Search Results (590)

Jujube is an important fruit tree and one of the five major economic forest tree species native to China, possessing high nutritional and medicinal value. It plays a key supporting role in the efficient utilization of marginal land resources—such as mountainous, sandy, saline-alkali, and drought-prone areas—as well as in the revitalization of rural industries. Molecular marker technology, with its advantages of stability, accuracy, and efficiency, has become an important tool in jujube genetic breeding research and is widely applied. This article summarizes molecular markers based on three generations of technological intergenerational systems: the first generation of hybridization-based markers (Restriction Fragment Length Polymorphism, RFLP), the second generation of PCR-based markers (represented by Simple Sequence Repeat, SSR), and the third generation of high-throughput sequencing markers (Single Nucleotide Polymorphism, SNP, Genotyping-by-Sequencing, GBS, etc.). A comprehensive classification system based on technical principles, polymorphism sources, and other dimensions is constructed to clearly explain the driving forces and development trends of molecular marker system evolution in jujube tree research, and to clarify the selection criteria and adaptation strategies of molecular markers. Research has found that the second-generation molecular marker SSR is the fundamental core tool for standardized identification of jujube germplasm resources and genetic analysis of low-budget populations. The third-generation molecular markers represented by SNPs and InDel are high-density maps, Genome-Wide Association Study(GWAS), Genomic selection, and other modern precision breeding core carriers, forming a layered complementary technology system, and are gradually becoming the mainstream of research. This paper summarizes the application progress of molecular markers in the precise identification of jujube germplasm resources, analysis of genetic diversity, determination of genetic relationships, construction of high-density genetic maps, genome-wide association analysis, functional gene mapping, and tracing of domestication and evolution. This article integrates all existing research using the unified scientific framework of “technology defect driven tagging iteration”, analyzes the internal logic of the evolution and replacement of different tagging systems, the inherent limitations of early tagging, the existing problems in current research, and discusses future research directions, aiming to provide a reference for the scientific and efficient application of molecular markers in jujube and to promote the improvement and upgrading of the jujube molecular marker-assisted breeding technology system. Full article

Geographical authentication of medicinal plant materials remains challenging because multispectral variables are often highly collinear and sample grouping can complicate reliable model validation. Existing correlation-based feature-selection strategies also require careful adaptation to multiclass problems to avoid artificial ordering of class labels and information leakage during model development. Therefore, this study aimed to develop a compact and leakage-controlled multispectral learning framework for geographical-origin discrimination. This study analyzed 800 physical Pinellia ternata samples from Gansu Xihe, Sichuan Neijiang, Sichuan Chengdu, and Chongqing Dianjiang (200 samples per origin). Each physical sample was represented by 31 mean grayscale intensities calculated from Otsu-segmented multispectral regions of interest. A Pearson-correlation-guided deep multilayer perceptron (PCG-DeepMLP) was constructed by estimating one-vs-rest band relevance and inter-band redundancy only within the training data. The key methodological innovation is a unified multiclass-aware, relevance–redundancy spectral-learning framework in which class-specific one-vs-rest Pearson relevance is coupled with inter-band redundancy control and embedded within leakage-controlled grouped model development. By learning the spectral subset exclusively from each training partition before nonlinear classification, the framework produces compact and complementary multispectral signatures while preserving multiclass structure and strict independence of held-out groups. Model and feature-selection settings were chosen by three-fold grouped cross-validation within each training partition. PCG-DeepMLP retained 9–21 bands and achieved the highest mean accuracy (0.9812 ± 0.0135), macro-F1 (0.9812 ± 0.0135), Matthews correlation coefficient (MCC; 0.9752 ± 0.0179), and macro-AUC (0.9994 ± 0.0006) among seven models. Its macro-F1 was higher than that of 1D-CNN, 1D-ResNet, full-band MLP, PLS-DA, and random forest after Holm correction. Performance was estimated through a strict nested group-wise internal validation scheme, with every outer test fold remaining isolated from feature selection, preprocessing, and model optimization. These findings demonstrate that multiclass-aware relevance–redundancy learning can retain complementary Pinellia ternata origin-discriminative information in a compact and stable spectral representation, enabling accurate geographical-origin authentication while providing a principled basis for reduced-channel acquisition and future independent multi-batch validation. Full article

Forest microclimate strongly influences medicinal plant growth and habitat suitability; however, year-round characterization of forest microclimate for medicinal plant cultivation remains limited. This study presents a year-long, multi-station microclimate dataset and evaluates its potential for preliminary suitability assessment. Three monitoring stations (Pt1–Pt3) were deployed within the Plant Genetic Conservation Project under the Royal Initiative (RSPG), Thailand. Air temperature and relative humidity were continuously monitored at 30-min intervals from January to December 2025 using an Internet of Things (IoT)-based system. We used descriptive statistics, coefficients of variation (CV), repeated-measures analyses, and adjusted pairwise comparisons to evaluate year-round, seasonal, and site-specific microclimatic variabilities. Significant spatial differences were observed among the monitoring stations (p < 0.05). Pt3 exhibited the lowest annual mean temperature (26.05 °C), the highest relative humidity (80.60%), and the lowest environmental variability (CV = 16.41%), whereas Pt2 showed the highest temperature (30.72 °C), the lowest humidity (60.83%), and greater variability. A relative microclimatic comparison showed that Pt3 was cooler, more humid, and more stable; Pt1 exhibited intermediate conditions; and Pt2 was warmer, drier, and more variable. These findings characterize relative temperature–humidity conditions among the monitored sites and provide baseline information relevant to future species-specific assessment of medicinal plant cultivation. Full article

Chinese yam (Dioscorea spp.) is widely used as food and traditional medicine, but varietal differences may affect dried yam slice quality. This study compared ten Chinese yam varieties, examined relationships between raw-material quality indicators and dried yam slice quality, and evaluated hyperspectral imaging for rapid assessment before processing. Significant varietal differences were observed in reducing sugar content, total phenolic content, and texture properties (p < 0.05), and trait–quality relationships were variety-dependent. Spectral preprocessing, variable selection, and regression modelling were used to predict the reference values of reducing sugar content and total phenolic content obtained using the specified analytical procedures, together with fresh-slice hardness. The best models combined principal component analysis with decision tree regression (PCA-DTR), competitive adaptive reweighted sampling with partial least squares regression (CARS-PLSR), and CARS with random forest regression (CARS-RFR), respectively. Prediction-set coefficients of determination ($R_P^2$) were 0.9891, 0.9335, and 0.9314, with root mean square errors of prediction (RMSEP) of 0.0981%, 0.0905 mg gallic acid equivalents/100 g dry weight, and 130.3973 gf, and residual predictive deviation (RPD) values of 9.7535, 3.9438, and 3.8820, respectively. These results support hyperspectral imaging with chemometrics for rapid assessment and selection of yam raw materials for dried yam slice processing. Full article

Circular data arise in a wide range of scientific fields, including meteorology, medicine, biology, and neuroscience, yet existing regression methods for such data are largely restricted to parametric generalized linear models or tree-based methods that impose distributional assumptions on the circular response. In this paper, we propose a family of Bayesian Additive Regression Tree (BART) methods for regression with circular data, covering three cases: Circular–Circular BART (CCBART), where both the response and the covariates are circular; Circular–Linear BART (CLBART), where the response is circular and the covariates are linear; and Linear–Circular BART (LCBART), where the response is linear and the covariates are circular. The proposed methods adopt a projection approach, decomposing circular variables into their sine and cosine components, fitting separate BART models on these projections, and recovering circular predictions via the two-argument arctangent function. This avoids specifying a von Mises or wrapped normal likelihood directly for the circular response, though it does not avoid all distributional assumptions: BART assumes flexible Euclidean regression models, with Gaussian errors, for the projected sine and cosine components. The approach retains the full inferential power of BART, including posterior uncertainty quantification, automatic variable selection, and the ability to capture nonlinear effects and interactions without pre-specification. An extensive simulation study demonstrates that the proposed methods are highly competitive with random forest benchmarks and consistently outperform linear model benchmarks, with the clearest and most consistent advantage over random forests emerging at high noise levels and in the Linear–Circular case, where LCBART achieves up to 34% lower RMSE than projected random forests. Applications to wind direction forecasting and human motor resonance data further illustrate the practical utility of the proposed methods. Full article

Background/Objectives: The whole plant of Tetrastigma hemsleyanum is used medicinally, but the tuberous root is by far the most commonly used part, and the way in which its metabolites are partitioned among organs and among geographic origins underpins both the rational choice of the medicinal part and the evaluation of herb quality. Methods: Here, untargeted metabolomics based on ultra-high-performance liquid chromatography coupled to high-resolution Orbitrap mass spectrometry was used to compare roots, stems and leaves collected from nine regions of southern China (81 samples) with tuberous roots collected from 17 sites in seven provinces (51 samples). Annotations were graded according to the Metabolomics Standards Initiative (MSI), curated with explicit plausibility rules, and every conclusion was re-tested across five nested annotation subsets. Results: Organ identity was the dominant source of metabolic variation: the three organs were completely separable (random forest out-of-bag accuracy 100%), the organ effect was about four times larger than that of sampling region (PERMANOVA pseudo-F 16.7 versus 4.1), and this contrast was essentially unchanged from the complete set of 615 annotations down to the most stringent subset of 19 flavonoids and phenolic acids. The organ-level pattern was chemically coherent: amino acids and lipids were relatively enriched in the tuberous root, soluble sugars and phenolic acids in the stem, and flavonoids and alkaloids in the leaf, matching the contrasting roles of a storage, a transport and a photosynthetic organ. Geographic differences among tuberous roots were, by contrast, weak and largely local: although provinces could be separated with 88.9% out-of-bag accuracy, accuracy fell to 42.2% when an entire, previously unseen collection site was held out (chance level 20%), and to 52.9% for a coarse macro-geographic zone (chance level 25%), whereas holding out an entire sampling region left organ classification unaffected (100%). Conclusions: The present data therefore document a strong, generalisable and chemically interpretable organ division of labour, but do not support the use of this metabolome for origin authentication. Because most annotations remain at MSI Level 3, individual compounds are reported as putative throughout, and all conclusions rest on multivariate and class-level evidence. Full article

The sustainable restoration of tropical dry forest (TDF)—one of the planet’s most threatened ecosystems—is constrained by low community integration and limited cultural relevance, particularly in Afro-descendant territories, where the erosion of oral tradition and forest degradation reinforce one another. This study proposes a quantitative framework to systematize the biocultural memory embedded in oral tradition as an input for socially grounded, sustainable TDF restoration. A corpus of 401 works from the Afro-descendant community of the Patía Valley (Cauca, Colombia) was coded in a multidimensional database of 10 categories, and three indices were computed: the Biocultural Density Index (IDBC), the Biocultural Vulnerability Index (IVB), and an adaptation of Winter’s flora framework (IVBw), in a total version and a version restricted to wild/native species. The framework identifies the works of greatest biocultural density (IDBC max. = 84) and separates cultivated/introduced species of high cultural value (Limón, Yuca, Caña de azúcar), ones relevant to food sovereignty, and from wild/native species (e.g., Caña brava, Cañafístula, Guayacán, Ceiba) that constitute the restorable core. Cultural practices are the hubs of the system, traditional medicine is the most at risk of loss, and food security concentrates 43% of the flora records. These replicable tools link Afro-descendant knowledge to measurable, monitorable restoration priorities, advancing sustainable land management, biodiversity conservation and cultural sustainability. Full article

Alluvial gold mining can alter Amazonian tree communities, but its association with medicinal tree diversity, structure, and carbon stocks remains poorly documented. We compared four 1-ha forest plots in Boca Colorado, Madre de Dios, Peru: two with greater evidence of mining intervention and two less-impacted plots. All medicinal trees with DBH ≥ 10 cm were inventoried, and taxon richness, Hill diversity, rarefaction, floristic dissimilarity, dominance, structural attributes, and biomass carbon were evaluated. A total of 1344 individuals representing 203 taxa were recorded. Mean plot-level richness was higher in less-impacted forests than in impacted forests (135.5 vs. 95.5 taxa), as were diversity of orders q = 1 (79.9 vs. 48.1) and q = 2 (38.7 vs. 23.6). Richness therefore showed a scale-dependent pattern: less-impacted plots were richer individually, whereas impacted forests accumulated more taxa when plots were pooled (172 vs. 143), reflecting greater among-plot differentiation. Turnover accounted for 79.5% of Jaccard dissimilarity. Less-impacted forests also had 16.1% higher stem density and 47.1% higher total biomass carbon, with the carbon contrast supported by the hierarchical bootstrap analysis (p = 0.043). These findings indicate that mining intervention was associated with differences in abundance distribution, floristic composition, forest structure, and carbon stocks that were not captured by pooled richness alone. Full article

As key drivers of soil biogeochemical cycles, soil microbial communities play essential roles in maintaining soil fertility, nutrient cycling, and plant growth. In this study, high-throughput sequencing of 16S rRNA and ITS genes was used to investigate the diversity, the composition, and the driving factors of bacterial and fungal communities in bulk soils across four soil groups collected from different vegetation covers (forest soil (FS), soybean field (PGS), and two Atractylodes japonica cultivation soils (ALO and ALR)) under identical climatic conditions. The results showed that the bacterial α-diversity remained stable across all the vegetation types, whereas the fungal α-diversity and richness were more sensitive to the vegetation type, with the PGS generally exhibiting lower Shannon and Chao1 indices. The β-diversity analysis revealed significant differences in the microbial community structure among the vegetation types, with a stronger effect on fungi (R² = 0.737, p = 0.001) than on bacteria (R² = 0.493, p = 0.001). At the phylum and genus levels, the fungal communities displayed more pronounced shifts than the bacterial communities, which remained relatively stable. A redundancy analysis indicated that the soil chemical properties significantly shaped the microbial community structure (p = 0.002). The microbial communities in the A. japonica soils (ALO and ALR) were primarily driven by pH, available phosphorus, and available potassium, while the FS and PGS communities were more strongly influenced by soil organic carbon, total nitrogen, and nitrogen forms (NH₄⁺-N and NO₃⁻-N). The Spearman correlation and functional prediction analyses further confirmed that the key soil factors differentially regulated the abundance and ecological functions of the dominant microbial taxa. These findings demonstrate the vegetation-specific assembly of soil microbial communities and highlight the distinct edaphic drivers associated with A. japonica cultivation, providing a scientific basis for soil health management and the sustainable cultivation of this medicinal plant. Full article

Background: Suicide is a leading cause of preventable death, yet machine learning (ML) analyses of forensic (medico-legal) suicide data are scarce and, to our knowledge, absent for Romania. Population-based forensic registries offer exhaustive, autopsy-confirmed coverage that is structurally distinct from clinical or civil death-registration data. We applied supervised and unsupervised ML to a complete regional medico-legal suicide registry to profile the method of death and to identify latent victim subgroups of preventive relevance. Methods: We analysed 395 consecutive suicide deaths (Galați and Brăila counties, ≈750,000 inhabitants; 2018–2024). Two supervised classifiers—L2-regularised logistic regression (LR) and random forest (RF, 200 trees)—were trained to discriminate hanging from other methods, using eleven sociodemographic and clinical predictors, and evaluated by 10-fold stratified cross-validation. Given severe class imbalance, the area under the ROC curve (AUC) was the primary metric. Model hyperparameters were fixed a priori, and no class-imbalance correction was applied; both decisions are pre-specified and justified in the Methods. Robustness was assessed by stratified non-parametric bootstrap confidence intervals for the odds ratios, a tipping-point sensitivity analysis for the undocumented clinical fields, and Ward-linkage hierarchical clustering as an independent partitioning check. Predictor importance was quantified by out-of-bag (OOB) permutation importance and Spearman correlations. Unsupervised structure was assessed by K-means clustering (k = 2–7), with the optimal solution selected by the average silhouette coefficient and the elbow (WCSS) criterion. Reporting followed TRIPOD+AI and STROBE. Results: The study population was predominantly male (87.1%) and rural (73.2%), with a mean age of 54.1 years; hanging accounted for 94.2% of deaths—far above the European average (≈50%). RF achieved AUC = 0.865 ± 0.181 and LR AUC = 0.847 ± 0.192, both within the “excellent” discrimination band; sensitivity was very high (0.995–0.997) and specificity was limited (0.233–0.367), an expected consequence of imbalance. Prior suicide attempts (OOB importance 0.959; Spearman ρ = −0.549, p < 0.001; OR = 0.496, 95% CI 0.25–0.72) and the presence of a suicide note (importance 0.575; ρ = −0.439, p < 0.001; OR = 0.549, 95% CI 0.34–0.76) were the dominant predictors. K-means identified two well-separated clusters (silhouette = 0.707), and the partition was reproduced exactly by Ward-linkage hierarchical clustering (adjusted Rand index = 1.000). Cluster 2 (n = 19; 4.8%) was a clinically distinct, younger subgroup (42.4 vs. 54.7 years) characterised by prior attempts (57.9% vs. 0%), suicide notes (68.4% vs. 0%), higher psychiatric comorbidity (52.6% vs. 30.9%) and lower hanging proportion (36.8% vs. 97.1%)—an exploratory, hypothesis-generating profile of recurrent suicidal behaviour with documented prior contact with the medical or medico-legal system. The principal findings were stable across all plausible degrees of clinical under-documentation in the tipping-point sensitivity analysis. Conclusions: ML applied to a complete forensic suicide registry reproduced known regional epidemiology and, beyond classical statistics, isolated an exploratory but clinically coherent high-risk subgroup of direct relevance to the audit of structured post-attempt follow-up. This is, to our knowledge, the first ML study of Romanian forensic suicide data and supports integrating ML into medico-legal research and into the regional targeting and audit of existing post-attempt follow-up provision. Full article

Background/Objectives: Early identification of breast cancer patients unlikely to benefit from neoadjuvant chemotherapy (NAC) remains a pressing clinical problem because ineffective therapy delays definitive surgery and exposes patients to unnecessary toxicity. Quantitative ultrasound (QUS) and shear wave elastography (SWE) probe complementary tissue properties—scatterer microstructure and mechanical stiffness—that may change before macroscopic tumor shrinkage. This study aimed to evaluate whether multi-parametric ultrasound (mpUS) radiomic kinetics, analyzed with a machine learning ensemble and interpreted with SHAP, could predict pathologic response to NAC. Methods: A prospective observational cohort enrolled 135 women with biopsy-proven stage II–III breast cancer treated with NAC within the multidisciplinary breast pathway shared between Vasile Goldis Western University of Arad and Victor Babes University of Medicine and Pharmacy Timisoara (Pius Brinzeu County Emergency Hospital). All patients underwent standardized QUS and SWE acquisitions at baseline, week 1, and week 3. Response was defined pathologically at surgery as residual cancer burden (RCB) class 0/I versus II/III. Group comparisons used Welch’s t-test, Mann–Whitney U, chi-square, and Fisher’s exact tests; correlations used Spearman’s rho. A stacked machine learning ensemble (four base learners—XGBoost, random forest, support vector machine, and L2-penalized logistic regression—combined by a separate second-stage logistic meta-learner) was trained with nested 10-fold cross-validation, bootstrap stability assessment, SHAP-based interpretability, and decision curve analysis. Results: Sixty patients (44.4%) were responders and 75 (55.6%) were non-responders. Responders showed greater week 3 increases in mid-band fit (3.4 ± 0.9 vs. 1.2 ± 0.8 dB, p < 0.001), entropy (0.7 ± 0.2 vs. 0.2 ± 0.2, p < 0.001), and more pronounced SWE mean stiffness reduction (−44.1 ± 9.7 vs. −12.1 ± 8.6 kPa, p < 0.001). The stacked ensemble integrating clinical, QUS, and SWE kinetic features reached an AUC of 0.93 (95% CI 0.88–0.97) versus 0.71 for the clinical-only model (all reported performance figures represent internal cross-validation only). SHAP analysis identified Δ MBF and Δ entropy at week 3 as the dominant features, with high bootstrap stability. Conclusions: Multi-parametric ultrasound radiomic kinetics integrated through a machine learning ensemble may provide an interpretable early-response biomarker for NAC in breast cancer, pending external validation. Full article

Background: Machine learning (ML) is increasingly applied in medicine, underscoring the need for transparent and clinically relevant models. In gastrointestinal oncology, most ML studies rely on raw imaging data, which limits clinical adoption due to poor interpretability and the difficulty of collecting high-quality, large-scale video and image datasets in routine practice. Endoscopic ultrasound (EUS) plays a central role in the evaluation of pancreatic cancer; however, structured EUS features remain underused in predictive modeling. Objective: To assess the performance and interpretability of ML models for diagnosing pancreatic ductal adenocarcinoma (PDAC) using routinely collected EUS variables. Methods: We conducted a retrospective multicenter study using data from two Italian hospitals (n = 641) for model training and internal validation and from a third hospital (n = 120) for external validation, collected from 2015 to 2023. Decision trees, random forests, naïve Bayes and other classifiers were developed and evaluated. Model performance was assessed in terms of discriminative ability, calibration, and selective prediction. Results: All models demonstrated high discriminative performance (AUC ≥ 0.90). Decision trees provided the most favorable balance between interpretability and accuracy (balanced accuracy = 0.87; sensitivity = 0.89). Calibration and selective prediction analyses confirmed the robustness of the models. Conclusions: These findings demonstrate the feasibility of implementing interpretable yet high-performing ML models for PDAC diagnosis in real-life endoscopic settings. Full article

Background: Polymyalgia rheumatica (PMR) is a clinically heterogeneous inflammatory disorder in which conventional acute-phase reactants may inadequately reflect the complexity and biological variability of disease activity. Precision medicine approaches integrating multidimensional clinical and laboratory data may offer a more comprehensive characterization of inflammatory phenotypes. This study investigated whether the combined assessment of cytokine profiles, routine laboratory biomarkers, ultrasound findings, and clinical variables could improve disease activity stratification in PMR. Methods: A total of 103 consecutive patients with PMR were retrospectively analyzed. Disease activity was assessed using the PMR Activity Score (PMR-AS) and, for exploratory purposes, dichotomized according to the cohort median (≥11 vs. <11). Group differences were evaluated using non-parametric statistical methods. The multidimensional structure of the dataset was explored through Spearman correlation analysis, principal component analysis (PCA), and unsupervised clustering. Predictive models, including logistic regression, random forest, and gradient boosting, were developed to evaluate the potential contribution of integrated analytical approaches to patient stratification. Results: The study cohort included 103 patients (63.1% female), with a median age of 76 years (IQR 71–81); 57 patients (55.3%) presented PMR-AS ≥11. Patients with higher disease activity exhibited significantly increased levels of CRP, fibrinogen, platelet count, IL-6, serum amyloid A (SAA), and myeloid-related protein (MRP), together with a higher prevalence of joint effusion and Power Doppler positivity. Among the evaluated biomarkers, SAA demonstrated the strongest correlation with disease activity (Spearman ρ = 0.878; p < 0.001). Multivariate predictive modeling showed high discriminative performance, with random forest achieving the highest cross-validated AUC (0.934), whereas gradient boosting demonstrated the best overall accuracy (0.883). Unsupervised clustering analysis identified a subgroup characterized by a more pronounced inflammatory signature associated with higher PMR-AS values. Conclusions: These findings support the concept that disease activity in PMR may be more effectively represented through an integrated multidimensional inflammatory profile rather than isolated biomarkers. The combined evaluation of routine laboratory parameters, cytokines, and imaging features may contribute to more refined patient stratification within a precision medicine framework. Although exploratory, these results highlight the potential value of advanced data integration strategies for supporting biologically informed disease characterization in PMR, while underscoring the need for external validation before translation into clinical practice. Full article

First-trimester prediction of preeclampsia (PE) remains a major clinical challenge, particularly outside specialized fetal medicine centers. This study aimed to identify and validate serum protein biomarkers for early PE prediction using an integrated proteomic approach. A prospective cohort of 64 first-trimester singleton pregnancies (32 future PE cases, 32 matched controls) was analyzed. Untargeted proteomics was performed using DIA-PASEF-MS, followed by targeted cross-platform verification with MRM-MS. Machine learning classifiers (support vector machines, SVM, and random forest) were trained on differentially abundant proteins (FDR < 0.01, VIP > 1.5). DIA-MS identified 33 protein markers associated with complement activation, IGF transport regulation, and platelet degranulation. An SVM model with a linear kernel achieved 95% accuracy (AUC = 0.95, sensitivity = 95%, specificity = 97%). Four markers (AFM, AHSG, C8A, IGHG1) were confirmed across platforms, confirming the discovery findings. Cross-platform correlation was high: 71% of overlapping proteins showed r > 0.5 (p < 0.001), with the highest concordance observed for potential PE marker AHSG (r = 0.8, p < 0.001). PRSS1, IGHV1-4, and SERPINC1 showed a strong correlation with proteinuria (|r| > 0.5, p < 0.05), linking the proteomic signature to clinical severity. Integrated DIA-MS and MRM-MS proteomics yields a reproducible, high-performance serum signature for first-trimester PE prediction. The identified markers reflect core pathophysiological pathways and offer potential to augment current FMF-based screening algorithms. Full article

Medicinal plant research increasingly combines heterogeneous public data, but data leakage and unsupported biological inference remain major risks. We developed a leakage-aware framework separating taxon–compound evidence ranking from environmental niche characterization. Six taxa and ten molecules or broad classes formed 60 taxon–compound pairs (27 supported and 33 below-threshold background); primary modeling used 36 specific-molecule pairs (8 supported and 28 unlabeled background) and five compound-matched pathway/chemical predictors. Under leave-one-taxon-out validation, the prespecified balanced random forest achieved a balanced accuracy of 0.621 (95% fold interval: 0.500–0.800; accuracy: 0.694; precision: 0.250; recall: 0.500; permutation: p = 0.154). Matched-pathway-only and molecular-weight-only benchmarks achieved 0.662 and 0.358, respectively, and a post hoc logistic comparator achieved 0.646. The cross-molecule balanced accuracy was 0.746 (fold interval: 0.516–0.975). Evidence scores correlated moderately with out-of-fold probabilities (Spearman: ρ = 0.39, p = 0.017). Environmental analyses used 248 SoilGrids and 324 NASA POWER taxon × exact-cell rows. The spatially restricted PERMANOVA was non-significant for soil (R² = 0.257, p = 0.067) and climate (R² = 0.233, p = 0.075), whereas grouped taxon classifiers achieved balanced accuracies of 0.479 and 0.547 (permutation: p = 0.005 for both). Environmental-only compound controls were non-significant. The outputs provide an auditable exploratory ranking workflow, but predictive validity for taxon–compound prioritization was not established. Full article