Gene Surfing: An efficient and versatile tool for targeted enzyme mining in metagenomics.

Microbial community studies have established enzymes' pivotal catalytic roles in ecosystem metabolism, yet cultivation-dependent methods fail to exploit uncultured microbial enzyme resources. Metagenomics overcomes this by directly accessing microbial genetic information, but its massive data generation challenges precise enzyme identification: (1) Restricted applicability across varied sample types. (2) Narrow functional scope in target enzyme discovery.

MVSGDR: multi-view stacked graph convolutional network for drug repositioning.

Drug repositioning (DR) presents a cost-effective strategy for drug development by identifying novel therapeutic applications for existing drugs. Current computational approaches remain constrained by their inability to synergize localized substructure patterns with global network semantics, leading to overreliance on data augmentation to mitigate latent drug-disease association (DDA) information gaps. To address these limitations, we present multi-view stacked graph convolutional network (MVSGDR), a novel DR framework featuring three technical innovations: (i) multi-view stacked module that enables depth-wise feature enhancement through hierarchical aggregation of multi-hop neighborhood interactions across distinct graph convolutional layers; (ii) bi-level subgraph transformer module that decomposes DDAs into METIS (a graph partitioning tool) informative subgraphs for breadth-wise analysis of external and internal subgraph drug-disease relationships; and (iii) negative sampling balancing strategy that mitigates sample imbalance through negative sample synthesis.

Heterogeneity-optimized method for predicting immune checkpoint blockade response.

Interpatient tumor heterogeneity manifests as multimodal distributions across genomic, transcriptomic, and microenvironmental profiles. This fundamentally violates the unimodal assumption of conventional machine learning models, impairing immune checkpoint blockade (ICB) response prediction. To resolve this limitation, we propose a heterogeneity-optimized framework that applies K-means clustering to stratify patients into biologically distinct hot-tumor and cold-tumor subgroups, demonstrating superiority over hierarchical/DBSCAN clustering.

GMSR: Gradient-integrated mamba for spectral reconstruction from RGB images.

Mainstream approaches to spectral reconstruction primarily focus on Convolution- and Transformer-based architectures. However, CNN methods fall short in handling long-range dependencies, whereas Transformers are constrained by computational efficiency limitations. Therefore, constructing a efficient spectral reconstruction network while ensuring the quality of reconstructed hyperspectral images (HSIs) has become a major challenge.

MCAMEF-BERT: an efficient deep learning method for RNA N7-methylguanosine site prediction via multi-branch feature integration.

Accurate identification of N7-methylguanosine (m7G) modification sites plays a critical role in uncovering the regulatory mechanisms of various biological processes, including human development, tumor initiation, and progression. However, existing prediction methods still suffer from limited representational power, redundant feature fusion, insufficient utilization of biological prior knowledge, and poor interpretability. In this study, we propose a novel deep learning model named MCAMEF-BERT.

MRDagent: Iterative and Adaptive Parameter Optimisation for stable ctDNA-Based MRD Detection in Heterogeneous Samples.

Motivation: Minimal residual disease (MRD) as critical biomarker for cancer prognosis and management, plays a crucial role in improving patient outcomes. However, detecting minimal residual disease (MRD) via next-generation sequencing (NGS)-based circulating tumor DNA (ctDNA) variant calling remains unstable due to the extremely low variant allele frequency (VAF) and significant inter- and intra-sample heterogeneity. Although parameter optimization can theoretically enhance variants detection performance, achieving stable MRD detection remains challenging due to three key factors: (i) the necessity for individualized parameter tuning across numerous heterogeneous genomic intervals within each sample, (ii) the tightly interdependent parameter requirements across different stages of variant detection workflows, and (iii) the limitations of current automated parameter optimization methods.

Detection of Microscopic Glioblastoma Infiltration in Peritumoral Edema Using Interactive Deep Learning With DTI Biomarkers: Testing via Stereotactic Biopsy.

Background: Microscopic tumor cell infiltration beyond contrast-enhancing regions influences glioblastoma prognosis but remains undetectable using conventional MRI.

Purpose: To develop and evaluate the glioblastoma infiltrating area interactive detection framework (GIAIDF), an interactive deep-learning framework that integrates diffusion tensor imaging (DTI) biomarkers for identifying microscopic infiltration within peritumoral edema.

Study Type: Retrospective.

[Brain midline segmentation method based on prior knowledge and path optimization].

To address the challenges faced by current brain midline segmentation techniques, such as insufficient accuracy and poor segmentation continuity, this paper proposes a deep learning network model based on a two-stage framework. On the first stage of the model, prior knowledge of the feature consistency of adjacent brain midline slices under normal and pathological conditions is utilized. Associated midline slices are selected through slice similarity analysis, and a novel feature weighting strategy is adopted to collaboratively fuse the overall change characteristics and spatial information of these associated slices, thereby enhancing the feature representation of the brain midline in the intracranial region.

Significant spatiotemporal shifts of land cover over the Mongolian Plateau through the past three decades.

Land cover (LC) change is a crucial indicator reflecting the interaction between human activities and ecological environment. In semi-arid and arid regions like the Mongolian Plateau (MP), LC change analysis is particularly meaningful in shaping biodiversity, agricultural and grassland environment, and climate regulation, but long-term spatiotemporal dynamics of LC change in MP remain uncertain. This study employed an intensity analysis approach to investigate LC changes over the MP from 1990 to 2020 by using a fine-scale 30 m resolution land cover dataset generated from multi-source satellite images.

StaDis: Stability distance to detecting out-of-distribution data in computational pathology.

Modern Computational pathology (CPath) models aim to alleviate the burden on pathologists. However, once deployed, these models may generate unreliable predictions when encountering data types not seen during training, potentially causing a trust crisis within the computational pathology community. Out-of-distribution (OOD) detection, acting as a safety measure before model deployment, demonstrates significant promise in ensuring the reliable use of models in real clinical application.

Predicting textbook outcome after pancreaticoduodenectomy for invasive intraductal papillary mucinous neoplasm: An international validation cohort study.

Background: Textbook outcome, a composite measure of optimal recovery, remains poorly defined for invasive intraductal papillary mucinous neoplasm after pancreaticoduodenectomy. This study aimed to develop and validate the first nomogram predicting textbook outcome in this distinct cohort, addressing gaps in tailored prognostic tools for patients meeting contemporary surgical criteria on the basis of high-risk features.

Methods: Using multicenter data from 327 US patients (training cohort) and 152 Chinese patients (external test cohort), we evaluated 43 preoperative and intraoperative variables.

YModPred: an interpretable prediction method for multi-type RNA modification sites in S. cerevisiae based on deep learning.

Background: RNA post-transcriptional modifications involve the addition of chemical groups to RNA molecules or alterations to their local structure. These modifications can change RNA base pairing, affect thermal stability, and influence RNA folding, thereby impacting alternative splicing, translation, cellular localization, stability, and interactions with proteins and other molecules. Accurate prediction of RNA modification sites is essential for understanding modification mechanisms.

Target-aware 3D molecular generation based on guided equivariant diffusion.

Recent molecular generation models for structure-based drug design (SBDD) often produce unrealistic 3D molecules due to the neglect of structural feasibility and drug-like properties. In this paper, we introduce DiffGui, a target-conditioned E(3)-equivariant diffusion model that integrates bond diffusion and property guidance, to address the above challenges. The combination of atom diffusion and bond diffusion guarantees the concurrent generation of both atoms and bonds by explicitly modeling their interdependencies.

Wafer Defect Image Generation Method Based on Improved Styleganv3 Network.

This paper takes a look at training a generator model based on a limited dataset that can fit the distribution of the original dataset, improving the reconstruction ability of wafer datasets. High-fidelity wafer defect image generation remains challenging due to limited real data and poor physical authenticity of existing methods. We propose an enhanced StyleGANv3 framework with two key innovations: (1) a Heterogeneous Kernel Fusion Unit (HKFU) enabling multi-scale defect feature refinement via spatiotemporal attention and dynamic gating; (2) a Dynamic Adaptive Attention Module (DAAM) adaptively boosting discriminator sensitivity.

Correction: Yin et al. Improvement of SAM2 Algorithm Based on Kalman Filtering for Long-Term Video Object Segmentation. 2025, , 4199.

In the original publication [...

VCformer: Variable-Centric Multi-Scale Transformer for Multivariate Time Series Forecasting.

Multivariate time series forecasting is crucial for numerous practical applications ranging from financial markets to climate monitoring. Traditional multivariate time series forecasting methods primarily adopt a time-centric modeling paradigm, applying attention mechanisms to the temporal dimension, which presents significant limitations when handling complex dependencies between variables. To better capture inter-variable interaction patterns, this paper proposes the Variable-Centric Transformer (VCformer), which shifts the attention paradigm from time-centric to variable-centric through sequence transposition.

SimID: Wi-Fi-Based Few-Shot Cross-Domain User Recognition with Identity Similarity Learning.

In recent years, indoor user identification via Wi-Fi signals has emerged as a vibrant research area in smart homes and the Internet of Things, thanks to its privacy preservation, immunity to lighting conditions, and ease of large-scale deployment. Conventional deep-learning classifiers, however, suffer from poor generalization and demand extensive pre-collected data for every new scenario. To overcome these limitations, we introduce SimID, a few-shot Wi-Fi user recognition framework based on identity-similarity learning rather than conventional classification.

SMA-YOLO: A Novel Approach to Real-Time Vehicle Detection on Edge Devices.

Vehicle detection plays a pivotal role in traffic management as a key technology for intelligent traffic management and driverless driving. However, current deep learning-based vehicle detection models face several challenges in practical applications. These include slow detection speeds, large computational and parametric quantities, high leakage and misdetection rates in target-intensive environments, and difficulties in deploying them on edge devices with limited computing power and memory.

Improved U-Shaped Convolutional Neural Network with Convolutional Block Attention Module and Feature Fusion for Automated Segmentation of Fine Roots in Field Rhizotron Imagery.

Accurate segmentation of fine roots in field rhizotron imagery is essential for high-throughput root system analysis but remains challenging due to limitations of traditional methods. Traditional methods for root quantification (e.g.

BIM-Ken: Identifying Disease-Related miRNA Biomarkers Based on Knowledge-Enhanced Bio-Network.

The identification of microRNA (miRNA) biomarkers is crucial in advancing disease research and improving diagnostic precision. Network-based analysis methods are powerful for identifying disease-related biomarkers. However, it is a challenge to generate a robust molecular network that can accurately reflect miRNA interactions and define reliable miRNA biomarkers.

Hybrid EEG Feature Learning Method for Cross-Session Human Mental Attention State Classification.

Background: Decoding mental attention states from electroencephalogram (EEG) signals is crucial for numerous applications such as cognitive monitoring, adaptive human-computer interaction, and brain-computer interfaces (BCIs). However, conventional EEG-based approaches often focus on channel-wise processing and are limited to intra-session or subject-specific scenarios, lacking robustness in cross-session or inter-subject conditions.

Methods: In this study, we propose a hybrid feature learning framework for robust classification of mental attention states, including focused, unfocused, and drowsy conditions, across both sessions and individuals.

Precise Monoisotopic Peak Assignment of Intact Glycopeptides Using Partial Average Mass Matching.

Accurate assignment of monoisotopic peaks plays a crucial role in mass spectrometry-based glycoproteomics, as inaccurate assignment can severely impair both the quantity and credibility of glycopeptide identifications. In this work, we introduce a method that utilizes a partial match between the observed isotopic cluster (ObIC) and the average isotopic cluster (AvgIC) to enable precise monoisotopic peak assignment for intact -glycopeptide identification, MAP-Match (onoisotopic ssignment using artial ). The key aspects of MAP-Match are (1) generation of the AvgIC using the "average elemental composition per Da" data from the Byonic glycan database and (2) stepwise partial matching of the ObIC and AvgIC based on the deviation of their mass centroids to determine which section of the AvgIC matches most closely to the ObIC, thereby deducing the true monoisotopic peak.

Pseudo-distribution elite critics: Enhancing accuracy in reinforcement learning value estimation.

Reinforcement learning has succeeded significantly in developing intelligent agents capable of adeptly navigating complex environments, yet it often encounters limitations due to persistent biases in state-action value estimation. To address this challenge, we introduce the Pseudo-distribution Elite Critics (PEC), an innovative framework designed to enhance sample efficiency and effectively balance overestimation and underestimation biases in Q-value approximations. PEC revolves around the innovative concept of pseudo-distribution representation, which enriches Q-value approximations with distributional characteristics, capturing nuanced variations in Q-values without increasing the number of critics, leading to more refined and precise estimations.

Deciphering chromatin domain, domain community and chromunity for 3D genome maps with Mactop.

Advanced high-throughput chromosome conformation capture techniques, like Hi-C, reveal genome organization into structural units like topologically associating domains (TADs), which are crucial in gene expression regulation. While accurately identifying TADs is vital, distinguishing different types of TAD boundaries and TAD categories remains a significant challenge in genomic research. We develop a Markov clustering-based tool, Mactop, to accurately identify TADs and provide biologically important classifications of TADs and their boundaries.