Search Results (64,171)

Background: Neurodevelopmental disorders (NDDs) are genetically heterogeneous, and exome sequencing (ES) is now a first-line diagnostic tool. However, many patients receive variants of uncertain significance (VUSs) or inherited variants with incomplete penetrance, limiting clinical interpretation. Emerging multi-omics evidence from the literature can support the interpretation of novel and rare variants, helping to refine classification in selected cases. Methods: We assessed 20 patients and their parents referred for genetic testing for NDDs. ES was performed, followed by ACMG/ACGS-based variant classification, segregation analysis, and targeted literature review. Variants were included when deemed plausible contributors to the phenotype by a multidisciplinary team. Gene-level constraint metrics, in silico predictions, and emerging multi-omics evidence from the literature were integrated to support interpretation. Results: Across 18 NDD-associated genes, we identified 20 rare variants: Three pathogenic (P), nine likely pathogenic (LP), and eight VUSs. All P and most LP variants were de novo. Inherited variants, particularly in KMT5B, TANC2, SPTBN1, and CHD4, highlighted challenges related to incomplete penetrance. Two patients had dual molecular diagnoses. Several VUSs were supported by literature-derived transcriptomic, proteomic, or model-system evidence. Conclusions: This cohort underscores ongoing challenges in interpreting VUSs and inherited variants in NDDs. Integrating genomic findings with published multi-omics data enhances variant interpretation, reveals mechanistic insights, and strengthens diagnostic confidence, supporting broader adoption of multi-omics approaches in rare NDD evaluation. Full article

Zinc finger proteins (ZFPs) are a diverse group of plant transcription factors essential for regulating development, signaling, and stress responses. In this study, we performed a genome-wide identification and integrative analysis of 140 C3H-type zinc finger transcription factor genes in the soybean genome, exhibiting an uneven distribution across all 20 chromosomes. These C3H-ZFPs contained one (37), two (58), three (19), four (7), five (17), or six (2) C3H domains and were classified into 14 subsets based on their domain architecture. All C3H genes encoding proteins harbored the conserved C3H-ZFP domain and displayed various physicochemical characteristics. Phylogenetic analysis grouped them into 10 clades, closely related to other species like Arabidopsis, rice and alfalfa. Promoter analysis revealed cis-elements associated with stress response (~39.1%), light response (~37.3%), phytohormones (~18.5%), and development (~4.97%). Duplication analysis revealed 78 pairs of segmental and eight tandem duplication events, with purifying selection indicated by Ka/Ks (nonsynonymous/synonymous) ratios, indicating that these C3H-ZFP duplicates were largely maintained under purifying selection. A total of 388 miRNAs from 196 gene families were predicted to target 140 C3H-ZFP genes, with most enriched miRNAs targeting C3H-ZFP genes, including the miR156, miR395, and miR396 families. Transcription factor binding sites for MYB, AP2, MIKC_MADS, BBR-BPC, ERF, C2H2, and Dof were found upstream of most C3H-ZFP genes. RNA-Seq and qRT-PCR analyses showed tissue-specific expression and stress-responsive expression patterns, with several C3H-ZFP genes, especially GmC3H1, GmC3H63, GmC3H124, and GmC3H127, being significantly upregulated under abiotic stress conditions. Together, these results provide a comprehensive overview of soybean C3H-ZFP genes and identify promising candidates for future functional studies on development and abiotic stress adaptation. Full article

Acute coronary syndrome (ACS), driven by inflammation and thrombosis, remains a leading cause of morbidity globally. While traditional risk scores are useful, the prognostic value of combining inflammatory and autoimmune biomarkers remains understudied. This study aimed to evaluate the predictive role of high-sensitivity C-reactive protein (hs-CRP), platelet factor 4 (PF4), D-dimer, and antiphospholipid antibodies (anticardiolipin and anti-β2-glycoprotein I) for the development of major adverse cardiovascular events (MACE) in patients with ACS. We conducted a prospective cohort study at a tertiary referral center in Mexico. A total of 103 patients admitted with confirmed ACS were included. Blood samples were collected upon admission to measure biomarker levels. Participants were followed for 30 days. The primary outcome was the occurrence of MACE, defined as reinfarction, death, percutaneous coronary intervention, or bypass surgery. Multivariate logistic regression analysis was performed to identify independent predictors, adjusting for age, smoking, and comorbidities. MACE occurred in 51.4% of participants. Patients with adverse outcomes were significantly older and had longer hospital stays (p < 0.05). In the biomarker analysis, PF4 and hs-CRP demonstrated high sensitivity (98%) but low specificity. In the multivariate analysis, IgG anti-β2-glycoprotein I (p < 0.001) and D-dimer (p = 0.024) emerged as significant independent predictors of MACE. Conversely, IgM isotypes did not show independent predictive value. Beyond traditional risk factors, markers of coagulation (D-dimer) and autoimmunity (IgG anti-β2-glycoprotein I) are independent predictors of short-term adverse events in ACS patients. Integrating these multidomain biomarkers into clinical assessment may enhance risk stratification and prognostic accuracy. Full article

Background: Non-alcoholic fatty liver disease (NAFLD) represents the most widespread chronic liver disorder globally, impacting roughly 30% of the general population. Numerous factors have been linked to NAFLD, including obesity, type 2 diabetes, diet, physical inactivity, age, sex, genetic factors, and metabolic syndrome. Previous research predominantly treated NAFLD as a categorical outcome, providing less granular data compared to the continuous fatty liver index (FLI). This investigation enrolled healthy young Taiwanese men and applied multivariate adaptive regression spline (MARS) modeling to develop a predictive equation. Our aims were twofold: 1. To assess the predictive accuracy of traditional multiple linear regression (MLR) versus MARS. 2. To construct a MARS-derived equation for estimating FLI in this demographic. Methods: Data originated from the Taiwan MJ Cohort, comprising 5496 men aged 20–50 years not using medications for metabolic syndrome. MARS was used to formulate the FLI estimation equation. Model performance was compared using symmetric mean absolute percentage error (SMAPE), relative absolute error (RAE), root relative squared error (RRSE), and root mean squared error (RMSE). Results: Evaluation indicated that MARS yielded lower estimation errors than MLR, demonstrating its superior performance. The derived equation is: FLI = 65.224 − 0.436 × B1 − 0.490 × B2 + 0.252 × B3 − 2.962 × B4 + 2.231 × B5 − 0.292 × B6 + 0.189 × B7 − 0.361 × B8 − 0.699 × B9 + 0.160 × B10 − 2.715 × B11 + 0.799 × B12 − 0.153 × B13 + 0.084 × B14 − 35.274 × B15 − 4.424 × B16. Conclusions: Using MLR as a benchmark, our analysis revealed that MARS delivered better predictive performance. The presented equation explains 62.7% of the variance in FLI (r² = 0.627). Based on standardized variable importance scores (nsubsets metric), CRP emerged as the most influential predictor, followed by WBC, UA, HDL-C, AST, age, ALT, FPG, SBP, and LDL in this cohort of healthy young Taiwanese men. Full article

Accurate runoff forecasting is essential for effective water resource management, hydropower operation, and flood risk mitigation. In this study, daily inflow runoff in the Xin’an River Basin, eastern China, was simulated using four ensemble learning models: Gradient Boosting Decision Tree (GBDT), XGBoost, CatBoost, and Stacking. Among them, the CatBoost model achieved the best performance, with a correlation coefficient (CC) exceeding 0.97, Nash–Sutcliffe efficiency (NSE) above 0.95, and reduced RMSE and MAE compared with the currently operational hydrological model. To extend the forecast lead times, two hydro–meteorological coupled models were developed by integrating the CatBoost model with a single numerical weather prediction model (EC) and a dynamically weighted multi-model ensemble precipitation forecast system (OCF). The coupled models were evaluated for lead times up to 240 h. The forecast skill value was highest within 96 h, with CC values above 0.80 and NSE around 0.50. The OCF-coupled model demonstrated improved reliability for lead times of 48–96 h, whereas the EC-driven forecasts performed better within the first 48 h. Case studies during the 2021–2022 flood seasons confirmed that the coupled framework accurately reproduced flood evolution and peak discharge dynamics, demonstrating its practical value for medium-range runoff forecasting in humid river basins. Full article

RNA N7-methylguanosine (m7G) is an important post-transcriptional epigenetic modification that participates in key biological processes, including RNA processing, stability maintenance, and translational regulation. Medical research has shown that m7G modification and its related regulatory factors are closely related to many neurological diseases and tumors. The accurate prediction of m7G sites is thus critical for understanding their biological functions in diseases. In this work, we propose BF-m7GPred, a dual-branch deep learning framework that integrates single-nucleotide-level embeddings and motif-level embeddings for m7G modification site prediction. Our proposed context-aware module tokenizes RNA sequences using byte-pair encoding and encodes sequences with the pretrained foundation biological model DNABERT2. In parallel, the proposed feature fusion module transforms sequences into multiple feature matrices using multiple traditional encoders. We introduce a feature selection strategy tailored to the encoding characteristics of the two branches. On a benchmark dataset collected from m7G-Hub v2.0, BF-m7GPred achieves superior performance on the independent test set against existing methods. Furthermore, its generalization capability is validated through comparative experiments on 10 diverse RNA modification datasets. Full article

Warfarin is one of the most used oral anticoagulants, even after the arrival of non-vitamin K oral anticoagulants. Warfarin has been implicated in approximately one-third of emergency hospitalizations for adverse drug events among older adults in national U.S. data. Warfarin dose has been shown to vary between patients with up to 10 times the standard dose. This variability is due to multiple factors such as age, gender, diet, body size, co-medications, and the genetic background of the patient, where the genetic background accounts for 50% of warfarin dose variability among Europeans. Sadly, these findings do not apply to Caribbean Hispanic populations such as Puerto Ricans due to them having an admixed genetic profile. In the field of pharmacogenomics (PGx), the utility of machine learning (ML) has been used to predict individual drug responses by analyzing complex genetic and clinical data, which helps personalize medicine by tailoring treatments to a patient’s genetic makeup. Inclusion of ethno-specific variants has demonstrated improvement on the application of ML to a specific population. This study compares eight ML methods to predict warfarin sensitivity in Puerto Rican Caribbean Hispanics. This study is a secondary analysis of genetic and clinical data from 217 Puerto Rican patients treated with warfarin for thromboembolic disorders. After quality control filtering and exclusion of participant records with incomplete genetic and clinical data, 146 participants are retained for analysis. Data are divided into 65% and 35% to be used as training and test sets. Model performance is determined by comparing the precision and accuracy metrics, computed through the corresponding confusion matrixes. A gradient boosting classifier (GDB) achieves the highest overall accuracy (0.7500) and weighted precision of (0.7642); however, sensitivity for detecting warfarin-sensitive patients remains low. Feature importance analysis suggests that rs202201137 could contribute to model predictions, although overall detection of warfarin-sensitive individuals remains limited. Full article

This study investigates the interaction between polycarboxylate-based water-reducing admixtures (WRAs) and various types of CEM I 42.5R Portland cements, focusing on optimizing input parameters in cementitious systems. Despite the widespread use of WRAs to enhance concrete’s workability, strength, and durability, their compatibility with cement remains a critical challenge, often leading to performance issues such as low initial flow, bleeding, and rapid slump loss. This research addresses two significant gaps in the literature: the unexplored use of input parameter reduction in cementitious systems and the application of novel metaheuristic algorithms in optimizing these systems. In this study, 25 WRA were first synthesized to enrich the inputs of machine learning (ML) models. Then, a dataset of 750 entries was generated, and advanced prediction models were developed. To ensure scientific rigor and eliminate data leakage, a triple-split dataset strategy (Training–Validation–Test) and 5-fold cross-validation were implemented. Among the machine learning techniques analyzed, the Optimized Artificial Neural Networks (opANN) architecture decisively demonstrated the highest prediction performance on the isolated test dataset. In the opANN process, 10 different metaheuristics were tested to evaluate their effectiveness in hyperparameter optimization. As a result, the Kepler Optimization (KOA) algorithm was determined as the algorithm with the highest performance in ANN hyperparameter optimization. Furthermore, Shapley Additive Explanations (SHAP) analysis was utilized to bridge the gap between empirical observations and algorithmic predictions, quantitatively corroborating the rheological roles of phosphate and sulfonate groups. The results offer new insights into WRA–cement compatibility and present advanced, interpretable modeling approaches that enhance predictive accuracy, contributing to more reliable and sustainable concrete practices. Full article

Hami melon is a widely consumed fruit worldwide, and its sweetness, characterized by soluble solids content (SSC), is a key indicator of fruit quality and commercial value. In this study, hyperspectral imaging combined with machine learning was systematically applied to develop non-destructive models for SSC prediction in multiple Hami melon varieties. Four varieties, namely ‘Xizhoumi’, ‘Jiashigua’, ‘Jinfenghuang’, and ‘Heimeimao’, with a total of 160 samples, were used as the test materials. Hyperspectral images were collected, and SSC was measured at two pulp positions for each sample (denoted as BRIX1 and BRIX2). After applying preprocessing methods including Standard Normal Variate (SNV) transformation and Savitzky–Golay smoothing, five machine learning models were compared: XGBoost, LightGBM, Random Forest (RF), Support Vector Regression (SVR), and Partial Least Squares Regression (PLSR). Furthermore, an ensemble modeling strategy based on residual predictive deviation (RPD) weighting from the validation set was proposed. The results show that all models could effectively predict SSC, with the ensemble model achieving the best performance: the coefficients of determination (R²) for BRIX1 and BRIX2 were 0.848 and 0.833, the root mean square errors (RMSEs) were 0.992 and 0.899, the Mean Absolute Percentage Errors (MAPEs) were 6.90% and 6.76%, and the RPD values were 2.57 and 2.45, respectively, demonstrating its strong quantitative analysis capability. This performance benefited from three core optimized designs adopted in this study: (1) a multi-cultivar experimental design that verified the stable correlation between sugar-related spectral features and internal SSC across different Hami melon varieties; (2) an RPD-weighted ensemble modeling strategy that balanced the fitting ability and generalization performance of linear and nonlinear models; and (3) a dual-position SSC measurement design that validated the robustness of the model for SSC prediction at different spatial positions in the pulp. This study confirms the feasibility of hyperspectral imaging technology for non-destructive SSC detection in the four tested Hami melon varieties under laboratory-controlled conditions. The proposed ensemble model achieved a marginal but stable improvement in overall prediction accuracy across the tested varieties compared with the optimal single model, providing a preliminary methodological reference and data support for the development of cross-cultivar non-destructive SSC detection models for Hami melon. Full article

Ischemic stroke remains a major cause of mortality and long-term disability worldwide, and improved strategies for identifying individuals at elevated vascular risk are needed. Serum autoantibodies have emerged as potential biomarkers reflecting vascular injury and immune activation; however, their integrative biological significance and incremental predictive value beyond established clinical risk factors remain unclear. We analyzed 833 participants, including patients with acute ischemic stroke (AIS) or transient ischemic attack (TIA) and healthy controls. Serum levels of anti-PDCD11 antibody (Ab), anti-DNAJC2 antibody, and anti-PAI-1 (SERPINE1) antibody were quantified, and multivariable logistic regression and machine-learning (ML) models (logistic regression and random forest) were constructed using clinical variables with and without antibody markers. Model performance was evaluated using cross-validation, bootstrap-derived confidence intervals, calibration metrics, and reclassification indices. Model interpretability analyses, principal component analysis (PCA), unsupervised clustering, and propensity score matching were performed to explore latent biological structures. Clinical-only models demonstrated excellent discrimination (bootstrap Area Under the Curve (AUC) 0.917 for random forest and 0.919 for logistic regression). The addition of antibody markers yielded similar performance (AUC 0.913 and 0.923, respectively) without evidence of meaningful improvement in reclassification. However, SHapley Additive exPlanations (SHAP) analysis identified antibody markers as influential contributors following major clinical risk factors. PCA revealed a dominant antibody component explaining approximately 79% of the variance, which remained independently associated with stroke after age adjustment. Unsupervised clustering further identified a high-risk subgroup characterized by consistently elevated antibody levels. These findings support the presence of a latent antibody axis associated with vascular vulnerability. Although antibody markers did not substantially enhance global predictive performance, they captured integrated biological signals reflecting cumulative vascular and immunological stress. Autoantibody profiling may complement conventional risk assessment by improving biological characterization of stroke susceptibility. Prospective validation in independent cohorts is required prior to clinical implementation. Full article

Accurate spatial–temporal crime prediction is a critical component of proactive public safety governance, yet it remains challenging due to complex dependency structures and severe data sparsity in real-world crime datasets. Most existing methods either focus on local spatial–temporal correlations or attempt to model global dependencies at fine-grained region levels, which limits their robustness under highly sparse and imbalanced crime distributions. In this paper, we propose GL-MoPA, a global–local modulated prototype attention framework for city-scale crime prediction. GL-MoPA integrates three key components. First, a local dependency modeling module is designed to capture fine-grained spatial and short-term temporal patterns. Second, a prototype-aware global attention mechanism aggregates region-level representations into semantically meaningful prototypes to efficiently model long-range dependencies. Third, a two-stage occurrence-aware prediction strategy decouples crime occurrence estimation from intensity regression to explicitly address data sparsity. We evaluate GL-MoPA on a real-world crime dataset from New York City covering four major crime categories. The experimental results show that GL-MoPA achieves state-of-the-art performance, consistently outperforming both classical statistical models and recent deep learning baselines. In particular, a robustness analysis shows substantial error reductions in sparse regions, while ablation studies reveal the complementary roles of individual model components. These results indicate that GL-MoPA provides an effective and robust solution for spatial–temporal crime forecasting under sparse-data scenarios. Full article

Arabic sign language (ArASL) is the primary communication medium for Deaf and hard-of-hearing people across Arabic-speaking communities. Most current ArASL recognition systems are based solely on visual features and do not incorporate linguistic or semantic information that could improve generalization and semantic grounding. This paper introduces CLIP-ArASL, a lightweight CLIP-style multimodal approach for static ArASL letter recognition that aligns visual hand gestures with bilingual textual descriptions. The approach integrates an EfficientNet-B0 image encoder with a MiniLM text encoder to learn a shared embedding space using a hybrid objective that combines contrastive and cross-entropy losses. This design supports supervised classification on seen classes and zero-shot prediction on unseen classes using textual class representations. The proposed approach is evaluated on two public datasets, ArASL2018 and ArASL21L. Under supervised evaluation, recognition accuracies of $99.25\pm 0.14\%$ and $91.51\pm 1.29\%$ are achieved, respectively. Zero-shot performance is assessed by withholding $20\%$ of gesture classes during training and predicting them using only their textual descriptions. In this setting, accuracies of $55.2\pm 12.15\%$ on ArASL2018 and $37.6\pm 9.07\%$ on ArASL21L are obtained. These results show that multimodal vision–language alignment supports semantic transfer and enables recognition of unseen classes. Full article

Background: Accurate vertebral instance segmentation on full-spine radiographs is essential for spinal parameter assessment, but supervised methods require costly instance-level annotations and may be sensitive to domain shift. Methods: We investigated whether promptable segmentation foundation models can generalize zero-shot to raw DICOM spine radiographs without task-specific training. We evaluated SAM-ViT-Huge, SAM2-Hiera-Large, and MedSAM-ViT-Base on 144 full-spine radiographs with 1309 annotated vertebral masks using a standardized pipeline for DICOM decoding, intensity normalization, automatic prompt generation, and instance-level evaluation. For each prompt, models produced three candidate masks. Performance was reported under an oracle protocol selecting the candidate with the highest IoU against ground truth and a model-score protocol selecting the candidate with the highest predicted IoU. Metrics included IoU, Dice, precision, recall, ASSD, and HD95. Results: The best configuration was SAM-ViT-Huge with rectangle prompting, reaching a mean IoU/Dice of 0.782/0.870 under oracle selection and 0.737/0.837 under model-score selection. SAM2-Hiera-Large with rectangle prompting followed (0.744/0.848 oracle; 0.699/0.815 model-score), ahead of MedSAM-ViT-Base (0.599/0.737 oracle; 0.387/0.499 model-score). Point prompting yielded consistently low overlap (IoU 0.224–0.319; Dice 0.276–0.414) despite high recall, indicating systematic over-segmentation and large boundary errors. Conclusions: Zero-shot vertebral instance segmentation on raw DICOM spine radiographs is feasible with promptable foundation models when prompts sufficiently constrain target extent. Rectangle prompting is clearly more effective than point prompting in this setting. Full article

This study proposes an end-to-end mathematical framework to automatically transform warehouse layout images into optimization-ready route matrices. The objective is to convert visual spatial information into a discrete, graph-based representation suitable for combinatorial route optimization. The problem is formulated as a mapping from continuous image space to a structured grid representation, integrating image segmentation, graph construction, and Traveling Salesman Problem (TSP)-based routing. Synthetic warehouse layouts were generated to create labeled training data, and a U-Net convolutional neural network was trained to perform multi-class segmentation of warehouse elements. The predicted grid representation was then converted into a graph structure, where feasible cells define vertices and adjacency defines edges. Shortest path distances were computed using Breadth-First Search, and the resulting distance matrix was used to solve a TSP instance. The segmentation model achieved approximately 98% training accuracy and 95–97% validation accuracy. The generated route matrices enabled successful construction of feasible and optimal round-trip routes in all tested scenarios. The proposed framework demonstrates that warehouse layouts can be automatically transformed into discrete mathematical representations suitable for logistics optimization, reducing manual preprocessing and enabling scalable integration into digital logistics systems. Full article

In October 2020, the International Coalition to Eliminate Hepatitis B Virus (ICE-HBV) updated the biomarker framework; they underscored major advances in the understanding of viral and immunologic markers, yet highlighted persistent gaps in their clinical integration. This is particularly the case in low- and middle-income regions, where HBV remains a substantial public health problem, including in the pediatric population. To synthesize contemporary evidence, a structured literature search was performed across PubMed/MEDLINE, Scopus, and Web of Science. Classical biomarkers—including HBeAg, HBV DNA, and quantitative HBsAg—remain central for disease staging and therapeutic monitoring, while emerging markers enhance precision in risk stratification: HBcrAg, which correlates strongly with intrahepatic cccDNA activity and virological rebound after NA discontinuation; serum HBV RNA, which offers additional insight into transcriptional activity, which is particularly relevant for RNA-targeted therapies; and quantitative anti-HBc (qAnti-HBc), which reflects stronger humoral imprinting and more competent HBV-specific immune memory, and is consistently associated with fewer ALT flares and reduced virological rebound at end of treatment. Despite these advances, assay standardization, genotype-related variability, and limited pediatric data constrain broad clinical application. Integrating classical and emerging biomarkers into personalized therapeutic algorithms offers substantial potential for refining treatment decisions, predicting post-treatment outcomes, and advancing HBV elimination strategies in diverse clinical settings. Full article