Search Results (863)

Background: Due to complex signal characteristics and distinct individual differences, the decoding of a motor imagery electroencephalogram (MI-EEG) is limited by the unsatisfactory performance of suboptimal traditional models. Methods: A subject-independent model named MSEI-ENet is proposed for multiple-task MI-EEG decoding. It employs a specially designed multi-scale structure EEG-inception module (MSEI) for comprehensive feature learning. The encoder module further helps to detect discriminative information by its multi-head self-attention layer with a larger receptive field, which enhances feature representation and improves recognition efficacy. Results: The experimental results on Competition IV dataset 2a showed that our proposed model yielded an overall accuracy of 94.30%, MF1 score of 94.31%, and Kappa of 0.92. Conclusions: A performance comparison with state-of-the-art methods demonstrated the effectiveness and generalizability of the proposed model on challenging multi-task MI-EEG decoding. Full article

The Connexin43 transmembrane protein (Cx43), encoded by the GJA1 gene, is a member of a multigenic family of proteins that oligomerize to form hemichannels and intercellular channels, allowing gap junctional intercellular communication between adjacent cells or communication between the intracellular and extracellular compartments. Cx43 has long been shown to play a significant but complex role in cancer development, acting as a tumor suppressor and/or tumor promoter. The effects of Cx43 are associated with both channel-dependent and -independent functionalities and differ depending on the expression level, subcellular location and the considered stage of cancer progression. Recently, six isoforms of Cx43 have been described and one of them, called GJA1-20k, has also been found to be expressed in cancer cells. This isoform is generated by alternative translation and corresponds to the end part of the fourth transmembrane domain and the entire carboxyl-terminal (CT) domain. Initial studies in the cardiac model implicated GJA1-20k in the trafficking of full-length Cx43 to the plasma membrane, in cytoskeletal dynamics and in mitochondrial fission and subcellular distribution. As these processes are associated with cancer progression, a potential link between Cx43 functions, mitochondrial activity and GJA1-20k expression can be postulated in this context. This review synthetizes the current knowledge on GJA1-20k and its potential involvement in processes related to epithelial-to-mesenchymal transition (EMT) and the proliferation, dissemination and quiescence of cancer cells. Particular emphasis is placed on the putative roles of GJA1-20k in full-length Cx43 exportation to the plasma membrane, mitochondrial activity and functions originally attributed to the CT domain. Full article

Background/Objectives: Lactic acid bacteria (LAB) produce several diverse metabolites during fermentation that play key roles in enhancing health and food quality. These metabolites include peptides, organic acids, exopolysaccharides, and antimicrobial compounds, which contribute to gut health, immune system modulation, and pathogen inhibition. This study analyzed the intracellular (Met-Int) and extracellular metabolites (Met-Ext-CFS; cell-free supernatant) of Lactiplantibacillus plantarum UTNGt2, a probiotic strain isolated from Theobroma grandiflorum. Methods: The assessment was performed using capillary LC-MS/MS metabolomics with a SWATH-based data-independent acquisition approach to identify molecules associated with antimicrobial activity. Results: The integration of metabolomic data with whole-genome annotation enabled the identification of several key metabolites, including amino acids, nucleotides, organic acids, oligopeptides, terpenes, and flavonoids, many of which were associated with the antimicrobial activity of UTNGt2. Pathway analysis reveals critical processes such as secondary metabolite biosynthesis, nucleotide and galactose metabolism, and cofactor biosynthesis. By integrating RiPP (ribosomally synthesized and post-translationally modified peptide) cluster gene predictions with LC-MS data, this study validates the production of specific RiPPs and uncovers novel bioactive compounds encoded within the UTNGt2 genome. The oligopeptide val-leu-pro-val-pro-gln found in both Met-Int (ESI+) and Met-Ext-CFS (ESI+) may contribute to the strain’s antimicrobial strength. It could also enhance probiotic and fermentation-related functions. Conclusions: While genome-based predictions highlight the strain’s biosynthetic potential, the actual metabolite profile is influenced by factors like transcriptional regulation, post-transcriptional and post-translational modifications, and environmental conditions. These findings emphasize the value of multi-omics approaches in providing a holistic understanding of metabolite production and its role in antimicrobial activity. Full article

Using deep learning or artificial intelligence (AI) in research with animals is a new interdisciplinary area of research. In this study, we have explored the potential of thermal imaging and AI in pig research. Thermal cameras play a vital role in obtaining and collecting a large amount of data, and AI has the capabilities of processing and extracting valuable information from these data. The amount of data collected using thermal imaging is huge, and automation techniques are therefore crucial to find a meaningful interpretation of the changes in temperature. In this paper, we present a complete pipeline to extract temperature automatically from a selected Region of Interest (ROI). This system consists of three stages: the first one checks whether the ROI is completely visible to observe the thermal temperature, and then the second stage uses an encoder–decoder structure of a convolution neural network to segment the ROI, if the condition was met at stage one. In the last stage, the maximum temperature is extracted and saved in an external file. The segmentation model showed good performance, with a mean Pixel Class accuracy of 92.3%, and a mean Intersection over Union of 87.1%. The extracted temperature observed by the model entirely matched the manually observed temperature. The system showed reliable results to be used independently without human intervention to determine the temperature in the selected ROI in pigs. Full article

Chromosome 21 DYRK1A kinase is associated with a variety of neuronal diseases including Down syndrome. However, the functional impact of this kinase at the synapse level remains unclear. We studied a mouse model that incorporated YAC 152F7 (570 kb), encoding six chromosome 21 genes including DYRK1A. The 152F7 mice displayed learning difficulties but their N-methyl-D-aspartate (NMDA)-dependent synaptic long-term potentiation is indistinguishable from non-transgenic animals. We have demonstrated that a presynaptic form of NMDA-independent long-term potentiation (LTP) at the hippocampal mossy fiber was impaired in the 152F7 animals. To obtain insights into the molecular mechanisms involved in such synaptic changes, we analyzed the Dyrk1a interactions with chromatin remodelers. We found that the number of DYRK1A-EP300 and DYRK1A-CREBPP increased in 152F7 mice. Moreover, we observed a transcriptional decrease in genes encoding presynaptic proteins involved in glutamate vesicle exocytosis, namely Rims1, Munc13-1, Syn2 and Rab3A.To refine our findings, we used a mouse BAC 189N3 (152 kb) line that only triplicates the gene Dyrk1a. Again, we found that this NMDA-independent form of LTP is impaired in this mouse line. Altogether, our results demonstrate that Dyrk1a up-regulation is sufficient to specifically inhibit the NMDA-independent form of LTP and suggest that this inhibition is linked to chromatin changes that deregulate genes encoding proteins involved in glutamate synaptic release. Full article

Accurate Remaining Useful Life (RUL) prediction is vital for effective prognostics in and the health management of industrial equipment, particularly under varying operational conditions. Existing approaches to multi-condition RUL prediction often treat each working condition independently, failing to effectively exploit cross-condition knowledge. To address this limitation, this paper introduces MoEFormer, a novel framework that combines a Mixture of Encoders (MoE) with a Transformer-based architecture to achieve precise multi-condition RUL prediction. The core innovation lies in the MoE architecture, where each encoder is designed to specialize in feature extraction for a specific operational condition. These features are then dynamically integrated through a gated mixture module, enabling the model to effectively leverage cross-condition knowledge. A Transformer layer is subsequently employed to capture temporal dependencies within the input sequence, followed by a fully connected layer to produce the final prediction. Additionally, we provide a theoretical performance guarantee for MoEFormer by deriving a lower bound for its error rate. Extensive experiments on the widely used C-MAPSS dataset demonstrate that MoEFormer outperforms several state-of-the-art methods for multi-condition RUL prediction. Full article

Introduction: This study introduces a fully differentiable, end-to-end audio transformation network designed to overcome these limitations by operating directly on acoustic features. Methods: The proposed method employs an encoder–decoder architecture with a global conditioning mechanism. It eliminates the need for parallel utterances, intermediate phonetic representations, and speaker-independent ASR systems. The system is evaluated on tasks of voice conversion and musical style transfer using subjective and objective metrics. Results: Experimental results demonstrate the model’s efficacy, achieving competitive performance in both seen and unseen target scenarios. The proposed framework outperforms seven existing systems for audio transformation and aligns closely with state-of-the-art methods. Conclusion: This approach simplifies feature engineering, ensures vocabulary independence, and broadens the applicability of audio transformations across diverse domains, such as personalized voice assistants and musical experimentation. Full article

Developmental and epileptic encephalopathies (DEEs) are a group of neuropediatric diseases associated with epileptic seizures, severe delay or regression of psychomotor development, and cognitive and behavioral deficits. What sets DEEs apart is their complex interplay of epilepsy and developmental delay, often driven by genetic factors. These two aspects influence one another but can develop independently, creating diagnostic and therapeutic challenges. Intellectual disability is severe and complicates potential treatment. Pathogenic variants are found in 30–50% of patients with DEE. Many genes mutated in DEEs encode ion channels, causing current conduction disruptions known as channelopathies. Although channelopathies indeed make up a significant proportion of DEE cases, many other mechanisms have been identified: impaired neurogenesis, metabolic disorders, disruption of dendrite and axon growth, maintenance and synapse formation abnormalities —synaptopathies. Here, we review recent publications on non-channelopathies in DEE with an emphasis on the mechanisms linking epileptiform activity with intellectual disability. We focus on three major mechanisms of intellectual disability in DEE and describe several recently identified genes involved in the pathogenesis of DEE. Full article

Traditional sparse coding has proven to be an effective method for image feature representation in recent years, yielding promising results in image classification. However, it faces several challenges, such as sensitivity to feature variations, code instability, and inadequate distance measures. Additionally, image representation and classification often operate independently, potentially resulting in the loss of semantic relationships. To address these issues, a new method is proposed, called Histogram intersection and Semantic information-based Non-negativity Local Laplacian Sparse Coding (HS-NLLSC) for image classification. This method integrates Non-negativity and Locality into Laplacian Sparse Coding (NLLSC) optimisation, enhancing coding stability and ensuring that similar features are encoded into similar codewords. In addition, histogram intersection is introduced to redefine the distance between feature vectors and codebooks, effectively preserving their similarity. By comprehensively considering both the processes of image representation and classification, more semantic information is retained, thereby leading to a more effective image representation. Finally, a multi-class linear Support Vector Machine (SVM) is employed for image classification. Experimental results on four standard and three maritime image datasets demonstrate superior performance compared to the previous six algorithms. Specifically, the classification accuracy of our approach improved by 5% to 19% compared to the previous six methods. This research provides valuable insights for various stakeholders in selecting the most suitable method for specific circumstances. Full article

This paper introduces a novel joint model architecture for Speech Emotion Recognition (SER) that integrates both discrete and dimensional emotional representations, allowing for the simultaneous training of classification and regression tasks to improve the comprehensiveness and interpretability of emotion recognition. By employing a joint loss function that combines categorical and regression losses, the model ensures balanced optimization across tasks, with experiments exploring various weighting schemes using a tunable parameter to adjust task importance. Two adaptive weight balancing schemes, Dynamic Weighting and Joint Weighting, further enhance performance by dynamically adjusting task weights based on optimization progress and ensuring balanced emotion representation during backpropagation. The architecture employs parallel feature extraction through independent encoders, designed to capture unique features from multiple modalities, including Mel-frequency Cepstral Coefficients (MFCC), Short-term Features (STF), Mel-spectrograms, and raw audio signals. Additionally, pre-trained models such as Wav2Vec 2.0 and HuBERT are integrated to leverage their robust latent features. The inclusion of self-attention and co-attention mechanisms allows the model to capture relationships between input modalities and interdependencies among features, further improving its interpretability and integration capabilities. Experiments conducted on the IEMOCAP dataset using a leave-one-subject-out approach demonstrate the model’s effectiveness, with results showing a 1–2% accuracy improvement over classification-only models. The optimal configuration, incorporating the joint architecture, dynamic weighting, and parallel processing of multimodal features, achieves a weighted accuracy of 72.66%, an unweighted accuracy of 73.22%, and a mean Concordance Correlation Coefficient (CCC) of 0.3717. These results validate the effectiveness of the proposed joint model architecture and adaptive balancing weight schemes in improving SER performance. Full article

Interleukin-6 (IL-6) is a potent glycoprotein that plays a crucial role in regulating innate and adaptive immunity, as well as metabolism. The expression and release of IL-6 are closely correlated with the severity of various diseases. IL-6-inducing peptides are critical for the development of immunotherapy and diagnostic biomarkers for some diseases. Most existing methods for predicting IL-6-induced peptides use traditional machine learning methods, whose feature selection is based on prior knowledge. In addition, none of these methods take into account the three-dimensional (3D) structure of peptides, which is essential for their functional properties. In this study, we propose a novel IL-6-inducing peptide prediction method called DGIL-6, which integrates 3D structural information with graph neural networks. DGIL-6 represents a peptide sequence as a graph, where each amino acid is treated as a node, and the adjacency matrix, representing the relationships between nodes, is derived from the predicted residue contact graph of the peptide sequence. In addition to commonly used amino acid representations, such as one-hot encoding and position encoding, the pre-trained model ESM-1b is employed to extract amino acid features as node features. In order to simultaneously consider node weights and information updates, a dual-channel method combining Graph Attention Network (GAT) and Graph Convolutional Network (GCN) is adopted. Finally, the extracted features from both channels are merged for the classification of IL-6-inducing peptides. A series of experiments including cross-validation, independent testing, ablation studies, and visualizations demonstrate the effectiveness of the DGIL-6 method. Full article

Wind speed forecasting is an essential part of weather prediction, with significant value in economics, business, and management. Utilizing multiple meteorological variables can improve prediction accuracy, but existing methods face challenges such as mixing and noise due to variable differences, as well as difficulty in capturing complex spatio-temporal dependencies. To address these issues, this study introduces a novel short-term wind speed forecasting model named as MIESTC. The proposed model employs an independent encoder to extract features from each meteorological variable, mitigating the issues of noise that are caused by variable mixing. Then, a multivariate spatio-temporal correlation module is used to capture the global spatio-temporal dependencies between variables and model their interactions. Experimental results on the ERA5-LAND dataset show that, compared to the ConvLSTM, UNET, and SimVP models, the MIESTC model reduces RMSE by 14.60%, 8.64%, and 10.41%, respectively, for a 1 h prediction duration. For a 6 h prediction duration, the corresponding reductions are 13.91%, 8.20%, and 6.95%, validating its superior performance in short-term wind speed forecasting. Furthermore, an analysis of variable impacts reveals that U10, V10, and T2M play dominant roles in wind speed prediction, while TP exhibits a relatively lower impact, aligning with the results of the correlation analysis. These findings underscore the potential of MIESTC as an effective and reliable tool for short-term wind speed prediction. Full article

The trans-translation system, mediated by transfer-messenger RNA (tmRNA, encoded by the ssrA gene) and its partner protein SmpB, helps to release ribosomes stalled on defective mRNA and targets incomplete protein products for hydrolysis. Knocking out the ssrA and smpB genes in various pathogens leads to different phenotypic changes, indicating that they have both cooperative and independent functionalities. This study aimed to clarify the functional relationships between tmRNA and SmpB in Aeromonas veronii, a pathogen that poses threats in aquaculture and human health. We characterized the expression dynamics of the ssrA and smpB genes at different growth stages of the pathogen, assessed the responses of deletion strains ΔssrA and ΔsmpB to various environmental stressors and carbon source supplementations, and identified the gene-regulatory networks involving both genes by integrating transcriptomic and phenotypic analyses. Our results showed that the gene ssrA maintained stable expression throughout the bacterial growth period, while smpB exhibited upregulated expression in response to nutrient deficiencies. Compared to the wild type, both the ΔssrA and ΔsmpB strains exhibited attenuated resistance to most stress conditions. However, ΔssrA independently responded to starvation, while ΔsmpB specifically showed reduced resistance to lower concentrations of Fe³⁺ and higher concentrations of Na⁺ ions, as well as increased utilization of the carbon source β-Methyl-D-glucoside. The transcriptomic analysis supported these phenotypic results, demonstrating that tmRNA and SmpB cooperate under nutrient-deficient conditions but operate independently in nutrient-rich environments. Phenotypic experiments confirmed that SsrA and SmpB collaboratively regulate genes involved in siderophore synthesis and iron uptake systems in response to extracellular iron deficiency. The findings of the present study provide crucial insights into the functions of the trans-translation system and highlight new roles for tmRNA and SmpB beyond trans-translation. Full article

Laodelphax striatellus permutotetra-like virus (LsPLV) is a novel insect virus identified via small RNA deep sequencing. At present, there is a lack of awareness of LsPLV, restricting research on its utilization in biocontrol. In this paper, the full-length genome of LsPLV was cloned and analyzed, then viral capsid protein (CP) was expressed and prepared as an antibody, and CP property was tested. It was found that the LsPLV genome was 4667 nt in length, encoding two proteins, RNA-dependent RNA polymerase (RdRP) and CP, and the palm subdomain conserved region in RdRp was arranged in a “C–A–B” permutation pattern, exhibiting the typical characteristics of permutotetra-like viruses. Phylogenetic analysis suggested that LsPLV shared the highest homology (excluding LsPLV1) with a Nodaviridae virus (QLI47702.1), and their nucleotide identities of RdRP and CP were 55.4% and 59.2%, respectively. After expression, purified CP exhibited two bands of 60 kDa and 47 kDa, suggesting a potential cleavage in the protein. LsPLV CP in L. striatellus was detected by Western blot, and except for the complete CP band, the specific bands with molecular weights lower than CP were also detected, indicating that CP underwent cleavage. Detection of purified CP in vitro showed that the cleavage could occur independent of any protease, confirming that CP has self-cleavage characteristics. Full article

Chitin deacetylases (CDAs) are carbohydrate esterases associated with chitin metabolism and the conversion of chitin into chitosan. Studies have demonstrated that chitin deacetylation is essential for chitin organization and compactness and therefore influences the mechanical and permeability properties of chitinous structures, such as the peritrophic membrane (PM) and cuticle. In the present study, two genes (ApCDA5a and ApCDA5b) encoding CDA protein isoforms were identified and characterized in Chinese oak silkworm (Antheraea pernyi) larvae. Although five signature motifs were identified, CDA5 proteins only have the chitin-deacetylated catalytic domain. Spatiotemporal expression pattern analyses revealed that both transcripts presented the highest abundance in the anterior region of the midgut during the feeding period after molting, suggesting their role in chitin turnover and PM assembly. The down-regulation of ApCDA5a and ApCDA5b via RNA interference (RNAi) was correlated with the breakage of chitin microfibrils in the PM, suggesting that group V CDAs were essential for the growth and assembly of the chitinous layer. Additionally, ApCDA5a and ApCDA5b may have non-overlapping functions that regulate the morphological characteristics of PM chitin construction in different ways. Larvae injected with double-stranded RNA (dsRNA) against ApCDA5a and ApCDA5b transcripts were less resistant to infection by N. pernyi than those in the control groups. These results revealed that down-regulating ApCDA5a and ApCDA5b had independent effects on the PM structure and undermined the intactness of the PM, which disrupted the function of the PM against microsporidia infection per os. Our data provide new evidence for differentiating CDA functions among group V CDAs in lepidopteran insects. Full article