Explore the vast range of titles available.

Graph neural networks (GNNs), which learn node representations via aggregating their neighbors, have shown superior performance and become the de facto efficient toolkit for analyzing and learning from data with structured properties. However, most existing GNNs are designed for static graphs and assume fixed graph structures and node sets. In many real-world applications, graphs evolve continuously over time-with nodes and edges appearing or disappearing-rendering static models insufficient for capturing these temporal dynamics. In this paper, we propose Evolving Graph Attention Networks (EGAT), a novel framework for dynamic graph representation learning. Specifically, EGAT leverages the anisotropic attention mechanism of Graph Attention Networks (GATs) to capture complex inter-node relationships. Crucially, the multi-head attention weights of the GAT are evolved over time via a recurrent neural network (RNN), enabling the model to adaptively adjust the importance of different neighbors as the graph topology and relational dynamics change. This weight-evolving paradigm couples the anisotropic attention mechanism of GATs with a recurrent subnetwork, enabling the joint modeling of topological evolution and temporal relational dynamics. Extensive experiments on benchmark datasets demonstrate that the proposed model consistently outperforms state-of-the-art baselines.

Data-driven approaches were applied to investigate the temporal and spatial changes of 1,022 individuals of wild yellowfin goby and its potential interaction with the estuarine environment in Japan. Nuclear magnetic resonance (NMR)-based metabolomics revealed that growth stage is a primary factor affecting muscle metabolism. Then, the metabolic, elemental and microbial profiles of the pooled samples generated according to either the same habitat or sampling season as well as the river water and sediment samples from their habitats were measured using NMR spectra, inductively coupled plasma optical emission spectrometry and next-generation 16 S rRNA gene sequencing. Hidden interactions in the integrated datasets such as the potential role of intestinal bacteria in the control of spawning migration, essential amino acids and fatty acids synthesis in wild yellowfin goby were further extracted using correlation clustering and market basket analysis-generated networks. Importantly, our systematic analysis of both the seasonal and latitudinal variations in metabolome, ionome and microbiome of wild yellowfin goby pointed out that the environmental factors such as the temperature play important roles in regulating the body homeostasis of wild fish.

Delta compression, as a complementary technique for data deduplication, has gained widespread attention in network storage systems. It can eliminate redundant data between non‐duplicate but similar chunks that cannot be identified by data deduplication. The network transmission overhead between servers and clients can be greatly reduced by using data deduplication and delta compression techniques. Resemblance detection is a technique that identifies similar chunks for post‐deduplication delta compression in network storage systems. The existing resemblance detection approaches fail to detect similar chunks with arbitrary similarity by setting a similarity threshold, which can be suboptimal. In this paper, the authors propose Chunk2vec, a resemblance detection scheme for delta compression that utilizes deep learning techniques and Approximate Nearest Neighbour Search technique to detect similar chunks with any given similarity range. Chunk2vec uses a deep neural network, Sentence‐BERT, to extract an approximate feature vector for each chunk while preserving its similarity with other chunks. The experimental results on five real‐world datasets indicate that Chunk2vec improves the accuracy of resemblance detection for delta compression and achieves higher compression ratio than the state‐of‐the‐art resemblance detection technique. The existing resemblance detection approaches fail to identify similar chunks with arbitrary similarity by setting a similarity threshold. In this work, the authors propose a novel resemblance detection scheme called Chunk2vec, which uses a deep neural network, Sentence‐BERT, to extract an approximate feature vector for each chunk while preserving its similarity with other chunks and applies the Approximate Nearest Neighbour Search technique to find the chunk's fingerprint feature vector with any given similarity range. This novel approach can significantly improve the accuracy of resemblance detection for post‐deduplication delta compression and greatly reduces the network transmission overhead between servers and clients.

It is essential to estimate the indoor pesticides/insecticides exposure risk since reports show that 80% of human exposure to pesticides occurs indoors. As one of the three major contamination sources, surface collected pesticides contributed significantly to this risk. Here, a highly sensitive liquid freestanding membrane (FSM) SERS method based on iodide modified silver nanoparticles (Ag NPs) was developed for quantitative detection of insecticide deltamethrin (DM) residues in solution phase samples and on surfaces with good accuracy and high sensitivity. The DM SERS spectrum from 500 to 2500 cm−1 resembled the normal Raman counterpart of solid DM. Similar bands at 563, 1000, 1165, 1207, 1735, and 2253 cm−1 were observed as in the literature. For the quantitative analysis, the strongest peak at 1000 cm−1 that was assigned to the stretching mode of the benzene ring and the deformation mode of C-C was selected. The peak intensity at 1000 cm−1 and the concentration of DM showed excellent linearity from 39 to 5000 ppb with a regression equation I = 649.428 + 1.327 C (correlation coefficient R2 = 0.991). The limit of detection (LOD) of the DM was found to be as low as 11 ppb. Statistical comparison between the proposed and the HPLC methods for the analysis of insecticide deltamethrin (DM) residues in solution phase samples showed no significant difference. DM residue analysis on the surface was mimicked by dropping DM pesticide on the glass surface. It is found that DM exhibited high residue levels up to one week after exposure. This proposed SERS method could find application in the household pesticide residues analysis.

Background Neoadjuvant chemotherapy (NAC) with anti-HER2 agents is standard for HER2-positive breast cancer, achieving pathological complete response (pCR) in 40–50% of patients; however, reliable predictors of response remain limited. HER2 is an immunogenic antigen capable of eliciting humoral responses, yet the predictive value of HER2-specific autoantibodies in the neoadjuvant setting remains unclear. We investigated whether HER2-peptide–specific antibody responses could serve as potential biomarkers of treatment response. Methods Paired pre- and post-NAC sera from 112 patients enrolled in the JBCRG-16 (Neo-Lath) trial, which evaluated trastuzumab- and lapatinib-containing NAC, were analyzed. IgG titers against 63 non-overlapping 20-mer HER2-derived peptides were measured using a multiplex bead array, and serum HER2 protein levels were also quantified. Data were analyzed using Wilcoxon signed-rank and rank-sum tests, Spearman’s correlation analyses, and univariate logistic regression for pCR. Predictive models were constructed using elastic net regression with nested cross-validation across pretreatment, posttreatment, and fold-change datasets, and model performance was assessed by the area under the receiver operating characteristic curve (AUC). Results HER2-derived peptides elicited heterogeneous immune responses, and IgG titers against 37 of 63 peptides (58.7%) significantly decreased after NAC. Pretreatment IgG titers were positively correlated with the Boman index and negatively correlated with the aliphatic index. In univariate analyses, neither IgG titers nor serum HER2 levels at either time point, nor their treatment-induced changes, were significantly associated with pCR. In contrast, a predictive model based on treatment-induced changes in a subset of peptide-specific IgG titers demonstrated consistent predictive performance (AUC 0.78 in training and 0.79 in validation). Six peptides distributed across the HER2 sequence contributed to pCR prediction. Conclusions Dynamic changes in HER2-peptide-specific autoantibodies during NAC, rather than static titers alone, may provide informative biomarkers for predicting clinical response. Serum HER2 levels were not significantly associated with pCR, suggesting that autoantibody profiling may capture response-related biology not reflected by antigen levels alone. These findings provide proof-of-concept evidence that minimally invasive, longitudinal profiling of peptide-specific autoantibodies could complement established response-assessment modalities, such as imaging or molecular assays. However, these results are exploratory and require validation in larger, independent cohorts before clinical application. Trial registration UMIN000007576 (Registration date: March 26, 2012).

Thrombocytosis is associated with poor prognosis in lung cancer patients. However, no studies have further assessed the effect of platelet-related parameters on the prognosis among lung cancer patients with thrombocytosis. Between 2020 and 2021, lung cancer patients with a platelet count ≥ 300 *10 /L or normal count were retrospectively reviewed. Potential prognostic factors were identified using univariate and multivariate accelerate failure time (AFT) model. Kaplan-Meier method and log-rank test were used to compare survival outcome. Among patients with thrombocytosis (  = 148), time point of platelet elevation, platelet distribution width (PDW), platelet-to-lymphocyte ratio (PLR) and neutrophil-to-lymphocyte ratio (NLR) did not significantly impact first-line progression-free survival (PFS). Compared to patients whose platelet count normalized after treatment, patients with sustained platelet elevation exhibited a worst PFS (β =  - 1.291,  < 0.001), and although patients with fluctuant platelet elevation had worse PFS (β =  - 0.358,  = 0.054), the difference was not statistically significant. Additionally, mean platelet volume (MPV) (β = 0.319,  = 0.008) and D-dimer (β =  - 0.046,  = 0.025) were also factors affecting first-line PFS. Among platelet-related parameters, besides MPV and D-dimer, the dynamic pattern of platelet count serves as a prognostic marker in lung cancer patients with thrombocytosis.

Persimmons are a traditional, autumnal, and healthy fruit commonly consumed in Japan and East Asia based on the saying, “a persimmon a day keeps the doctor away.” The differences in metabolites among five major Japanese persimmon cultivars were investigated using a nuclear magnetic resonance (NMR)-based metabolomics approach. By using a broadband water suppression enhanced through T 1 effects (WET) method for the sensitive detection of minor metabolites, better discrimination among cultivars and more informative details regarding their metabolic differences have been achieved compared to those achieved in conventional 1 H NMR sequences. Among the nonastringent cultivars analyzed, the Taishu cultivar has the highest abundance of amino acids. The Matsumotowase-Fuyu cultivar contains ethyl-β-glycosides as characteristic components, which may relate to fruit softening. Citric acid concentration is higher in Maekawa Jiro than in other nonastringent cultivars. Among the two astringent cultivars analyzed, ethanol was significantly higher in Hiratanenashi than in Yotsumizo, which indicates different reactivity during deastringency treatments. The present study proposes an efficient and relatively quantitative metabolomics approach based on broadband WET NMR spectra.

Traditional membrane separation materials suffer from drawbacks such as a high carbon footprint, significant energy consumption, membrane fouling, and the potential for secondary pollution. Under the dual drivers of carbon neutrality and carbon peak strategies, as well as the deepening of environmental governance, low-carbon membrane separation materials have emerged as a pivotal direction for the green transformation of membrane technology, leveraging their core advantages of green raw materials, low-energy preparation, and high application adaptability. This green transition is primarily achieved through the development of green raw materials and preparation processes, the enhancement of separation efficiency, and a reduction in operational energy consumption. Consequently, this review systematically summarizes the low-carbon design principles, key performance metrics, separation mechanisms, catalytic coupling technologies, and the recent application progress of several mainstream types of low-carbon membrane materials. It further identifies current bottlenecks in the research of low-carbon membrane materials such as performance trade-offs, challenges in scalable fabrication, and long-term operational instability. Finally, the review proposes future research directions aimed at developing novel membrane materials that integrate low-carbon attributes, excellent separation performance, and multifunctionality.

Functional diversity rather than species richness is critical for the understanding of ecological patterns and processes. This study aimed to develop novel integrated analytical strategies for the functional characterization of fish diversity based on the quantification, prediction and integration of the chemical and physical features in fish muscles. Machine learning models with an improved random forest algorithm applied on 1867 muscle nuclear magnetic resonance spectra belonging to 249 fish species successfully predicted the mobility patterns of fishes into four categories (migratory, territorial, rockfish, and demersal) with accuracies of 90.3–95.4%. Markov blanket-based feature selection method with an ecological–chemical–physical integrated network based on the Bayesian network inference algorithm highlighted the importance of nitrogen metabolism, which is critical for environmental adaptability of fishes in nutrient-rich environments, in the functional characterization of fish biodiversity. Our study provides valuable information and analytical strategies for fish home-range assessment on the basis of the chemical and physical characterization of fish muscle, which can serve as an ecological indicator for fish ecotyping and human impact monitoring.