Search Results (258)

Background: Autism spectrum disorder (ASD) is a highly prevalent neurodevelopmental condition influenced by both genetic and non-genetic factors, although the underlying pathomechanisms remain unclear. We systematically analyzed microRNA (miRNA) expression and associated functional pathways in ASD to evaluate their potential as prenatal/postnatal, diagnostic, and prognostic biomarkers. Methods: Peripheral blood mononuclear cells from 12 Sicilian patients with ASD (eight with normal cognitive function) and 15 healthy controls were analyzed using small RNA sequencing. Differential expression analysis was performed with DESeq2 (|fold change| ≥ 1.5; adjusted p ≤ 0.05). Functional enrichment and network analyses were conducted using Ingenuity Pathway Analysis, focusing on Diseases and Biofunctions. Results: 998 miRNAs were differentially expressed in ASD, 424 upregulated and 553 downregulated. Enriched pathways were primarily associated with psychological and neurological disorders. Network analysis highlighted three principal interaction clusters related to inflammation, cell survival and mechanotransduction, synaptic plasticity, and neuronal excitability. Four miRNAs (miR-296-3p, miR-27a, miR-146a-5p, and miR-29b-3p) emerged as key regulatory candidates. Conclusions: The marked divergence in miRNA expression between ASD and controls suggests distinct regulatory patterns, thus reinforcing the central involvement of inflammatory, autoimmune, and infectious mechanisms in ASD, mediated by miRNAs regulating S100 family genes, neuronal migration, and synaptic communication. However, rather than defining a predictive biomarker panel, this study identified candidate miRNAs and regulatory networks that may be relevant to ASD pathophysiology. As such, further validation in appropriately powered cohorts with predictive modeling frameworks are warranted before any biomarker or diagnostic implications can be inferred. Full article

Traditional plant scouting is often a costly and labor-intensive task that requires experienced specialists to diagnose and manage plant stresses. Artificial intelligence (AI), particularly deep learning and computer vision, offers the potential to transform scouting by enabling rapid, non-intrusive detection and classification of early stress symptoms from plant images. However, deep learning models are often opaque, relying on millions of parameters to extract complex nonlinear features that are not interpretable by growers. Recently, eXplainable AI (XAI) techniques have been used to identify key spatial regions that contribute to model predictions. This project explored the potential of convolutional neural networks (CNNs) for classifying the severity of chilli thrips damage in strawberry plants in Florida and employed XAI techniques to interpret model decisions and identify symptom-relevant canopy features. Four CNN architectures, YOLOv11, EfficientNetV2, Xception, and MobileNetV3, were trained and evaluated using 2353 square RGB canopy images of different sizes (256, 480, 640 and 1024 pixels) to classify symptoms as healthy, moderate, or severe. Trade-offs between image size, model parameter count, inference speed, and accuracy were examined in determining the best-performing model. The models achieved accuracies ranging from 77% to 85% with inference times of 5.7 to 262.3 ms, demonstrating strong potential for real-time pest severity estimation. Gradient-Weighted Class Activation Mapping (Grad-CAM) visualization revealed that model attention focused on biologically relevant regions such as fruits, stems, leaf edges, leaf surfaces, and dying leaves, areas commonly affected by chilli thrips. Subsequent analysis showed that model attention spread from localized regions in healthy plants to wide diffuse regions in severe plants. This alignment between model attention and expert scouting logic suggests that CNNs internalize symptom-specific visual cues and can reliably classify pest-induced plant stress. Full article

Sugarcane diseases cause estimated global annual losses of over $5 billion. While deep learning shows promise for disease detection, current approaches lack transparency and confidence estimates, limiting their adoption by agricultural stakeholders. We developed an uncertainty-aware detection system integrating Monte Carlo (MC) dropout with MobileNetV3, trained on 2521 images across five categories: Healthy, Mosaic, Red Rot, Rust, and Yellow. The proposed framework achieved 97.23% accuracy with a lightweight architecture comprising 5.4 M parameters. It enabled a 2.3 s inference while generating well-calibrated uncertainty estimates that were 4.0 times higher for misclassifications. High-confidence predictions (>70%) achieved 98.2% accuracy. Gradient-weighted Class Activation Mapping provided interpretable disease localization, and the system was deployed on Hugging Face Spaces for global accessibility. The model demonstrated high recall for the Healthy and Red Rot classes. The model achieved comparatively higher recall for the Healthy and Red Rot classes. The inclusion of uncertainty quantification provides additional information that may support more informed decision-making in precision agriculture applications involving farmers and agronomists. Full article

Background: Pediatric Major Depressive Disorder (pMDD) is one of the leading causes of disability in adolescents. There is currently no single explanation that fully accounts for the cause of the disorder, but various factors, including dysregulation of the immune and stress responses, have been linked to its onset. Oxylipins and endocannabinoids, derived from metabolization of n-3 and n-6 polyunsaturated fatty acids (PUFAs), regulate inflammation and have been suggested to attenuate inflammation associated with depression. This study aims to understand whether adolescents with pMDD have altered baseline levels of oxylipins and endocannabinoids compared to healthy adolescents. Methods: In this case–control study, we measured 60 oxylipins and endocannabinoids in plasma from 82 adolescents with pMDD and their matching healthy controls. Results: A Principal Component Analysis revealed substantial variability within each group and only a moderate degree of separation between them. In a paired analysis, the lipid mediators of controls exhibited higher concentrations of n-6 PUFA-derived prostaglandins and thromboxanes (PGE2, PGD2, PGF2a and TXB2), n-3 PUFA-derived TxB3, and the endocannabinoids AEA, EPEA, and DHEA. In contrast, cases had higher concentrations of the n-6 PUFA-derived 6-keto-PGF1a and the n-3 PUFA-derived PGD3. In addition, we observed a higher percentage of oxylipins and endocannabinoids derived from DHA (5.65 ± 5.46% vs. 4.72 ± 4.94%) and AA (16.31 ± 11.10% vs. 12.76 ± 13.46%) in plasma from controls, in line with the higher DHA and AA levels observed in erythrocytes from controls compared to cases. Conclusions: Overall, our results show lower plasma levels of endocannabinoids and lower DHA- and AA-derived oxylipins in adolescents with pMDD, supporting their role in the pathophysiology of pMDD. To infer a causative role of the n-3 and n-6 PUFA-derived oxylipins and endocannabinoids in pMDD, an intervention study with n-3 PUFA supplementation and monitoring of oxylipins and endocannabinoids would be necessary. Full article

Background: Physical literacy is a multidimensional construct that may be relevant for promoting active lifestyles and healthy development during adolescence. However, the association between perceived physical literacy (PPL) and body composition assessed by dual-energy X-ray absorptiometry (DXA) remains underexplored. Objective: To examine the association between PPL and DXA-derived body composition parameters in Spanish adolescents. Methods: This cross-sectional study included 56 adolescents (13.2 ± 1.27 years, 28.6% girls). PPL was assessed using the validated Spanish version of the Perceived Physical Literacy Instrument (S-PPLI). Body composition was measured by DXA. Associations between PPL and body composition outcomes were examined using general linear models, adjusting for sex, age, and device-measured moderate-to-vigorous physical activity (MVPA) and sedentary time. Results: Higher PPL was significantly associated with greater lean body mass (β = 0.81; p = 0.02), lean mass index (β = 0.22; p = 0.01), and fat-free mass (β = 0.85; p = 0.01), as well as with higher body mass index (BMI) (β = 0.24; p = 0.03). Conclusions: Higher PPL is associated with more favorable lean-related body composition outcomes in Spanish adolescents, whereas no associations were found with adiposity or bone parameters. These findings highlight PPL as a relevant correlation of lean body composition during adolescence. Given the cross-sectional design, causal inferences cannot be drawn, and future longitudinal and interventional studies are warranted. Full article

Background/Objectives: Equol, a gut microbial metabolite of the soy isoflavone, daidzein, is associated with estrogenic activity and potential benefits for women’s health. While equol production depends on individual gut microbial composition, its dietary and clinical correlates in young women remain incompletely characterized. This study explored the relationship between urinary equol production, dietary habits, and premenstrual symptom severity in healthy university-aged women. Methods: We conducted a cross-sectional study of 41 Japanese women, aged 19–20 years. Urinary equol was measured using a validated liquid chromatography–tandem mass spectrometry (LC–MS/MS) method, following enzymatic hydrolysis. Participants were classified as either equol producers or non-producers, based on urinary concentration thresholds. Dietary intake was evaluated using a dietary questionnaire focused on soy products and dietary fiber sources. Premenstrual symptoms were assessed using a standardized Japanese questionnaire for premenstrual syndrome and premenstrual dysphoric disorder. Results: Twelve percent of participants were classified as equol producers. Compared with non-producers, equol producers reported higher consumption of pumpkin, soybean sprouts, and green tea. Among non-producers, higher consumption of certain vegetables and fiber-rich foods, including broccoli, pickled radish, konjac, and konjac jelly, was associated with greater premenstrual symptom severity, whereas such associations were not observed among equol producers. The analytical method demonstrated high sensitivity and reproducibility for urinary equol measurement. Conclusions: These findings suggest that equol production status may be associated with distinct dietary patterns and with differences in the relationship between food intake and premenstrual symptom severity in young women. Although the cross-sectional design and limited sample size preclude causal inference, these findings suggest that urinary equol is a promising candidate biomarker for future research on diet-related modulation of premenstrual symptoms. Full article

Background/Objectives: Long-term serological studies are essential to understand how repeated antigenic exposure affects the specific humoral immune response. The aim of this study was to investigate the long-term SARS-CoV-2 antibody dynamics in Austrian blood donors, as representatives of healthy adults, over a period of 36 months after the first SARS-CoV-2 infection. Methods: SARS-CoV-2 anti-N antibody levels were determined in more than 146,000 blood donations collected between 2020 and 2025. In addition, SARS-CoV-2 anti-N and anti-S antibody dynamics were examined in 204 individual blood donors at predefined points in time over a period of 36 months. Reinfections were inferred from increases in anti-N levels within an individual. Vaccination history and self-reported infection data were documented. Results: Anti-N seroprevalence was over 90% from the beginning of 2023 and remained at this level until 2025. Among the longitudinally observed participants, 97% had at least one serologically detected reinfection and 50% had two or more. While anti-N levels continued to increase over time, suggesting cumulative antigenic stimulation, anti-S concentrations and in vitro antibody functionality remained consistently high. Self-reported reinfections underestimated the actual incidence by a factor of six. Symptom profiles shifted toward mild respiratory manifestations, with significantly fewer cases of hyposmia or dysgeusia reported compared to the initial infection. Conclusions: After three years of observation, SARS-CoV-2 immunity is characterized by sustained antibody activity. The results show a transition from persistent, but inherently declining, to a repeatedly rebuilding, enhanced humoral immunity, indicating that SARS-CoV-2 has become endemic in Austria. Full article

Background: Parkinson’s disease (PD) involves progressive neurodegeneration with clinical or subclinical disturbance of the gut–brain axis, including altered gastrointestinal motility and enteric nervous system involvement. Clinical studies have reported gut microbiome alterations in PD, with shifts in taxa associated with inflammatory signalling and short-chain fatty acid (SCFA) metabolism. Photobiomodulation (PBM), a non-invasive light therapy, has been investigated as a potential adjunctive treatment for PD, with proposed effects on neural, metabolic, and immune pathways. We previously reported the five-year clinical outcomes in a PBM-treated Parkinson’s disease case series. Here we report the five-year gut microbiome outcomes based on longitudinal samples collected from the same participants. This was an exploratory, open-label longitudinal study without a control group. Objective: Our objective was to assess whether long-term PBM was associated with changes in gut microbiome diversity and composition in the same Parkinson’s disease cohort as previously assessed for changes in Parkinson’s symptoms. Methods: Six participants from the earlier PBM proof-of-concept study who had been diagnosed with idiopathic PD and who had continued treatment (transcranial light emitting diode [LED] plus abdominal and neck laser) for five years had their faecal samples analysed by 16S rDNA sequencing to assess microbiome diversity and taxonomic composition. Results: Microbiome analysis revealed significantly reduced evenness (α-diversity) and significant shifts in β-diversity over five years, as assessed by Permutational Multivariate Analysis of Variance (PERMANOVA). At the phylum level, Pseudomonadota and Methanobacteriota decreased in four of the six participants. Both of these phyla are often increased in the Parkinson’s microbiome compared with the microbiomes of healthy controls. Family-level changes included increased acetate-producing Bifidobacteriaceae (five of the six participants); decreased pro-inflammatory, lipopolysaccharide (LPS)-producing Enterobacteriaceae (two of the three participants who have this bacterial family present); and decreased LPS- and H₂S-producing Desulfovibrionaceae (five of six). At the genus level, Faecalibacterium, a key butyrate producer, increased in four of the six participants, potentially leading to more SCFA availability, although other SCFA-producing bacteria were decreased. This was accompanied by reductions in pro-inflammatory LPS and H₂S-producing genera that are often increased in the Parkinson’s microbiome. Conclusions: This five-year case series represents the longest follow-up of microbiome changes in Parkinson’s disease, although the interpretation of results is limited by very small numbers, the lack of a control group, and the inability to control for lifestyle influences such as dietary changes. While causal relationships cannot be inferred, the parallel changes in improvements in mobility and non-motor Parkinson’s symptoms observed in this cohort, raises the hypothesis that PBM may interact with the gut–brain axis via the microbiome. Controlled studies incorporating functional multi-omics are needed to clarify potential mechanistic links between microbial function, host metabolism, and clinical outcomes. Full article

Background/Objectives: Polycystic ovary syndrome (PCOS) is a common endocrine–metabolic disorder in which skeletal muscle insulin resistance contributes substantially to cardiometabolic risk. Pioglitazone improves insulin sensitivity in women with PCOS, yet the underlying transcriptional changes and their potential as treatment-response biomarkers remain incompletely defined. We aimed to reanalyse skeletal muscle gene expression from pioglitazone-treated PCOS patients using modern machine learning and network approaches to identify candidate biomarkers and regulatory hubs that may support precision therapy. Methods: Public microarray data (GSE8157) from skeletal muscle of obese women with PCOS and healthy controls were reprocessed. Differentially expressed genes (DEGs) were identified and submitted to Ingenuity Pathway Analysis to infer canonical pathways, upstream regulators, and disease functions. Four supervised machine learning algorithms (logistic regression, random forest, support vector machines, and gradient boosting) were trained using multi-step feature selection and 3-fold stratified cross-validation to provide superior Exploratory Gene Analysis. Gene co-expression networks were constructed from the most informative genes to characterize network topology and hub genes. A simulated multi-omics framework combined selected transcripts with representative clinical variables to explore the potential of integrated signatures. Results: We identified 1459 DEGs in PCOS skeletal muscle following pioglitazone, highlighting immune and fibrotic signalling, interferon and epigenetic regulators (including IFNB1 and DNMT3A), and pathways linked to mitochondrial function and extracellular matrix remodelling. Within this dataset, all four machine learning models showed excellent cross-validated discrimination between PCOS and controls, based on a compact gene panel. Random forest feature importance scoring and network centrality consistently prioritized ITK, WT1, BRD1-linked loci and several long non-coding RNAs as key nodes in the co-expression network. Simulated integration of these transcripts with clinical features further stabilized discovery performance, supporting the feasibility of multi-omics biomarker signatures. Conclusions: Reanalysis of skeletal muscle transcriptomes from pioglitazone-treated women with PCOS using integrative machine learning and network methods revealed a focused set of candidate genes and regulatory hubs that robustly separate PCOS from controls in this dataset. These findings generate testable hypotheses about the immunometabolism and epigenetic mechanisms of pioglitazone action and nominate ITK, WT1, BRD1-associated loci and related network genes as promising biomarkers for future validation in larger, independent PCOS cohorts. Full article

Major depressive disorder (MDD) is a prevalent mental health condition that requires accurate and objective diagnostic tools. Electroencephalogram (EEG) signals provide valuable insights into brain activity and have been widely studied for mental disorder classification. In this study, we propose a novel DML + ANFIS framework that integrates deep metric learning (DML) with an adaptive neuro-fuzzy inference system (ANFIS) for the automated diagnosis of major depressive disorder (MDD) using EEG time series signals. Time–frequency features are first extracted from raw EEG signals using the short-time Fourier transform (STFT) and the continuous wavelet transform (CWT). These features are then embedded into a low-dimensional space using a DML approach, which enhances the inter-class separability between MDD and healthy control (HC) groups in the feature space. The resulting time–frequency feature embeddings are finally classified using an ANFIS, which integrates fuzzy logic-based nonlinear inference with deep metric learning. The proposed DML + ANFIS framework was evaluated on a publicly available EEG dataset comprising MDD patients and healthy control (HC) subjects. Under subject-dependent evaluation, the STFT-based DML + ANFIS and CWT-based models achieved an accuracy of 92.07% and 98.41% and an AUC of 97.28% and 99.50%, respectively. Additional experiments using subject-independent cross-validation demonstrated reduced but consistent performance trends, thus indicating the framework’s ability to generalize to unseen subjects. Comparative experiments showed that the proposed approach generally outperformed conventional deep learning models, including Bi-LSTM, 2D CNN, and DML + NN, under identical experimental conditions. Notably, the DML module compressed 1280-dimensional EEG features into a 10-dimensional embedding, thus achieving substantial dimensionality reduction while preserving discriminative information. These results suggest that the proposed DML + ANFIS framework provides an effective balance between classification performance, generalization capability, and computational efficiency for EEG-based MDD diagnosis. Full article

Background/Objectives: Parkinson’s disease (PD) is an adult-onset neurodegenerative disorder whose pathogenesis is still not completely understood. Several lines of evidence suggest that alterations in epigenetic architecture may contribute to the development of this condition. Here, we present a pilot DNA methylation study from peripheral blood in a cohort of Sicilian PD patients and matched controls. Peripheral tissue analysis has previously been shown to reflect molecular and functional profiles relevant to neurological diseases, supporting their validity as a proxy for studying brain-related epigenetic mechanisms. Methods: We analyzed 20 PD patients and 20 healthy controls (19 males and 21 females overall), matched for sex, with an age range of 60–87 years (mean 72.3 years). Peripheral blood DNA was extracted and processed using the Illumina Infinium MethylationEPIC v2.0 BeadChip, which interrogates over 935,000 CpG sites across the genome, including promoters, enhancers, CpG islands, and other regulatory elements. The assay relies on sodium bisulfite conversion of DNA to detect methylation status at single-base resolution. Results: Epigenome-wide association study (EWAS) data allowed for multiple levels of analysis, including immune cell-type deconvolution, estimation of biological age (epigenetic clocks), quantification of stochastic epigenetic mutations (SEMs) as a measure of epigenomic stability, and differential methylation profiling. Immune cell-type inference revealed an increased but not significant proportion of monocytes in PD patients, consistent with previous reports. In contrast, epigenetic clock analysis did not reveal significant differences in biological age acceleration between cases and controls, partially at odds with earlier studies—likely due to the limited sample size. SEMs burden did not differ significantly between groups. Epivariations reveal genes involved in pathways known to be altered in dopaminergic neuron dysfunction and α-synuclein toxicity. Differential methylation analysis, however, yielded 167 CpG sites, of which 55 were located within genes, corresponding to 54 unique loci. Gene Ontology enrichment analysis highlighted significant overrepresentation of pathways with neurological relevance, including regulation of synapse structure and activity, axonogenesis, neuron migration, and synapse organization. Notably, alterations in KIAA0319, a gene involved in neuronal migration, synaptic formation, and cortical development, have previously been associated with Parkinson’s disease at the gene expression level, while methylation changes in FAM50B have been reported in neurotoxic and cognitive contexts; our data suggest, for the first time, a potential epigenetic involvement of both genes in Parkinson’s disease. Conclusions: This pilot study on a Sicilian population provides further evidence that DNA methylation profiling can yield valuable molecular insights into PD. Despite the small sample size, our results confirm previously reported findings and highlight biological pathways relevant to neuronal structure and function that may contribute to disease pathogenesis. These data support the potential of epigenetic profiling of peripheral blood as a tool to advance the understanding of PD and generate hypotheses for future large-scale studies. Full article

The coffee leaf miner (Leucoptera coffeella) is a major pest of coffee crops and can cause significant economic losses. Early monitoring is essential to support decision-making for its control. This study aimed to evaluate the potential of fuzzy logic for detecting leaf miner infestation using a 2.5-year historical series of Sentinel-2A satellite images processed on the Google Earth Engine platform. Field monitoring of coffee leaf miner infestation was carried out at the EPAMIG Experimental Field, located in São Sebastião do Paraíso, Minas Gerais, Brazil. The period evaluated was from September 2022 to April 2025. Vegetation indices were calculated using the Google Earth Engine platform, and a database was built with eight indices (NDVI, EVI, GNDVI, SR, IPVI, NDMI, MCARI, and CLMI) along with coffee leaf miner infestation data. Principal Component Analysis (PCA) was applied to reduce data dimensionality and identify the most relevant indices for distinguishing infested from healthy plants, explaining 90.9% of the total variance in the first two components (PC1 and PC2). The indices CLMI, IPVI, GNDVI, and MCARI showed the greatest contribution to class separation. A fuzzy inference model was implemented based on the mean index values and validated through performance metrics. The results indicated an overall accuracy of 79.1%, a sensitivity (recall) of 86.6%, a specificity of 66.6%, an F1-score of 0.838, a Kappa coefficient of 0.545, and an area under the curve (AUC) of 0.766. These findings confirm the potential of integrating orbital spectral data via Google Earth Engine with fuzzy logic analysis as an efficient tool, contributing to the adoption of more sustainable monitoring practices in coffee farming. The fuzzy logic system received as input the spectral values derived from Sentinel-2A imagery, specifically the indices identified as most relevant by the PCA (CLMI, IPVI, GNDVI, and MCARI). These indices were computed and integrated into the inference model through processing routines developed in the Google Earth Engine platform, enabling a direct connection between satellite-derived spectral patterns and the detection of coffee leaf miner infestation. Full article

Background: Periodontitis is a common inflammatory disease characterized by progressive loss of alveolar bone. Cone-beam computed tomography (CBCT) can visualize 3D periodontal bone defects, but its interpretation is time-consuming and examiner-dependent. Deep learning may support standardized CBCT assessment if performance and biological relevance are adequately characterized. Methods: We used the publicly available MMDental dataset (403 CBCT volumes from 403 patients) to train a 3D ResNet-18 classifier for binary discrimination between periodontitis and healthy status based on volumetric CBCT scans. Volumes were split by subject into training (n = 282), validation (n = 60), and test (n = 61) sets. Model performance was evaluated using area under the receiver operating characteristic curve (AUROC), area under the precision–recall curve (AUPRC), and calibration metrics with 95% bootstrap confidence intervals. Grad-CAM saliency maps were used to visualize the anatomical regions driving predictions. To explore phenotype-level biological concordance, we analyzed an independent gingival transcriptomic cohort (GSE10334, n ≈ 220 arrays after quality control) and an independent oral microbiome cohort based on 16S rRNA amplicon sequencing, using unsupervised clustering, differential expression/abundance testing, and pathway-level summaries. Results: On the held-out CBCT test set, the model achieved an AUROC of 0.729 (95% CI: 0.599–0.850) and an AUPRC of 0.551 (95% CI: 0.404–0.727). At a high-sensitivity operating point (sensitivity 0.95), specificity was 0.48, yielding an overall accuracy of 0.62. Grad-CAM maps consistently highlighted the alveolar crest and furcation regions in periodontitis cases, in line with expected patterns of bone loss. In the transcriptomic cohort, inferred periodontitis samples showed up-regulation of inflammatory and osteoclast-differentiation pathways and down-regulation of extracellular-matrix and mitochondrial programs. In the microbiome cohort, disease-associated samples displayed a dysbiotic shift with enrichment of classic periodontal pathogens and depletion of health-associated commensals. These omics patterns are consistent with an inflammatory–osteolytic phenotype that conceptually aligns with the CBCT-defined disease class. Conclusions: This study presents a proof-of-concept 3D deep learning model for CBCT-based periodontal disease classification that achieves moderate discriminative performance and anatomically plausible saliency patterns. Independent transcriptomic and microbiome analyses support phenotype-level biological concordance with the imaging-defined disease class, but do not constitute subject-level multimodal validation. Given the modest specificity, single-center imaging source, and inferred labels in the omics cohorts, our findings should be interpreted as exploratory and hypothesis-generating. Larger, multi-center CBCT datasets and prospectively collected paired imaging–omics cohorts are needed before clinical implementation can be considered. Full article

Background: Virtual cells are embedded in widely used single-cell generative models. Nonetheless, the models’ implicit knowledge of perturbations remains unclear. Methods: We train variational autoencoders on three gene expression datasets spanning genetic, chemical, and temporal perturbations, and infer perturbations by differentiating decoder outputs with respect to latent variables. This yields vector fields of infinitesimal change in gene expression. Furthermore, we probe a publicly released scVI decoder trained on the $\mathrm{CELL}\times \mathrm{GENE}$ Discover Census ($\sim 5.7$ M mouse cells) and score genes by the alignment between local gradients and an empirical healthy-to-disease axis, followed by a novel large language model-based evaluation of pathways. Results: Gradient flows recover known transitions in Irf8 knockout microglia, cardiotoxin-treated muscle, and worm embryogenesis. In the pretrained Census model, gradients help identify pathways with stronger statistical support and higher type 2 diabetes relevance than an average expression baseline. Conclusions: Trained single-cell decoders already contain rich perturbation-relevant information that can be accessed by automatic differentiation, enabling in-silico perturbation simulations and principled ranking of genes along observed disease or treatment axes without bespoke architectures or perturbation labels. Full article

Powered ankle exoskeletons have become efficient ability-enhancing and rehabilitation tools that support human body movements. Traditionally, the control schemes for ankle exoskeletons were implemented relying on precise physical and kinematic models. However, this approach resulted in poor coordination of human–machine coupled motion and an increase in the wearer’s energy consumption. To solve the cooperative control issue between the wearer and the ankle exoskeleton, this work introduces an adaptive impedance control method for the ankle exoskeleton that is based on the surface electromyography (sEMG) of the calf muscles. The proposed method achieves cooperative control by leveraging an experience-based fuzzy rule interpolation (E-FRI) approach to dynamically adjust the impedance model parameters. This adaptive mechanism is driven by the wearer’s calf sEMG signals, which capture the wearer’s movement state. The adaptive impedance model then computes the desired torque for the ankle exoskeleton. To validate and evaluate the system, the control method was implemented on a simplified ankle exoskeleton. Experimental validation with five healthy participants (age 19 ± 1.35 years) demonstrated significant improvements over conventional fixed-impedance approaches: mean RMS reductions of 19.7% in gastrocnemius activation and 21.4% in soleus activation during treadmill walking. This study establish a new paradigm for responsive exoskeleton control through symbiotic integration of neuromuscular signals and adaptive fuzzy inference, offering critical implications for rehabilitation robotics and assistive mobility technologies. Full article