measurement radar (PMR) and four S-band radars in Hunan Province, China. Our analysis demonstrates that integrating clear-sky ground clutter, long-duration precipitation echoes, and terrain data effectively detects actual beam blocking in GR. Selecting data with a time difference of 180 s or less, within 230 km of the GR center, GR reflectivity between 20 and 35 dBZ, and a signal-to-noise ratio (SNR) above 15 dB significantly mitigates random errors in SR versus GR matching results. Additionally, we explore a method for tracking reflectivity deviations within a “ground-satellite-ground” radar network, validated through adjacent GR comparisons. This approach is based on the Changsha Meteorological Radar Calibration Center’s reference radar. The method was validated using adjacent ground radar comparison, showing a correlation between the two methods with a minimum deviation transfer difference of 0.29 dB and a maximum of 1.13 dB. Additionally, the Yiyang radar exhibited slightly higher reflectivity, indicating that the method is both reliable and practically applicable.

Structural variation (SV) is an important form of genomic variation that influences gene function and expression by altering the structure of the genome. Although long-read data have been proven to better characterize SVs, SVs detected from noisy long-read data still include a considerable portion of false-positive calls. To accurately detect SVs in long-read data, we present SVDF, a method that employs a learning-based noise filtering strategy and an SV signature-adaptive clustering algorithm, for effectively reducing the likelihood of false-positive events. Benchmarking results from multiple orthogonal experiments demonstrate that, across different sequencing platforms and depths, SVDF achieves higher calling accuracy for each sample compared to several existing general SV calling tools. We believe that, with its meticulous and sensitive SV detection capability, SVDF can bring new opportunities and advancements to cutting-edge genomic research.