Search Results (1,313)

RNA-binding proteins (RBPs) play essential roles in all major steps of RNA processing. Genetic studies in human and mouse models support that many RBPs are crucial for maintaining homeostasis in key tissues/organs, but to what extent the function of RBPs is conserved between humans and mice is not clear. Our recent study using a chimeric humanized liver mouse model found that knocking down human HuR in human hepatocytes resulted in a broad upregulation of human genes involved in fatty acid catabolism. This regulation is human-specific, as the knocking down of mouse HuR in the liver of traditional mouse models did not show these effects. To further study this human-specific role of HuR, we co-overexpressed HuR with PPARα, a master transcription factor that promotes fatty acid catabolism, in cultured cells. We found that HuR suppressed the expression of PPARα-induced fatty acid catabolism genes in human cells but not in mouse cells. We provide evidence supporting that the human-specific suppressive effect of HuR is independent of PPARα expression or location. The regulatory effects of HuR are also independent of its role in regulating mRNA stability. Using the human HMGCS2 gene as an example, we found that the suppressive effect of HuR cannot be explained by decreased promoter activity. We further provide evidence supporting that HuR suppresses the pre-mRNA processing of HMGCS2 gene, leading to accumulated intron/pre-mRNA expression of HMGCS2 gene. Furthermore, overexpression of HuR blocked and knocking down of HuR sensitized PPARα agonist-induced gene expression. By analyzing published RNA-seq data, we found compromised pre-mRNA processing for fatty acid catabolism genes in patients with fatty liver diseases, which was not observed in mouse fatty liver disease models. Our study supports the model that HuR suppresses the expression of fatty acid catabolism genes by blocking their pre-mRNA processing, which may partially explain the mild effects of PPARα agonists in treating fatty liver diseases in humans as compared with studies in mice. Full article

Buffaloes are a vital genetic resource for dairy production, yet advancements in improving milk production have been somewhat limited. In this study, we performed an integrated analysis of genomic sequencing data from 78 water buffaloes and their milk production traits, with a focus on 305-day milk yield (MY). Leveraging advancements in sequencing technology alongside genome-wide association study (GWAS) methods such as cBLUP, GMATs, and BayesR, we aimed to identify genetic factors that could facilitate the breeding of high-quality buffaloes. Our analysis revealed two significant SNPs associated with milk production traits. Based on these markers, four candidate genes were identified within the surrounding genomic regions. These genes showed significant enrichment in lactation-related pathways, including the prolactin signaling pathway (mitogen-activated protein kinase 10, MAPK10), IL-17 signaling pathway (MAPK10), MAPK signaling pathway (MAPK10), and adipocytokine signaling pathway (MAPK10). The identification of these candidate genes, particularly MAPK10, provides a robust theoretical basis for molecular breeding strategies aimed at enhancing milk production in buffaloes. This work paves the way for more targeted and effective breeding programs in the future. Full article

RNA virus populations exist as quasispecies-complex, dynamic clouds of closely related but genetically diverse variants generated by high mutation rates during replication. Assessing quasispecies structure and diversity is crucial for understanding viral evolution, adaptation, and response to antiviral treatments. However, comparing single quasispecies observations from individual biosamples, especially at different infection or treatment time points, presents statistical challenges. Traditional inferential tests are inapplicable due to the lack of replicate observations, and resampling-based approaches such as the bootstrap and jackknife are limited by biases and non-independence, particularly for diversity indices sensitive to rare haplotypes. In this study, we address these limitations by applying the delta method to derive analytical variances for a set of quasispecies structure indicators specifically designed to assess the quasispecies maturation state. We demonstrate the utility of this approach using high-depth next-generation sequencing data from hepatitis C virus (HCV) quasispecies evolving in vitro under various conditions, including free evolution and exposure to antiviral or mutagenic treatments. Our results reveal that with highly fit HCV quasispecies, sofosbuvir inhibits quasispecies genetic diversity, while mutagenic treatments accelerate maturation, compared to untreated controls. We emphasize the interpretation of results through absolute differences, log-fold changes, and standardized effect sizes, moving beyond mere statistical significance. This framework enables robust, quantitative comparisons of quasispecies diversity from single observations, providing valuable insights into viral adaptation and treatment response. The R code and session info with required libraries and versions is provided in the supplementary material. Full article

The dry-bulb temperature is a critical parameter in weather forecasting, agriculture, energy management, and climate research. This work proposes a new hybrid prediction model (FBSE-GA-LSTM) that integrates the Fourier–Bessel series expansion (FBSE), genetic algorithm (GA), and long short-term memory (LSTM) networks together to predict the dry-bulb air temperature. The hybrid model FBSE-GA-LSTM utilises the FBSE to decompose time series data of interest into an attempt to remove the noise level for capturing the dominant predictive patterns. Then, the FBSE is embedded into the GA method for the best feature selection and dimension reduction. To predict the dry-bulb temperature, a new model (FBSE-GA-LSTM) was used by hybridising a proposed model FBSE-GA with the LSTM model on the time series dataset of two different regions in Saudi Arabia. For comparison, the FBSE and GA models were hybridised with a bidirectional LSTM (BiLSTM), gated recurrent unit (GRU), and bidirectional gated recurrent unit (BiGRU) models to obtain the hybrid FBSE-GA-BiLSTM, FBSE-GA-GRU, and FBSE-GA-BiGRU models along with their standalone versions. In addition, benchmark models, including the climatic average and persistence approaches, were employed to demonstrate that the proposed model outperforms simple baseline predictors. The experimental results indicated that the proposed hybrid FBSE-GA-LSTM model achieved improved prediction performance compared with the contrastive models for the Jazan region, with a mean absolute error (MAE) of 1.458 °C, a correlation coefficient (R) of 0.954, and a root mean squared error (RMSE) of 1.780 °C, and for the Jeddah region, with an MAE of 1.459 °C, an R of 0.952, and an RMSE of 1.782 °C, between the predicted and observed values of dry-bulb air temperature. Full article

The aggregation of α-synuclein (αSyn) is a central feature of Parkinson’s disease (PD) and other synucleinopathies. The efficient clearance of αSyn depends largely on the autophagy–lysosomal pathway. Emerging genetic evidence highlights the role of pleckstrin homology and RUN domain-containing M1 protein (PLEKHM1), a critical regulator of autophagosome–lysosome fusion, in the pathogenesis of multiple neurodegenerative diseases. This study investigates the possible effects of increased PLEKHM1 expression on αSyn pathology and neurodegeneration in mice. We utilized a mouse model of PD that is based on A53T-αSyn overexpression, achieved by the stereotactic injection of recombinant adeno-associated viral vectors (rAAV) into the substantia nigra. Additionally, this study explores the effect of PLEKHM1 overexpression on the autophagy–lysosomal pathway under physiological conditions, using transgenic autophagy reporter mice. PLEKHM1 overexpression facilitated the αSyn-induced degeneration of dopaminergic somata in the substantia nigra and degeneration of dopaminergic axon terminals in the striatum. In concert with αSyn expression, PLEKHM1 also potentiated microglial activation. The extent of αSyn pathology, as reported by staining for phosphorylated αSyn, was not affected by PLEKHM1. Using RFP-EGFP-LC3 autophagy reporter mice, rAAV-mediated PLEKHM1 overexpression reduced lysosomal and autolysosomal area, increased LAMP1-LC3 colocalization, and decreased the autolysosome-to-autophagosome ratio. Concurrently, PLEKHM1 overexpression in both genotypes caused p62 accumulation, accompanied by reduced overlap with lysosomal and autophagosomal markers but increased colocalization with autolysosomal markers, indicating impaired cargo degradation during late-stage autophagy. Taken together, elevated PLEKHM1 levels exacerbate neurodegeneration in αSyn-overexpressing mice, possibly by impairing autophagic flux. Now, with in vivo evidence complementing genetic data, alterations in PLEKHM1 expression appear to compromise autophagy, potentially enhancing neuronal vulnerability to secondary insults like αSyn pathology. Full article

Background and Objectives: Laryngeal cancer is a common head and neck tumor burden, with no significant improvements in long term patient survival. Despite the progress of molecular genetics and oncology strategies, there is still a lack of biomarker use in routine clinical practice for early laryngeal cancer screening or diagnosis. miRNAs are explored as promising molecules, that could serve as liquid biopsy. Our goal is to explore the screening potential of miR-31-3p and miR-196a-5p in early- and advanced-stage laryngeal HPV-negative plasma samples. Methods: In this study, 50 plasma samples obtained from early and advanced HPV-negative laryngeal cancer patients were included. The expression levels of mir-31-3p and miR-196a-5p were analyzed via TaqMan RT-qPCR. SPSS v27.0 was used for statistical analysis. Results: For the first time, miR-31-3p and miR-196a-5p were analyzed in plasma samples from early HPV-negative primary LSCC patients. Both circulating miRNAs showed significantly elevated expression levels in early and advanced laryngeal cancer samples. miR-31-3p was significantly associated with T stages (p < 0.001) and N stages (p = 0.009). The ROC analysis revealed that miR-31-3p could significantly discriminate early-stage from advanced-stage LSCC with an AUC of 0.850 (95% CI: 0.743–0.956, p < 0.001) at an RQ cutoff of 2.03, achieving a sensitivity of 95.5% and a specificity of 64%. Nevertheless, miR-196a-5p was found to be significantly overexpressed in early-stage LSCC, which could contribute to the development of its screening potential. For the first time, both miRNAs revealed a significant positive correlation, which indicates that miR-31-3p and miR-196a-5p could coregulate cancerogenesis. Conclusions: In conclusion, the data revealed that miR-31-3p has greater potential as an LSCC screening marker in comparison to miR-196a-5p. Still, miR-196a-5p also showed promising results in early-stage laryngeal cancer monitoring. The utilization of circulating miR-31-3p or miR-196a-5p analysis could enable liquid biopsy approaches, with results potentially informing treatment monitoring strategies, personalized oncological protocols, and early diagnosis. These advancements could ultimately benefit patient outcomes by improving laryngeal organ preservation and survival rates. Full article

Urbanization in China and the proliferation of high-rise office buildings have led to increased demand for daylighting and thermal comfort. These requirements often result in reliance on active systems, including heating, cooling, and artificial lighting, which increase energy consumption. Existing studies have often focused on individual cases or room-scale models, which makes it difficult to generalize findings to the design of various high-rise office building types. Therefore, in this study, parametric prototype building models for high-rise office buildings were developed based on surveys of completed and under-construction projects. These surveys reflected actual design practices and were used to support systematic performance evaluation and typology-level optimization. Building performance was simulated using Grasshopper and Honeybee to generate large-scale datasets, and stacking ensemble learning models were used as surrogate predictors for energy use, daylighting, and thermal comfort. Multi-objective optimization was conducted using the non-dominated sorting genetic algorithm III (NSGA-III), followed by strategy formulation. The results revealed the following: (1) the proposed prototype model establishes clear parameter ranges for geometry, envelope design, and thermal performance, offering reusable models and data; (2) the stacking ensemble model outperforms individual models, improving the coefficient of determination (R²) by 0.5–16.1%, with mean squared error (MSE) reductions of 4.4–70.6%, and mean absolute error (MAE) reductions of 2.8–45.8%; (3) space length, aspect ratio, usable area ratio, window U-value, and solar heat gain coefficient (SHGC) were identified as primary performance drivers; and (4) optimized solutions reduced energy use by 3.79–11.81% and enhanced daylighting comfort by 40.16–50.32% while maintaining thermal comfort. The proposed framework provides localized, data-driven guidance for early-stage performance optimization in high-rise office building design. Full article

Obesity is an epidemic that currently impacts many nations. The persistence of this disease is shaped by both genetic and epigenetic factors that extend beyond calorie balance. Research in the past year has revealed that epigenetic and cellular memory within adipose tissue can predispose individuals to weight regain after initial fat loss, as shown by studies indicating persistent transcriptional and chromatin changes even after fat mass reduction. Independent studies also demonstrate long-lasting metabolic shifts, such as those triggered by glucose-dependent insulinotropic polypeptide receptor (GIPR)-induced thermogenesis and sarcolipin (SLN) stabilization that also support a form of “metabolic memory” that is associated with sustained weight loss. At the neural level, rare variants in synaptic genes like BSN (Bassoon presynaptic cytomatrix protein), a presynaptic scaffold protein, and APBA1 (amyloid beta precursor protein binding family A member 1), a neuronal adaptor involved in vesicular trafficking, disrupt communication in feeding circuits, elevating obesity risk and illustrating how synaptic integrity influences food intake regulation. Similarly, the spatial compartmentalization of metabolic signaling within neuronal cilia is emerging as crucial, with cilia-localized receptors G protein-coupled receptor 75 (GPR75) and G protein-coupled receptor 45 (GPR45) exerting opposing effects on energy balance and satiety. Meanwhile, genome-wide association studies (GWAS) have advanced through larger, more diverse cohorts and better integration of environmental and biological data. These studies have identified novel obesity-related loci and demonstrated the value of polygenic risk scores (PRS) in predicting treatment responses. For example, genetic variants in GLP-1R (glucagon-like peptide-1 receptor) and GIPR (glucose-dependent insulinotropic polypeptide receptor) may modulate the effectiveness of incretin-based therapies, while PRS for satiation can help match individuals to the most appropriate anti-obesity medications. This review focuses on studies in the last two years that highlight how advances in obesity genetics are driving a shift toward more personalized and mechanism-based treatment strategies. Full article

Background/Objectives: Developmental dyslexia is characterised by neuropsychological processing deficits and marked hemispheric functional asymmetries. To uncover latent neurophysiological features linked to reading impairment, we applied dimensionality reduction and clustering techniques to high-density electroencephalographic (EEG) recordings. We further examined the functional relevance of these features to reading performance under standardised test conditions. Methods: EEG data were collected from 200 children (100 with dyslexia and 100 age- and IQ-matched typically developing controls). Principal Component Analysis (PCA) was applied to high-dimensional EEG spectral power datasets to extract latent neurophysiological components. Twelve principal components, collectively accounting for 84.2% of the variance, were retained. K-means clustering was performed on the PCA-derived components to classify participants. Group differences in spectral power were evaluated, and correlations between principal component scores and reading fluency, measured by the TILLS Reading Fluency Subtest, were computed. Results: K-means clustering trained on PCA-derived features achieved a classification accuracy of 89.5% (silhouette coefficient = 0.67). Dyslexic participants exhibited significantly higher right parietal–occipital alpha (P8) power compared to controls (mean = 3.77 ± 0.61 vs. 2.74 ± 0.56; p < 0.001). Within the dyslexic group, PC1 scores were strongly negatively correlated with reading fluency (r = −0.61, p < 0.001), underscoring the functional relevance of EEG-derived components to behavioural reading performance. Conclusions: PCA-derived EEG patterns can distinguish between dyslexic and typically developing children with high accuracy, revealing spectral power differences consistent with atypical hemispheric specialisation. These results suggest that EEG-derived neurophysiological features hold promise for early dyslexia screening. However, before EEG can be firmly established as a reliable molecular biomarker, further multimodal research integrating EEG with immunological, neurochemical, and genetic measures is warranted. Full article

This study presents a novel cyber-resilient, data-driven optimisation framework for real-time energy management in electric vehicle (EV)-integrated smart grids. The proposed framework integrates a hybrid optimisation engine—combining genetic algorithms and reinforcement learning—with a real-time analytics module to enable adaptive scheduling under uncertainty. It accounts for dynamic electricity pricing, EV mobility patterns, and grid load fluctuations, dynamically reallocating charging demand in response to evolving grid conditions. Unlike existing GA/RL schedulers, this framework uniquely integrates adaptive optimisation with resilient forecasting under incomplete data and lightweight blockchain-inspired cyber-defence, thereby addressing efficiency, accuracy, and security simultaneously. To ensure secure and trustworthy EV–grid communication, a lightweight blockchain-inspired protocol is incorporated, supported by an intrusion detection system (IDS) for cyber-attack mitigation. Empirical evaluation using European smart grid datasets demonstrates a daily peak demand reduction of 9.6% (from 33 kWh to 29.8 kWh), with a 27% decrease in energy delivered at the original peak hour and a redistribution of demand that increases delivery at 19:00 h by nearly 25%. Station utilisation became more balanced, with weekly peak normalised utilisation falling from 1.0 to 0.7. The forecasting module achieved a mean absolute error (MAE) of 0.25 kWh and a mean absolute percentage error (MAPE) below 20% even with up to 25% missing data. Among tested models, CatBoost outperformed LightGBM and XGBoost with an RMSE of 0.853 kWh and $R^2$ of 0.416. The IDS achieved 94.1% accuracy, an AUC of 0.97, and detected attacks within 50–300 ms, maintaining over 74% detection accuracy under 50% novel attack scenarios. The optimisation runtime remained below 0.4 s even at five times the nominal dataset scale. Additionally, the study outlines a conceptual extension to support location-based planning of charging infrastructure. This proposes the alignment of infrastructure roll-out with forecasted demand to enhance spatial deployment efficiency. While not implemented in the current framework, this forward-looking integration highlights opportunities for synchronising infrastructure development with dynamic usage patterns. Collectively, the findings confirm that the proposed approach is technically robust, operationally feasible, and adaptable to the evolving demands of intelligent EV–smart grid systems. Full article

Background: The Space Omics and Medical Atlas (SOMA) is an extensive database containing gene expression information from samples collected during the short-duration Inspiration4 spaceflight mission in 2021. Given our prior understanding of the genetic basis for cardiovascular diseases in spaceflight, including orthostatic intolerance and cardiac deconditioning, we aimed to characterize changes in differential gene expression among astronauts using SOMA-derived data and curated cardiovascular pathways. Methods: Using the KEGG 2021 database, we curated a list of genes related to cardiovascular adaptations in spaceflight, focusing on pathways such as fluid shear stress and atherosclerosis, lipid metabolism, arrhythmogenic ventricular hypertrophy, and cardiac muscle contraction. Genes were cross-matched to spaceflight-relevant datasets from the Open Science Data Repository (OSDR). Differential expression analysis was performed using DESeq2 (v1.40.2, R) with normalization by median-of-ratios, paired pre-/post-flight covariates, and log2 fold change shrinkage using apeglm. Differentially expressed genes (DEGs) were defined as |log2FC| ≥ 1 and FDR < 0.05 (Benjamini–Hochberg correction). Module score analyses were conducted across SOMA cell types to confirm conserved cardiac adaptation genes. Results: A total of 185 spaceflight-relevant genes were analyzed. Statistically significant changes were observed in immune-related cardiovascular pathways, particularly within monocytes and T cells. Persistent upregulation of arrhythmogenic genes such as GJA1 was noted at post-flight day 82. WikiPathways enrichment revealed additional pathways, including focal adhesion, insulin signaling, and heart development. Conclusions: Short-duration spaceflight induces significant gene expression changes that are relevant to cardiovascular disease risk. These changes are mediated largely through immune signaling and transcriptional regulation in peripheral blood mononuclear cells. Findings highlight the need for tailored countermeasures and longitudinal monitoring in future long-duration missions. Full article

The Naozhou stock of large yellow croakers (Larimichthys crocea) exhibits unique phenotypic traits and high genetic diversity, making it a valuable resource for selective breeding and genetic conservation in aquaculture. Despite its importance, simple sequence repeat (SSR) markers have not been developed for this stock, which limits efforts in genetic evaluation, breeding optimization, and sustainable utilization of this commercially important species. In this study, 195,263 SSRs were identified from the genome of the Naozhou stock of large yellow croaker, covering a total length of 16,578,990 bp with a density of 288 bp/Mb. Dinucleotide repeats were the most common, with the AC motif being the most prevalent. The frequency of SSR markers ranged from 245.63 to 346.60 per Mb. A total of 30 primer pairs were synthesized, of which 28 pairs (93.3%) successfully amplified clear and reproducible bands in PCR assays. Among these, 28 SSR markers exhibited distinct and reproducible bands following gel electrophoresis. For eight SSR loci, the number of alleles (Na) ranged from 4 to 22 (mean = 11.375), while the effective number of alleles (Ne) ranged from 1.5401 to 10.4727 (mean = 5.6475). The assembled mitochondrial genome (mtDNA) was 16,467 bp in length and comprised 37 genes, including 13 protein-coding genes (PCGs), 22 tRNA genes, and 2 rRNA genes. The total sequence length of the PCGs was 11,431 bp, accounting for 69.4% of the mtDNA. A large portion of the PCGs (5) used incomplete stop codons (e.g., nad2, nad3, cox2), while others used TAA stop codons (e.g., nad6, nad5, TrnT). The mtDNA encoded a total of 3808 codons, with UAA showing the highest relative synonymous codon usage value. The SSR markers and mtDNA data generated in this study provide valuable tools for future genetic breeding and genomic research on the Naozhou stock of large yellow croakers. Full article

Aboveground biomass (AGB) in grasslands is a vital metric for assessing ecosystem functioning and health. Accurate and efficient AGB estimation is essential for the scientific management and sustainable use of grassland resources. However, achieving low-cost, high-efficiency AGB estimation via remote sensing remains a key challenge. This study integrates Sentinel-1 and Sentinel-2 imagery to derive 38 multi-source feature variables, including backscatter coefficients, texture, spectral reflectance, vegetation indices, and topographic factors. These features are combined with AGB data from 112 field plots in the Three Parallel Rivers area. Feature selection was performed using Pearson correlation, Random Forest (RF), and SHAP values to identify optimal variable sets. Genetic Programming (GP) was then applied for nonlinear optimization of the selected features. Three machine learning models—RF, GBRT, and KNN—were used to estimate AGB and generate spatial distribution maps. The results revealed notable differences in model accuracy, with RF performing best overall, outperforming GBRT and KNN. After GP optimization, all models showed improved performance, with the RF model based on RF-selected features achieving the highest accuracy (R² = 0.90, RMSE = 0.31 t/ha, MAE = 0.23 t/ha), improving R² by 0.03 and reducing RMSE and MAE by 0.05 and 0.03 t/ha, respectively. Spatial mapping showed the AGB ranged from 0.41 to 3.59 t/ha, with a mean of 1.39 t/ha, closely aligned with the actual distribution characteristics. This study demonstrates that the RF model, combined with multi-source features and GP optimization, provides an effective approach to grassland AGB estimation and supports ecological monitoring in complex areas. Full article

Echinostomatidae is a taxonomically complex group with substantial species diversity and richness. The vast majority of species in this family parasitize birds and mammals, including humans, causing significant economic losses and medical costs. In this study, Echinostoma miyagawai (Digenea, Echinostomatidae) and Patagifer bilobus (Digenea, Echinostomatidae) were isolated from domestic duck and Grus japonensis, respectively. The nearly complete ribosomal transcription unit (rTU) sequences of two echinostomes were obtained, with the rTU for P. bilobus being obtained for the first time. The nearly complete rTU sequence of P. bilobus (6790 bp) and E. miyagawai (6893 bp) encompass the small-subunit (18S) ribosomal DNA (rDNA), internal transcribed spacer 1 (ITS1), 5.8S rDNA, internal transcribed spacer 2 (ITS2), and large-subunit (28S) rDNA. The complete lengths of 18S, ITS1, 5.8S, ITS2, and 28S sequences for E. miyagawai are 1989 bp, 444 bp, 162 bp, 431 bp, and 3858 bp, respectively. For P. bilobus, complete or nearly complete lengths of these sequences are 1929 bp (nearly complete), 419 bp, 162 bp, 432 bp, and 3848 bp (nearly complete), respectively. The 18S, ITS, and 28S sequences of E. miyagawai show the highest sequence similarity with other E. miyagawai. The ITS and 28S sequences of P. bilobus show the highest sequence similarity with other P. bilobus, while 18S sequence shows the highest similarity with E. miyagawai. This is likely due to the unavailability of the 18S sequence of P. bilobus in GenBank. Repeat sequences were identified in 18S, ITS1, ITS2, and 28S sequences, with the 28S sequence containing the most repeats and the 5.8S sequence having none. The results of phylogenetic reconstruction indicated that E. miyagawai clusters with other Echinostoma spp., while P. bilobus clusters with other Patagifer spp., forming sister taxa. This study not only provides the first rTU sequence for P. bilobus but also reinforces the sister group status of Patagifer to Echinostoma through phylogenetic evidence. Finally, this study represents the first record of the G. japonensis as a new host for P. bilobus and the first report of a bird from the crane family (Gruidae) as a host for any echinostome species. These findings are significant as they expand our understanding of the host range and ecological interactions of Echinostomatidae. The data obtained provide a valuable resource of molecular markers for studying the taxonomy, population genetics, and systematics of the family Echinostomatoidea. This research contributes to a more comprehensive understanding of the evolutionary relationships and biodiversity within this complex group of parasites, which is crucial for developing effective strategies to mitigate their impact on both wildlife and human health. Full article

The early determination of the type and severity of stresses caused by nutrient deficiency is necessary for taking timely measures and preventing a remarkable yield reduction. This study is an effort to investigate the performance of a machine learning-based model that identifies the type and severity of nitrogen, phosphorus, potassium, and sulfur in rice plants by using the plant microRNA data as model inputs. The concentration of 14 microRNA compounds in plants exposed to nutrient deficiency was measured using an electrochemical biosensor based on the peak currents produced during the probe–target microRNA hybridization. Subsequently, several machine learning models were utilized to predict the type and severity of stress. According to the results, the biosensor used in this work exerted promising analytical performance, including linear range (10⁻¹⁹ to 10⁻¹¹ M), limit of detection (3 × 10⁻²¹ M), and reproducibility during microRNA measurement in total RNA extracted from rice plant samples. Among the microRNAs studied, miRNA167, miRNA162, miRNA169, and miRNA395 exerted the largest contribution in predicting the nutrient deficiency levels based on feature selection methods. Using these four microRNAs as model inputs, the random forest with hyperparameters optimized by the genetic algorithm was capable of detecting the type of nutrient deficiency with an average accuracy, precision, and recall of 0.86, 0.94, and 0.87, respectively, seven days after the application of the nutrient treatment. Within this period, the optimized machine was able to detect the level of deficiency with average MSE and R² of 0.010 and 0.92, respectively. Combining the findings of this study and the results we reported earlier on determining the occurrence of salinity, drought, and heat in rice plants using microRNA biosensors can be useful to develop smart biosensing platforms for efficient plant health monitoring systems. Full article