Search Results (71)

Infrared small target detection (IRSTD) is hindered by low signal-to-noise ratios, minute object scales, and strong target–background similarity. Although long-range skip fusion is exploited in SCTransNet, the global context is insufficiently captured by its convolutional encoder, and the fusion block remains vulnerable to structured clutter. To address these issues, a Mamba-enhanced framework, MixMambaNet, is proposed with three mutually reinforcing components. First, ResBlocks are replaced by a perception-aware hybrid encoder, in which local perceptual attention is coupled with mixed pixel–channel attention along multi-branch paths to emphasize weak target cues while modeling image-wide context. Second, at the bottleneck, dense pre-enhancement is integrated with a selective-scan 2D (SS2D) state-space (Mamba) core and a lightweight hybrid-attention tail, enabling linear-complexity long-range reasoning that is better suited to faint signals than quadratic self-attention. Third, the baseline fusion is substituted with a non-local Mamba aggregation module, where DASI-inspired multi-scale integration, SS2D-driven scanning, and adaptive non-local enhancement are employed to align cross-scale semantics and suppress structured noise. The resulting U-shaped network with deep supervision achieves higher accuracy and fewer false alarms at a competitive cost. Extensive evaluations on NUDT-SIRST, NUAA-SIRST, and IRSTD-1k demonstrate consistent improvements over prevailing IRSTD approaches, including SCTransNet. Full article

Background: Colorectal cancer (CRC) is a major contributor to cancer-related mortality globally. Despite significant advances in therapeutic strategies, CRC continues to exhibit high recurrence rates. This underscores the urgent need for reliable, non-invasive biomarkers to improve diagnostic precision, early detection, and clinical outcomes. Methods: Gene expression datasets from the GEO database were analyzed to identify differentially expressed genes between CRC and normal tissue samples. Hub genes were identified through an integrative approach combining module membership, gene significance, differential expression, and network centrality. Prognostic significance was assessed via overall survival analysis, and diagnostic utility through ROC curve and AUC. Further integrative analysis included immune cell infiltration, promoter methylation, genetic alterations, and regulatory network construction. Results: An integrated approach identified 989 candidate hub genes. Of these, 128 genes demonstrated significant prognostic potential: 67 were associated with poor overall survival and 61 with favorable outcomes. These genes exhibited patterns of co-expression and positive correlations with immune cell infiltration, particularly B cells, dendritic cells, macrophages, mast cells, and monocytes. Twenty-three hub genes, including MACC1, YEATS4, HMMR, TIGD2, CENPE, GNL3, GMPS, NCAPG, RRM1, DLGAP5, YARS2, CCT8, MET, ZWILCH, KPNA2, KIF15, TRUB1, AURKA, NUDT21, PBK, TOMM20, KIAA1549, and MCM4, showed high diagnostic accuracy in distinguishing CRC from normal tissues. Furthermore, 18 hub genes exhibited statistically significant differential promoter methylation and may serve as promising candidates for epigenetic biomarkers in CRC. Conclusions: Our findings provide a strong foundation for developing more accurate multi-gene prognostic and diagnostic panels and personalized therapies for CRC, with the goal of improving clinical outcomes and reducing the global burden of this disease. Full article

Background/Objectives: Thiopurines remain a cornerstone in the management of inflammatory bowel disease (IBD) and gastrointestinal immune diseases but are associated with significant interindividual variability in efficacy and toxicity, mainly influenced by polymorphisms in Thiopurine S-methyltransferase TPMT and Nudix Hydrolase 15 NUDT15. This study aimed to assess the frequency of TPMT and NUDT15 variants in a pediatric cohort and evaluate their clinical impact to support a pharmacogenetic-guided approach to thiopurine therapy. Methods: Eighty-three pediatric patients with IBD and other autoimmune diseases were genotyped for clinically relevant TPMT and NUDT15 variants using two HRM-PCR assays and were confirmed with sequencing. Variant frequencies were compared to expected population data, and clinical records were reviewed to assess thiopurine dosing, tolerance, and adverse events. Results: Among the cohort, six carried heterozygous TPMT variants *1/*3A, while 2 carried the NUDT15 *1/*9 diplotype, with frequencies higher than expected. Among patients with TPMT variant alleles, some needed dose reductions or treatment discontinuation due to adverse effects, while others tolerated standard dosing without significant issues. Notably, no significant differences in adverse reactions were observed between NUDT15 *1/*9 carriers and wild-type patients. Conclusions: Our results confirm the clinical relevance of TPMT and NUDT15 genotyping to personalize thiopurine therapy in pediatric IBD. Routine implementation of rapid genetic testing, combined with therapeutic drug monitoring and a structured management algorithm, may optimize treatment outcomes and minimize preventable toxicity. Full article

Flower pigmentation is a critical trait in plants, influencing ecological interactions and ornamental value. This study investigates the mechanisms underlying petal coloration in Prunus campanulata and its hybrids, Prunus ‘Okame’ and Prunus ‘Yoko’. Morphological analysis revealed consistent flower size across varieties, indicating that color variation is not linked to structural differences. Physiological and biochemical analyses identified stages III and IV as critical for pigmentation, characterized by the significant accumulation of flavonoids and anthocyanins. Metabolomic profiling highlighted flavonoids as the dominant metabolites, with key compounds including chalcones, flavones, and anthocyanins contributing to color formation. Weighted gene co-expression network analysis (WGCNA) further identified several hub genes, including RPL34, NUDT12, and CYP78A9, within modules strongly correlated with pigment accumulation, suggesting their potential non-canonical roles in the coloration process. Environmental factors such as temperature and pH were found to influence pigment stability. Overall, this study provides insights into the genetic and biochemical regulation of flower pigmentation in P. campanulata, emphasizing the central role of flavonoid and anthocyanin biosynthesis. Full article

Acute leukemias are highly aggressive hematologic malignancies that demand intensive chemotherapy regimens. However, drug toxicity remains a major barrier to treatment success and patient survival. In this context, pharmacogenomics offers a promising strategy by identifying single-nucleotide variants (SNVs) that influence drug metabolism, efficacy, and toxicity, ultimately impacting treatment outcomes. This study analyzed data from the ClinPGx/PharmGKB database to identify clinically annotated variants related to chemotherapy response in Acute Myeloid Leukemia (AML) and Acute Lymphoblastic Leukemia (ALL). A total of 24 variants were curated for AML and 57 for ALL. Among these, nonsynonymous variants were most frequent in ALL (31.6%), while synonymous variants predominated in AML (33.3%). Although traditionally considered neutral, synonymous and intronic variants may influence gene expression through regulatory or splicing mechanisms. The analysis revealed clinically significant variants associated with chemotherapy response, particularly in the ABCB1 gene, observed in 12.5% of AML and 10.5% of ALL cases. Several variants, particularly TPMT, NUDT15, ABCC1, SLC28A3, and RARG, were associated with severe adverse effects such as myelotoxicity, mucositis, cardiotoxicity, and hepatotoxicity. This study reinforces the importance of genetic variants in modulating the therapeutic response and toxicity to chemotherapy drugs in acute leukemias. Analysis of ClinPGx/PharmGKB data emphasizes ABCB1 as a potential resistance marker and supports pre-treatment genotyping of genes like TPMT and NUDT15 to prevent severe toxicities. Future advances should include the expansion of pharmacogenetic studies in underrepresented populations and the clinical validation of new markers in prospective trials, aiming to consolidate precision medicine as a routine part of the therapeutic management of acute leukemias. Full article

Recent deep learning methods have achieved promising performance in infrared small target detection (IRSTD) but with high computational cost, limiting deployment or operation on resource-limited scenarios. There is an urgent need to develop both lightweight and high-precision model compression methods. In this paper, we propose a Multi-Directional Contrast Spatial Attention-driven Feature Distillation (DSAD) method for achieving quick and high-performance IRSTD. Specifically, we first extract feature maps from teacher and student networks. Then, a standard Gaussian transformation is adopted to eliminate magnitude effects. After that, a Multi-Directional Contrast Spatial Attention (DSA) is designed to capture multi-directional spatial information from teacher features, which can make student networks pay more attention to small target areas while suppressing background. Finally, we propose a Perceptual Weighted Mean Square Error (PWMSE) distillation loss by combining the DSA with feature discrepancies, guiding student networks to learn more effective information from small target features. Experimental results on the two benchmark datasets (e.g., NUDT-SIRST and NUAA-SIRST) demonstrate that our distillation method can achieve remarkable detection performance compared with the teacher counterparts on several benchmark IRSTD networks (e.g., DNANet, AMFU-Net, and DMFNet) and introduce consistent gains in inference speed (i.e., 2× more) on edge devices (NVIDIA AGX and HUAWEI Ascend-310B). Full article

Nucleotide diphosphate hydrolase type 5 (NUDT5) plays a significant role in the estrogen-signaling pathway and is overexpressed in breast cancer. This study aimed to explore the anti-breast cancer potential of quercetin and its 52 structural analogs by targeting the NUDT5 enzyme using the in silico molecular docking method. Moreover, Molecular Mechanics/General Born Surface Area (MM/GBSA) calculations were performed for compounds with superior binding affinity scores than quercetin. Their drug-likeness, according to Lipinski’s rule of five, water solubility, and Caco-2 permeability were predicted. In addition, the absorption, distribution, metabolism, excretion, and toxicity (ADMET) profile was determined for the top-scoring compounds from the docking studies and MM/GBSA calculations, as well as for those that complied with the rules of Lipinski and exhibited high permeability. The obtained results showed that all the tested ligands interact with the active site of NUDT5. Their binding energies ranged from −11.24 to −7.36 kcal/mol. The MM/GBSA calculations further supported the binding affinity predictions. ADMET analysis enabled the selection of compounds with favorable pharmacokinetic profiles in comparison to quercetin. Quercetin analogs L1 and L28 were identified as promising anti-breast cancer drug candidates worthy of further experimental evaluation. Full article

Infrared small target detection (IRSTD) remains a critical yet challenging task due to the inherent low signal-to-noise ratio, weak target features, and complex backgrounds prevalent in infrared images. Existing methods often struggle to effectively capture the subtle edge features of targets and suppress background clutter simultaneously. To address these limitations, this study proposed a novel Multi-directional Learnable Edge-assisted Dense Nested Attention Network (MLEDNet). Firstly, we propose a multi-directional learnable edge extraction module (MLEEM), which is designed to capture rich directional edge information. The extracted multi-directional edge features are hierarchically integrated into the dense nested attention module (DNAM) to significantly enhance the model’s capability in discerning the crucial edge features of infrared small targets. Then, we design a feature fusion module guided by residual channel spatial attention (ResCSAM-FFM). This module leverages spatio-channel contextual cues to intelligently fuse features across different levels output by the DNAM, effectively enhancing target representation while robustly suppressing complex background interferences. By combining the MLEEM and the ResCSAM-FFM within a dense nested attention framework, we present a new model named MLEDNet. Extensive experiments conducted on benchmark datasets NUDT-SIRST and NUAA-SIRST demonstrate that the proposed MLEDNet achieves superior performance compared to state-of-the-art methods. Full article

Infrared dim and small target detection aims to accurately localize targets within complex backgrounds or clutter. However, under extremely low signal-to-noise ratio (SNR) conditions, single-frame detection methods often fail to effectively detect such targets. In contrast, multi-frame detection can exploit temporal cues to significantly improve the probability of detection (Pd) and reduce false alarms (Fa). Existing multi-frame approaches often employ 3D convolutions/RNNs to implicitly extract temporal features. However, they typically lack explicit modeling of target motion. To address this, we propose a Dual Encoder–Decoder Multi-Frame Infrared Small Target Detection Network with Motion Encoding (DEMNet) that explicitly incorporates motion information into the detection process. The first multi-level encoder–decoder module leverages spatial and channel attention mechanisms to fuse hierarchical features across multiple scales, enabling robust spatial feature extraction from each frame of the temporally aligned input sequence. The second encoder–decoder module encodes both inter-frame target motion and intra-frame target positional information, followed by 3D convolution to achieve effective motion information fusion. Extensive experiments demonstrate that DEMNet achieves state-of-the-art performance, outperforming recent advanced methods such as DTUM and SSTNet. For the DAUB dataset, compared to the second-best model, DEMNet improves Pd by 2.42 percentage points and reduces Fa by 4.13 × 10⁻⁶ (a 68.72% reduction). For the NUDT dataset, it improves Pd by 1.68 percentage points and reduces Fa by 0.67 × 10⁻⁶ (a 7.26% reduction) compared to the next-best model. Notably, DEMNet demonstrates even greater advantages on test sequences with SNR ≤ 3. Full article

Mobile traffic classification serves as a fundamental component in network security systems. In recent years, pre-training methods have significantly advanced this field. However, as mobile traffic is typically mixed with third-party services, the deep integration of such shared services results in highly similar TCP flow characteristics across different applications. This makes it challenging for existing traffic classification methods to effectively identify mobile traffic. To address the challenge, we propose MS-PreTE, a two-phase pre-training framework for mobile traffic classification. MS-PreTE introduces a novel multi-level representation model to preserve traffic information from diverse perspectives and hierarchical levels. Furthermore, MS-PreTE incorporates a focal-attention mechanism to enhance the model’s capability in discerning subtle differences among similar traffic flows. Evaluations demonstrate that MS-PreTE achieves state-of-the-art performance on three mobile application datasets, boosting the F1 score for Cross-platform (iOS) to 99.34% (up by 2.1%), Cross-platform (Android) to 98.61% (up by 1.6%), and NUDT-Mobile-Traffic to 87.70% (up by 2.47%). Moreover, MS-PreTE exhibits strong generalization capabilities across four real-world traffic datasets. Full article

Thiopurines are employed in inflammatory bowel diseases (IBDs; Crohn’s disease, CD; ulcerative colitis, UC) to induce remission, prevent relapse, and reduce the steroid dosage, although they can sometimes be ineffective and present side effects. Genetic variations in the TPMT and NUDT15 genes are well recognized to influence the therapeutic response, despite notable regional differences in their frequencies across various ethnic populations. Herein, the risk haplotypes TPMT*3A, *3B, *3C, and the variant NUDT15*3 were examined in a retrospective cohort of 383 Italian IBD patients who received azathioprine or 6-mercaptopurine. TPMT and NUDT15 genotyping was performed by Sanger sequencing and TaqMan allelic discrimination, respectively. Allelic and genotype frequencies and genotype–phenotype correlations in non-responder and intolerant patients were assessed in comparison to responders. In total, 17% of patients did not respond to treatment, while 20% experienced adverse events, with leukopenia found in 13% of patients. TPMT haplotypes were found in 3.1% of patients, and 1.6% had the NUDT15*3 variant. CD patients with leukopenia had a higher frequency of the TPMT risk haplotype (40% vs. 4%, p = 0.024). Although additional validation through larger prospective studies or meta-analyses is needed, our findings support the importance of TPMT gene-variant assessment for forecasting azathioprine-related leukopenia in Italian IBD patients. Full article

Fibro-adipogenic progenitor cells (FAPs) support muscle tissue homeostasis, regulate muscle growth, injury repair, and fibrosis, and activate muscle progenitor cell differentiation to promote regeneration. We aimed to investigate the effects of co-culturing FAPs with muscle satellite cells (MuSCs) on myogenic differentiation. Proteomic profiling of co-culture supernatants identified significant DCX, IMP2A, NUDT16L1, SLC38A2, and IL-6 upregulation. Comparative transcriptomics of mono-cultured versus co-cultured MuSCs revealed differential expression of oxidative stress-related genes (HMOX1, ALOX5, GSTM3, TRPM2, PADI1, and CTSL). Pathway enrichment analyses highlighted cell cycle regulation, TNF signaling, and ferroptosis. Gene ontology analysis of MuSCs indicated significant gene enrichment in myosin-related components. Combined transcriptomic and proteomic analyses demonstrated HO-1 downregulation at the transcriptional and translational levels, with altered pathways being predominantly related to myosin filament, muscle system process, and muscle contraction cellular components. HO-1 knockdown reduced intracellular iron accumulation in MuSCs, suppressing iron-dependent autophagy. This alleviated oxidative stress and promoted myogenic differentiation. Exogenous IL-6 (0.1 ng/mL) downregulated HO-1 expression, initiating an identical regulatory cascade, while HO-1 overexpression reversed the IL-6-mediated reduction in the expression of the autophagy markers LC3 and ATG5, suppressing myogenic enhancement. This establishes the co-culture-induced IL-6/HO-1 axis as a core regulator of iron-dependent oxidative stress and autophagy during myogenic differentiation. Full article

The management of acute lymphoblastic leukemia (ALL), the most common pediatric malignancy, critically relies on thiopurine therapy, such as 6-mercaptopurine (6-MP), during the maintenance phase. However, significant inter-individual response variety and high risk of myelosuppression often disrupt therapy efficacy. Pharmacogenetics offer crucial strategies to personalized therapy. While thiopurine methyltransferase (TPMT) was initially the primary focus, the discovery of nudix hydrolase 15 (NUDT15) appears as a more comprehensive determinant of thiopurine intolerance. This review aims to consolidate and critically evaluate the advancement achieved in unraveling the biological mechanism and clinical significance of NUDT15 pharmacogenetics in thiopurine therapy. Foundational studies showed the vital role of NUDT15 in the detoxification of active thiopurines, with common genetic variants (for instance, p. Arg139Cys) significantly disrupting its activity, leading to the accumulation of toxic metabolites. Observational studies consistently associated NUDT15 variants with severe myelosuppression, notably in Asian populations. Recent randomized controlled trials (RCTs) confirmed that NUDT15 genotype-guided dosing effectively reduces thiopurine-induced toxicity without interfering with the therapeutic outcome. Despite these advancements, challenges remain present, including the incomplete characterization of rare variants, limited data in the diverse Asian populations, and the need for standardized integration with metabolite monitoring. In conclusion, NUDT15 pharmacogenetics is essential for improving patient safety and thiopurine dosage optimization in the treatment of ALL. For thiopurine tailored medicine to be widely and fairly implemented, future research should focus on increasing genetic data across different populations, improving the dose adjustment algorithm, and harmonizing therapeutic guidelines. Full article

Detecting small targets in infrared imagery remains highly challenging due to sub-pixel target sizes, low signal-to-noise ratios, and complex background clutter. This paper proposes PSHNet, a hybrid deep-learning framework that combines dense spatial heatmap supervision with geometry-aware regression for accurate infrared small-target detection. The network generates position–scale heatmaps to guide coarse localization, which are further refined through sub-pixel offset and size regression. A Complete IoU (CIoU) loss is introduced as a geometric regularization term to improve alignment between predicted and ground-truth bounding boxes. To better preserve fine spatial details essential for identifying small thermal signatures, an Enhanced Low-level Feature Module (ELFM) is incorporated using multi-scale dilated convolutions and channel attention. Experiments on the NUDT-SIRST and IRSTD-1k datasets demonstrate that PSHNet outperforms existing methods in IoU, detection probability, and false alarm rate, achieving IoU improvement and robust performance under low-SNR conditions. Full article

Infrared small target detection (IRSTD) aims to locate and separate targets from complex backgrounds. The challenges in IRSTD primarily come from extremely sparse target features and strong background clutter interference. However, existing methods typically perform discrimination directly on the features extracted by deep networks, neglecting the distinct characteristics of weak and small targets in the frequency domain, thereby limiting the improvement of detection capability. In this paper, we propose a frequency-aware masked-attention network (FM-Net) that leverages multi-scale frequency clues to assist in representing global context and suppressing noise interference. Specifically, we design the wavelet residual block (WRB) to extract multi-scale spatial and frequency features, which introduces a wavelet pyramid as the intermediate layer of the residual block. Then, to perceive global information on the long-range skip connections, a frequency-modulation masked-attention module (FMM) is used to interact with multi-layer features from the encoder. FMM contains two crucial elements: (a) a mask attention (MA) mechanism for injecting broad contextual feature efficiently to promote full-level semantic correlation and focus on salient regions, and (b) a channel-wise frequency modulation module (CFM) for enhancing the most informative frequency components and suppressing useless ones. Extensive experiments on three benchmark datasets (e.g., SIRST, NUDT-SIRST, IRSTD-1k) demonstrate that FM-Net achieves superior detection performance. Full article