Explore the vast range of titles available.

Recurrent neural networks have seen widespread use in modeling dynamical systems in varied domains such as weather prediction, text prediction and several others. Often one wishes to supplement the experimentally observed dynamics with prior knowledge or intuition about the system. While the recurrent nature of these networks allows them to model arbitrarily long memories in the time series used in training, it makes it harder to impose prior knowledge or intuition through generic constraints. In this work, we present a path sampling approach based on principle of Maximum Caliber that allows us to include generic thermodynamic or kinetic constraints into recurrent neural networks. We show the method here for a widely used type of recurrent neural network known as long short-term memory network in the context of supplementing time series collected from different application domains. These include classical Molecular Dynamics of a protein and Monte Carlo simulations of an open quantum system continuously losing photons to the environment and displaying Rabi oscillations. Our method can be easily generalized to other generative artificial intelligence models and to generic time series in different areas of physical and social sciences, where one wishes to supplement limited data with intuition or theory based corrections. Adding prior experimentally or theoretically obtained knowledge to the training of recurrent neural networks may be challenging due to their feedback nature with arbitrarily long memories. The authors propose a path sampling approach that allows to include generic thermodynamic or kinetic constraints for learning of time series relevant to molecular dynamics and quantum systems.

BackgroundTumor-associated macrophages (TAMs) secreting IL-10 could be a specific functional cell subset with distinct polarization state and suppressive role in antitumor immune response. Here, we assessed the associations of clinical outcome, therapeutic responses and molecular features with IL-10+TAMs infiltration, and potential impact of IL-10+TAMs on the immune contexture in muscle-invasive bladder cancer (MIBC).MethodsIn this retrospective study, 128 patients and 391 patients with MIBC from Zhongshan hospital (ZS cohort) and The Cancer Genome Atlas cohort were included respectively. Immunohistochemistry was performed to quantify various immune cell infiltration in the ZS cohort. Single cell RNA sequencing and flow cytometry were performed to examine the functional status of IL-10+TAMs and its correlation with other immune cells. Survival analyses and assessment of the adjuvant chemotherapy (ACT) benefit analyses were also performed.ResultsHigh IL-10+TAMs infiltration was associated with inferior prognosis in terms of overall survival and recurrence-free survival, but superior chemotherapeutic response in MIBC. IL-10+TAMs with suppressive features were associated with immunoevasive tumor microenviroment characterized by exhausted CD8+ T cells, immature NK cells and increased immune checkpoint expression. Additionally, high IL-10+TAMs infiltration showed a strong linkage with basal-featured subtype and augmented EGF signaling.ConclusionsImmunosuppresive IL-10+TAMs contributed to an evasive contexture with incapacitated immune effector cells and increased immune checkpoint expression, therefore, predicting unfavorable clinical outcomes despite better ACT responsiveness. IL-10+TAMs might provide guidance for customized selection of EGFR-targeted therapy, FGFR3-targeted therapy as well as immunotherapy. The potential of immunosuppressive IL-10+TAMs as a therapeutic target is worth further exploration.

Potato is one of the most significant food crops globally due to its essential role in the human diet. The growing demand for potato, coupled with severe environmental losses caused by extensive farming activities, implies the need for better crop protection and management practices. Precision agriculture is being well recognized as the solution as it deals with the management of spatial and temporal variability to improve agricultural returns and reduce environmental impact. As the initial step in precision agriculture, the traditional methods of crop and field characterization require a large input in labor, time, and cost. Recent developments in remote sensing technologies have facilitated the process of monitoring crops and quantifying field variations. Successful applications have been witnessed in the area of precision potato farming. Thus, this review reports the current knowledge on the applications of remote sensing technologies in precision potato trait characterization. We reviewed the commonly used imaging sensors and remote sensing platforms with the comparisons of their strengths and limitations and summarized the main applications of the remote sensing technologies in potato. As a result, this review could update potato agronomists and farmers with the latest approaches and research outcomes, as well as provide a selective list for those who have the intentions to apply remote sensing technologies to characterize potato traits for precision agriculture.

Following advances in machine learning and deep learning processing, cyber security experts are committed to creating deep intelligent approaches for automatically detecting software vulnerabilities. Nowadays, many practices are for C and C++ programs, and methods rarely target PHP application. Moreover, many of these methods use LSTM (Long Short-Term Memory) but not GNN (Graph Neural Networks) to learn the token dependencies within the source code through different transformations. That may lose a lot of semantic information in terms of code representation. This article presents a novel Graph Neural Network vulnerability detection approach, VulEye, for PHP applications. VulEye can assist security researchers in finding vulnerabilities in PHP projects quickly. VulEye first constructs the PDG (Program Dependence Graph) of the PHP source code, slices PDG with sensitive functions contained in the source code into sub-graphs called SDG (Sub-Dependence Graph), and then makes SDG the model input to train with a Graph Neural Network model which contains three stack units with a GCN layer, Top-k pooling layer, and attention layer, and finally uses MLP (Multi-Layer Perceptron) and softmax as a classifier to predict if the SDG is vulnerable. We evaluated VulEye on the PHP vulnerability test suite in Software Assurance Reference Dataset. The experiment reports show that the best macro-average F1 score of the VulEye reached 99% in the binary classification task and 95% in the multi-classes classification task. VulEye achieved the best result compared with the existing open-source vulnerability detection implements and other state-of-art deep learning models. Moreover, VulEye can also locate the precise area of the flaw, since our SDG contains code slices closely related to vulnerabilities with a key triggering sensitive/sink function.

In real-world scenarios, the number of phishing and benign emails is usually imbalanced, leading to traditional machine learning or deep learning algorithms being biased towards benign emails and misclassifying phishing emails. Few studies take measures to address the imbalance between them, which significantly threatens people’s financial and information security. To mitigate the impact of imbalance on the model and enhance the detection performance of phishing emails, this paper proposes two new algorithms with undersampling: the Fisher–Markov-based phishing ensemble detection (FMPED) method and the Fisher–Markov–Markov-based phishing ensemble detection (FMMPED) method. The algorithms first remove benign emails in overlapping areas, then undersample the remaining benign emails, and finally, combine the retained benign emails with phishing emails into a new training set, using ensemble learning algorithms for training and classification. Experimental results have demonstrated that the proposed algorithms outperform other machine learning and deep learning algorithms, achieving an F1-score of 0.9945, an accuracy of 0.9945, an AUC of 0.9828, and a G-mean of 0.9827.

Amyloids are protein aggregates implicated in both physiological functions and pathological conditions, including neurodegenerative diseases. Their polymorphic nature, dynamic aggregation behavior, and isoform complexity present significant challenges for detection and characterization. Traditional lock‐and‐key sensing methods often fall short in capturing this heterogeneity. Array‐based sensing has emerged as a powerful alternative, leveraging cross‐reactive sensors and multivariate data analysis to generate distinct response patterns or “fingerprints” for amyloids. This review highlights recent advances in arrays based on chemical sensors including colorimetric, fluorescent, and nanoparticle‐based, capable of discriminating amyloid isoforms, aggregation states, and polymorphs with high sensitivity and accuracy. The integration of machine learning techniques and neural networks, which enhance pattern recognition and predictive accuracy, even in complex biological matrices, is discussed. Notably, multidimensional approaches expand the analytical power of single‐sensor systems by exploiting excitation/emission spectral diversity. These innovations underscore the potential of array‐based platforms for early diagnosis, mechanistic studies, and therapeutic monitoring of amyloid‐related diseases. As the field evolves, combining sensor diversity with advanced computational tools promises to transform amyloid detection into a scalable and clinically relevant technology. Amyloids are protein aggregates with both pathological and functional roles. Their detection is challenged by structural polymorphism, isoform diversity, and dynamic aggregation behavior. This review presents chemical array‐based sensing strategies that address these complexities, emphasizing fluorescence and colorimetric methods, alongside multivariate analysis and machine learning for enhanced discrimination and diagnostic relevance.

Code cloning is a common practice in software development, where developers reuse existing code to accelerate programming speed and enhance work efficiency. Existing clone-detection methods mainly focus on code clones within a single programming language. To address the challenge of code clone instances in cross-platform development, we propose a novel method called TCCCD, which stands for Triplet-Based Cross-Language Code Clone Detection. Our approach is based on machine learning and can accurately detect code clone instances between different programming languages. We used the pre-trained model UniXcoder to map programs written in different languages into the same vector space and learn their code representations. Then, we fine-tuned TCCCD using triplet learning to improve its effectiveness in cross-language clone detection. To assess the effectiveness of our proposed approach, we conducted thorough comparative experiments using the dataset provided by the paper titled CLCDSA (Cross Language Code Clone Detection using Syntactical Features and API Documentation). The experimental results demonstrated a significant improvement of our approach over the state-of-the-art baselines, with precision, recall, and F1-measure scores of 0.96, 0.91, and 0.93, respectively. In summary, we propose a novel cross-language code-clone-detection method called TCCCD. TCCCD leverages the pre-trained model UniXcode for source code representation and fine-tunes the model using triplet learning. In the experimental results, TCCCD outperformed the state-of-the-art baselines in terms of the precision, recall, and F1-measure.

The development of nanomaterials for delivering natural compounds has emerged as a promising approach for atherosclerosis therapy. However, premature drug release remains a challenge. Here, we present a ROS-responsive biomimetic nanocomplex co-loaded with Geniposide (GP) and Emodin (EM) in nanoliposome particles (LP NPs) for targeted atherosclerosis therapy. The nanocomplex, hybridized with the macrophage membrane (Møm), effectively evades immune system clearance and targets atherosclerotic plaques. A modified thioketal (TK) system responds to ROS-rich plaque regions, triggering controlled drug release. In vitro, the nanocomplex inhibits endothelial cell apoptosis and macrophage lipid accumulation, restores endothelial cell function, and promotes cholesterol effluxion. In vivo, it targets ROS-rich atherosclerotic plaques, reducing plaque area ROS levels and restoring endothelial cell function, consequently promoting cholesterol outflow. Our study demonstrates that ROS-responsive biomimetic nanocomplexes co-delivering GP and EM exert a synergistic effect against endothelial cell apoptosis and lipid deposition in macrophages, offering a promising dual-cell therapy modality for atherosclerosis regression. Highlights The first report on ROS-responsive biomimetic nano complex co-loaded with Geniposide and Emodin for targeted atherosclerosis therapy. Discovery of the synergistic effect of simultaneous administration of Geniposide and Emodin in inhibiting endothelial cell apoptosis and macrophage lipid deposition, key steps in plaque progression. Utilization of macrophage membrane (Møm) hybrid nanocomplex to avoid clearance by the immune system and enhance targeting ability. Development of a modified thioketal (TK) system that responds to ROS-rich plaque regions, enabling accurate and rapid drug release. In vitro and in vivo evidence demonstrating the efficacy of ROS-responsive biomimetic nanocomplexes in reducing plaque area ROS levels, restoring endothelial cell function and reducing lipid deposition, with potential implications for atherosclerosis treatment.

Background: The reported associations between BMI (body mass index), WC (waist circumference) and cognitive decline are not consistent, especially in older adults. Objective: To investigate the longitudinal associations of BMI, WC and their change values with cognitive decline among Chinese adults sixty and older and examine the potential moderating effect of sex on these relationships. Methods: This study participants were from the waves one to four (2011-2018) of the China Health and Retirement Longitudinal Study (CHARLS). Cognition function, BMI, and WC were measured at four examinations over seven years. Interview-based cognitive assessments of memory, orientation and attention, and visuospatial ability were recorded. Standardized global cognitive scores were generated. BMI and WC were objectively measured. Mixed-effects models were performed to evaluate the associations. Results: A final sample of 3035 Chinese older adults [mean (SD) age, 66.94 (5.43) years; 40.16% (n = 1219) women] were included. Higher BMI (estimate = 0.0107; SE = 0.0024; p < 0.0001) and WC (estimate = 0.0019; SE = 0.0006; p = 0.0037) were associated with slower cognition score decline over the seven-year follow-up, while greater BMI variability (estimate = -0.0365; SE = 0.0116; p = 0.0017) was related to faster cognition score decline. The results were not modified by sex. BMI-defined overweight (estimate = 0.0094; SE = 0.0043; p = 0.0298) was associated with a slower cognition score decline, and large weight gain (estimate = -0.0266; SE = 0.0074; p = 0.0003) and large WC loss (estimate = -0.0668; SE = 0.0329; p = 0.0426) both were associated with faster cognition score decline. Conclusions: Among Chinese older adults, higher BMI, higher WC, and overweight are related to slower cognitive decline, while greater BMI variability, large weight gain, large WC loss are associated with faster cognitive decline.

Background Intestinal protozoa and helminths remain an under‑recognized cause of gastrointestinal morbidity in China. Molecular high‑throughput tools offer the chance to survey their diversity comprehensively, yet their application in clinical settings has been limited. Methods We pooled leftover fecal samples from 360 hospital patients in Changchun (36 pools; 12 demographic/seasonal groups) and enriched them by sucrose flotation. Three primer pairs targeting 18S V4‑V5, 18S V9 and 28S D3‑D4 rRNA regions were amplified, and paired‑end libraries (100–140 k reads per amplicon) were sequenced on Illumina platforms. Taxa were assigned with QIIME2 against SILVA, and true prevalences were estimated from pooled‑sample data using a binomial model with profile‑likelihood confidential intervals. Selected positives were confirmed by qPCR, nested PCR, gp60 subtyping and immunofluorescence assay. Results From 6.1 million quality‑filtered reads, only 1.65% mapped to parasites; fungal reads dominated (98.35%), underscoring primer bias. Four eukaryotic parasites were detected across 12/36 pools. Cryptosporidium parvum was most frequent (7 pools, true prevalence = 2.14%, 95% CI 0.92–4.10), and all gp60 ‑typed isolates belonged to subtype IIdA19G1. Blastocystis hominis occurred in five pools (1.48%, 0.53–3.17), predominantly ST1, with single detections of ST3 and ST6. Entamoeba hartmanni appeared in one pool (0.28%, 0.02–1.23). Reads assignable only to Opisthorchiidae suggested liver‑fluke carriage in four adult pools (1.17%, 0.36–2.70). No statistically significant associations were found between infection status and age, sex, season or diarrhea. Amplification success differed markedly between primer sets, limiting quantitative comparisons. Conclusions Metabarcoding of rDNA amplicons provides a feasible snapshot of human intestinal‑parasite communities in Northeast China, revealing C.   parvum IIdA19G1 as an emerging zoonotic threat and highlighting ongoing food‑borne trematodiasis. However, the overwhelming amplification of fungal templates and inter‑primer bias call for primer redesign and complementary diagnostics before routine clinical adoption. Graphical Abstract