Orphanet J Rare Dis. 2025 Aug 4;20(1):399. doi: 10.1186/s13023-025-03632-4.

ABSTRACT

BACKGROUND: The SLSMDS Research Network is a collaborative network comprising patient advocates, researchers, clinicians, and affected families seeking to improve outcomes for individuals with single large-scale mitochondrial DNA deletion syndromes (SLSMDS). Building off of jointly developed research infrastructures, including a patient registry and natural history study, advocates and clinicians cohosted the SLSMDS Family and Scientific Conference, enabling the collection of patient data from an ultra-rare and geographically dispersed patient population. Here we describe the data collection procedures for single-time point laboratory assessments and patient reported outcomes for a subset of individuals with SLSMDS.

RESULTS: Utilizing a reproducible model of rare disease data collection, we expand our understanding of the common psychiatric manifestations, describe variability in terms of self-care and quality of life, and emphasize potential biomarkers for individuals with SLSMDS.

CONCLUSION: Our study describes how efficient patient-researcher partnerships can develop and sustain novel mechanisms to collect rare disease data, improve our understanding of the natural history of these disorders, and support development of future treatments.

PMID:40760494 | DOI:10.1186/s13023-025-03632-4

Pharmacogenet Genomics. 2025 Aug 5. doi: 10.1097/FPC.0000000000000573. Online ahead of print.

ABSTRACT

It is unknown how many people in the US have had pharmacogenetic (PGx) testing and whether people want to be tested. We conducted a nationally representative survey of the general US adult population to determine the prevalence of adults that have had PGx testing using a validated confidential online survey, the Non-Medical Use of Prescription Drugs Program. A weighted logistic regression was used to test health characteristics associated with PGx testing and determine those who desire to be tested. The analysis included 29 146 individuals who completed the survey, which represents approximately 260 000 000 adults in the US. The prevalence of US adults who have been PGx tested is 6.6% [95% confidence interval (CI): 6.2-7.0]. Only 32.2% (95% CI: 31.5-32.9), an estimated 79 million individuals, desired PGx testing. Adults who had or want PGx testing were more likely to be female, have higher education, be students, current or former members of the military, use medications, and have a mental health disorder. The prevalence of adults who have been PGx tested remains low in the US. There are knowledge gaps about the benefits of PGx testing that must be bridged to increase implementation.

PMID:40762070 | DOI:10.1097/FPC.0000000000000573

Front Immunol. 2025 Jul 21;16:1609740. doi: 10.3389/fimmu.2025.1609740. eCollection 2025.

ABSTRACT

INTRODUCTION: Ulcerative colitis (UC) is characterized by aberrant immune responses involving multiple inflammatory pathways, including JAK/STAT signaling. However, the specific roles and interactions of individual components within this pathway remain unclear.

METHODS: We conducted a prospective, observational, single-center study enrolling 61 adult UC patients undergoing routine colonoscopy with endoscopic activity (Mayo Endoscopic Score > 0). Paired biopsies from inflamed and non-inflamed colonic mucosa were collected. Phosphorylation levels of JAK1, JAK2, JAK3, TYK2, STAT1, STAT3, and STAT4 were quantified by Western blot.

RESULTS: Inflamed tissue showed significantly increased phosphorylation of JAK2, JAK3, TYK2, STAT1, STAT3, and STAT4 compared to non-inflamed mucosa (p < 0.05), while JAK1 levels did not differ significantly. Correlation analysis revealed coordinated activation among JAK2, JAK3, TYK2, and STAT3, suggesting interdependent roles. Notably, male patients exhibited significantly higher activation of JAK2 and STAT3 than female patients (p < 0.05).

DISCUSSION: These findings highlight a heterogeneous but important involvement of the JAK/STAT pathway in UC pathophysiology. The observed sex-specific differences and coordinated activation patterns suggest the value of personalized therapeutic approaches targeting specific components of this pathway.

PMID:40761789 | PMC:PMC12318950 | DOI:10.3389/fimmu.2025.1609740

Toxicol Rep. 2025 Jul 20;15:102093. doi: 10.1016/j.toxrep.2025.102093. eCollection 2025 Dec.

ABSTRACT

The goal of this study was to explore associations between single-nucleotide polymorphisms (SNPs) and umbilical cord blood concentrations of buprenorphine and its metabolites following maternal administration. This is a sub-study of a prospective observational cohort investigation which included pregnant women receiving buprenorphine for opioid use disorder during pregnancy. Following delivery, umbilical cord blood samples were collected and genotyped using a pharmacogenetic panel. The drug and metabolite concentrations were analyzed through liquid chromatography-mass spectrometry, and genetic association analysis was completed using PLINK software. The included neonates (n = 14) had a mean birth weight of 3.00 ± 0.39 kg and were born to mothers receiving a mean buprenorphine dose of 10.29 ± 6.22 mg. Ten concentration groupings (drug, single metabolite, as well as drug/metabolite(s) combinations) produced 18 unique SNP associations. Two significant associations included variations in CYP3A4 and UGT1A1, which play a role in the metabolism of buprenorphine. These preliminary findings suggest potential pharmacogenetic factors influencing fetal drug exposure, warranting larger studies to validate associations and explore clinical implications for neonatal outcomes.

PMID:40761746 | PMC:PMC12319250 | DOI:10.1016/j.toxrep.2025.102093

Curr Res Pharmacol Drug Discov. 2025 Jul 24;9:100230. doi: 10.1016/j.crphar.2025.100230. eCollection 2025.

ABSTRACT

BACKGROUND: Pharmacogenetic variability has been reported to influence the efficacy and safety of immunosuppressive therapies in early stages of kidney transplantation. This study investigates long-term associations between pharmacogene variants and clinical outcomes in a cohort of kidney transplant recipients over a 12-year follow-up.

MATERIALS AND METHODS: We analyzed 37 SNPs from 14 genes related to drug metabolism and transport in 79 kidney transplant patients. Clinical parameters, including survival, renal function, tumor occurrence, and pharmacokinetics of tacrolimus, were evaluated. Logistic regression and Kaplan-Meier analyses assessed associations between gene variants and clinical outcomes.

RESULTS: Variants in metabolizer (CYP3A5, CYP2B6) and transporter genes (ABCB1, ABCC2) were associated with 12-year survival. Increased tumor risk correlated with ABCC2 variants in donors and decreased risk with CYP2B6 rs3745274 in recipients. Renal function was influenced by variants in ABCB1, ABCC2, CYP3A5, CYP3A4, and CYP2B6. Tacrolimus dose-dependent concentration was affected by variants in CYP3A4, CYP3A5, CYP2C19, ABCB1, and SLCO1B1. Increased nephrotoxicity risk was associated with CYP2C19 rs4244285 and reduced by SLCO1B1 rs2306283 AA and AG variants. Gene variant interactions between metabolizer and transporter genes were also associated with altered risk of events incidence.

DISCUSSION: Our findings support that pharmacogene variants influence transplant outcomes. Notable associations include survival related to ABCB1 and ABCC2 variants, tumor occurrence linked to CYP2B6 rs3745274, and renal function affected by multiple pharmacogenes. Variants in CYP2C19 and SLCO1B1 significantly impacted tacrolimus pharmacokinetics and nephrotoxicity risk. These results underline the importance of pharmacogenetic testing for personalized management in kidney transplantation, although further validation in larger cohorts is necessary.

PMID:40761554 | PMC:PMC12319246 | DOI:10.1016/j.crphar.2025.100230

Front Pharmacol. 2025 Jul 21;16:1627239. doi: 10.3389/fphar.2025.1627239. eCollection 2025.

ABSTRACT

The integration of pharmacogenetics into personalized medicine enables the optimization of drug selection and dosage, maximizing therapeutic benefits while minimizing the risk of adverse drug reactions. The association between APOE alleles and ARIA, a known adverse reaction in Alzheimer's disease patients treated with anti-amyloid monoclonal antibodies, has led to the inclusion of APOE genotyping among conventional pharmacogenetic tests. Given the dual role of APOE alleles, the widespread implementation of this genetic test requires caution and should be accompanied by appropriate genetic counselling. APOE genotyping is uniquely positioned at the intersection of pharmacogenetics and germline testing: it provides insight not only into drug safety (specifically the risk of Amyloid-Related Imaging Abnormalities) but also into familial risk for developing Alzheimer's disease. Carriers of risk alleles, especially homozygotes, face the highest risk and require close monitoring. While APOE genotyping can inform treatment decisions, it also raises ethical concerns due to the broader implications of disclosing genetic risk information for neurodegenerative diseases. Identifying a high-risk APOE genotype in a patient substantially impacts family members. Therefore, patients considered for treatment with anti-amyloid monoclonal antibodies should receive comprehensive pre- and post-test genetic counseling that goes beyond traditional standards, as currently provided for other peculiar tests. Such counseling ensures that patients are adequately informed about potential outcomes, psychological impacts, and familial implications. It also supports ethical decision-making and facilitates truly informed consent, helping to prevent deterministic or overly simplistic interpretations of genetic risk.

PMID:40761402 | PMC:PMC12318987 | DOI:10.3389/fphar.2025.1627239

Front Pharmacol. 2025 Jul 21;16:1614753. doi: 10.3389/fphar.2025.1614753. eCollection 2025.

ABSTRACT

BACKGROUND AND AIMS: Classification system of tacrolimus elimination and its clinical significance has not been well described in liver transplantation. This study aimed to present a novel tacrolimus clearance clinical-FIS (Fast-Intermediate-Slow) classification and its gene prediction system.

METHODS: Patients from 3 transplant centers were enrolled in this study. All recipients and their corresponding donor livers from center 1 were genotyped using an Affymetrix DMET Plus microarray, and association analysis was performed using trough blood concentration/weight-adjusted-dose ratios (CDR, (ng/mL)/(mg/kg)). The candidate-associated loci were then sequenced in center 2 and center 3 patients for verification.

RESULTS: A clinical classification based on tacrolimus CDR can effectively divide liver transplantation patients into fast elimination (FE), intermediate elimination (IE), and slow elimination (SE) groups, which we called the clinical-FIS classification. Trough blood concentrations in the clinical-SE group during the early postoperative period were higher than those in the clinical-FE and clinical-IE groups, which could lead to delayed recovery of liver (P = 0.0373) and kidney function (P = 0.0135) and a higher infection rate (P = 0.0086). The prediction accuracy of the current CPIC (Clinical Pharmacogenetics Implementation Consortium)-EIP metabolizer classification based on recipient CYP3A5 rs776746 genotype for clinical-FIS classification was only 35.56%. A newly established genetic-EIP classification including major effect genetic factors (donor and recipient CYP3A5 rs776746) and minor effect genetic factors (recipient SULT1E1 rs3775770 and donor SLC7A8 rs7141505) showed 73.2% overall consistency with the former clinical FIS classification.

CONCLUSION: Our study presented a novel tacrolimus clearance classification, clinical-FIS, and then proposed a novel prospective genetic-EIP classification as a genotyping basis for precisely predicting the clinical-FIS.

PMID:40761401 | PMC:PMC12319242 | DOI:10.3389/fphar.2025.1614753

Respir Med Case Rep. 2025 Jul 22;57:102267. doi: 10.1016/j.rmcr.2025.102267. eCollection 2025.

ABSTRACT

Prompt eradication of Pseudomonas aeruginosa following isolation in sputum samples is a fundamental part of therapy in people with cystic fibrosis in order to prevent chronic infection. Whilst multiple eradication regimens exist, none have been proven to be more efficacious than any other. Eradication treatment is effective but not always successful. Ciprofloxacin has been the preferred choice of oral antimicrobial in these eradication regimens due to its superior in-vitro activity against Pseudomonas aeruginosa compared to other fluoroquinolones. Delafloxacin, a fourth-generation fluoroquinolone, has been shown to have superior activity against Pseudomonas aeruginosa compared to ciprofloxacin in-vitro. We show herein, what we believe is the first documented successful eradication of Pseudomonas aeruginosa in a person with CF following a new isolation of the pathogen using oral delafloxacin in combination with nebulised tobramycin, instead of ciprofloxacin after the failure of first line treatment and the emergence of ciprofloxacin-resistance on antimicrobial sensitivity testing.

PMID:40761664 | PMC:PMC12320081 | DOI:10.1016/j.rmcr.2025.102267

ERJ Open Res. 2025 Aug 4;11(4):01248-2024. doi: 10.1183/23120541.01248-2024. eCollection 2025 Jul.

ABSTRACT

BACKGROUND: Elexacaftor/tezacaftor/ivacaftor (ETI) has improved outcomes for people with cystic fibrosis (pwCF). This study evaluated changes in airway microbiological infection status after initiating ETI.

METHODS: Using the European Cystic Fibrosis Society registry, pwCF who started ETI between 2019 and 2021 were identified. The changes in microbiological status from 1 year before to 1 year after ETI initiation, were compared with the changes seen from 3 to 1 years before starting ETI. Mixed-effect regression models were used to analyse changes. Data from 2 years after initiation were examined for those starting ETI in 2019-2020.

RESULTS: Included were 15 739 pwCF from 30 countries. In the year before ETI, 38.4% were positive for Pseudomonas aeruginosa (PsA) and 36.4% for methicillin-sensitive Staphylococcus aureus (MSSA). After ETI, 38.7% of PsA-positive and 47.2% of MSSA-positive patients transitioned to negative status, compared with 14.8% and 29.1%, respectively, in the previous years. The adjusted difference in transitioning to negative was 14.6% (PsA) and 17.1% (MSSA), both p<0.001. Similar improvements were seen for Burkholderia cepacia complex and Stenotrophomonas maltophilia. For those starting ETI in 2019-2020, PsA positivity remained low over 2 years, decreasing from 46.8% pre-ETI to 30.4% and 27.7% at 1 and 2 years after ETI treatment.

CONCLUSION: One year after starting ETI, many pwCF who were initially positive for various CF-related pathogens, shifted to a negative status, a change less common before ETI. These findings suggest that ETI reduces airway infections, with benefits extending into the second year of treatment, although some pwCF continue to carry these pathogens despite treatment.

PMID:40761658 | PMC:PMC12320108 | DOI:10.1183/23120541.01248-2024

ERJ Open Res. 2025 Aug 4;11(4):00211-2025. doi: 10.1183/23120541.00211-2025. eCollection 2025 Jul.

ABSTRACT

ETI reduces pathogen detection rates in respiratory samples, yet a significant proportion of pwCF continue to harbour hallmark pathogens putting them at risk of more rapid decline in lung function https://bit.ly/3DAcKKH.

PMID:40761647 | PMC:PMC12320102 | DOI:10.1183/23120541.00211-2025

APMIS. 2025 Aug;133(8):e70058. doi: 10.1111/apm.70058.

ABSTRACT

Cystic fibrosis (CF) is commonly associated with musculoskeletal issues including inflammatory arthritis, CF arthritis. We present a retrospective cohort study which aims to describe the clinical characteristics, prevalence, and demographic associations of CF arthritis using both a clinical and literature cohort. We identified adult CF patients (≥ 18 years) with arthritis from the rheumatology clinic at Rigshospitalet (2020-2022). The clinical cohort (CC) was reviewed through electronic medical records. Literature cases were identified by searching online databases for relevant studies, case reports, and reviews on CF arthritis. Eleven CF patients with arthritis were identified (CC) from our clinic and 54 cases from the literature (literature cohort, LC). Both cohorts showed equal gender distribution. In the LC, arthritis onset had a median age of 11 years (range 2-28), while in the CC it was 26 years (range 13-43). Clinical features were similar in both cohorts: the majority had episodic relapsing arthritis, with two-thirds having mono-/oligoarthritis and one-third polyarthritis. Large joints were most commonly affected. No clear link to pulmonary disease or serologic markers was found. Immunosuppressive treatment was safe. CF arthritis is a heterogeneous condition, presenting as non-erosive, episodic oligo- or polyarthritis affecting both large and small joints.

PMID:40761185 | DOI:10.1111/apm.70058

RSC Adv. 2025 Aug 4;15(34):27795-27815. doi: 10.1039/d5ra03747f. eCollection 2025 Aug 1.

ABSTRACT

The integration of artificial intelligence (AI) in targeted anticancer drug delivery represents a significant advancement in oncology, offering innovative solutions to enhance the precision and effectiveness of cancer treatments. This review explores the various AI methodologies that are transforming the landscape of targeted drug delivery systems. By leveraging machine learning algorithms, researchers can analyze extensive datasets, including genomic, proteomic, and clinical data, to identify patient-specific factors that influence therapeutic responses. Supervised learning techniques, such as support vector machines and random forests, enable the classification of cancer types and the prediction of treatment outcomes based on historical data. Deep learning approaches, particularly convolutional neural networks, facilitate improved tumor detection and characterization through advanced imaging analysis. Moreover, reinforcement learning optimizes treatment protocols by dynamically adjusting drug dosages and administration schedules based on real-time patient responses. The convergence of AI and targeted anticancer drug delivery holds the promise of advancing cancer therapy by providing tailored treatment strategies that enhance efficacy while minimizing side effects. By improving the understanding of tumor biology and patient variability, AI-driven methods can facilitate the transition from traditional treatment paradigms to more personalized and effective cancer care. This review discusses the challenges and limitations of implementing AI in targeted anticancer drug delivery, including data quality, interpretability of AI models, and the need for robust validation in clinical settings.

PMID:40761897 | PMC:PMC12320933 | DOI:10.1039/d5ra03747f

Ther Adv Musculoskelet Dis. 2025 Aug 1;17:1759720X251357188. doi: 10.1177/1759720X251357188. eCollection 2025.

ABSTRACT

While severe vasculopathic manifestations of systemic sclerosis (SSc) are well-recognized, characterization of subclinical progressive vasculopathy contributing to cardiac involvement remains an unmet clinical need. This review highlights the evolving understanding of SSc heart involvement (SHI), including current standard clinical cardiac evaluation methods, prevalence of various cardiac manifestations of SHI, and advances at the forefront of precision medicine. Informed by this growing body of literature, we describe the development of a novel interdisciplinary cardio-rheumatology clinic at the Vanderbilt University Medical Center. Utilizing advances in imaging techniques and systemic retrieval and analysis of complex data sets, our dedicated cardio-rheumatology clinic offers opportunities for therapeutic advances and personalized medicine through mechanistic disease phenotyping in SSc. Nailfold capillaroscopy, thermography, and hand ultrasound with Doppler are acquired to characterize small vessel vasculopathy, while echocardiogram, ambulatory cardiac rhythm monitoring, cardiac magnetic resonance imaging, and cardiac positron emission tomography/computed tomography are utilized to characterize cardiac disease. By correlating vasculopathy imaging with cardiac manifestations, our cardio-rheumatology clinic aims to identify patients with SSc who would benefit from additional cardiac investigation even in the absence of cardiac symptomatology. This interdisciplinary collaboration may allow earlier detection of primary SHI, which is a common cause of death in SSc patients, resulting from both morpho-functional and electrical cardiac abnormalities. Our shared model of care and robust data acquisition facilitate clinical investigation by utilizing technological advances in data management. Using deep learning and pattern recognition, artificial intelligence (AI) offers opportunities to integrate data from imaging and monitoring techniques outlined in this report to provide quantifiable markers of disease progression and treatment efficacy. Given the potential for extensive AI data processing but the low prevalence of SSc, developing a multicenter cloud-based image sharing platform would accelerate clinical investigation in the field. Ultimately, we aim to tailor therapeutic decisions and risk mitigation strategies to improve SSc patient outcomes.

PMID:40761822 | PMC:PMC12319188 | DOI:10.1177/1759720X251357188

Front Bioinform. 2025 Jul 21;5:1603133. doi: 10.3389/fbinf.2025.1603133. eCollection 2025.

ABSTRACT

INTRODUCTION: Diabetes Mellitus (DM) constitutes a global epidemic and is one of the top ten leading causes of mortality (WHO, 2019), projected to rank seventh by 2030. The US National Diabetes Statistics Report (2021) states that 38.4 million Americans have diabetes. Dipeptidyl Peptidase-4 (DPP-4) is an FDA-approved target for the treatment of type 2 diabetes mellitus (T2DM). However, current DPP-4 inhibitors may cause adverse effects, including gastrointestinal issues, severe joint pain (FDA safety warning), nasopharyngitis, hypersensitivity, and nausea. Moreover, the development of novel drugs and the in vivo assessment of DPP-4 inhibition are both costly and often impractical. These challenges highlight the urgent need for efficient in-silico approaches to facilitate the discovery and optimization of safer and more effective DPP-4 inhibitors.

METHODOLOGY: Quantitative Structure-Activity Relationship (QSAR) modeling is a widely used computational approach for evaluating the properties of chemical substances. In this study, we employed a Neuro-symbolic (NeSy) approach, specifically the Logic Tensor Network (LTN), to develop a DPP-4 QSAR model capable of identifying potential small-molecule inhibitors and predicting bioactivity classification. For comparison, we also implemented baseline models using Deep Neural Networks (DNNs) and Transformers. A total of 6,563 bioactivity records (SMILES-based compounds with IC50 values) were collected from ChEMBL, PubChem, BindingDB, and GTP. Feature sets used for model training included descriptors (CDK Extended-PaDEL), fingerprints (Morgan), chemical language model embeddings (ChemBERTa-2), LLaMa 3.2 embedding features, and physicochemical properties.

RESULTS: Among all tested configurations, the Neuro-symbolic QSAR model (NeSyDPP-4) performed best using a combination of CDK extended and Morgan fingerprints. The model achieved an accuracy of 0.9725, an F1-score of 0.9723, an ROC AUC of 0.9719, and a Matthews correlation coefficient (MCC) of 0.9446. These results outperformed the baseline DNN and Transformer models, as well as existing state-of-the-art (SOTA) methods. To further validate the robustness of the model, we conducted an external evaluation using the Drug Target Common (DTC) dataset, where NeSyDPP-4 also demonstrated strong performance, with an accuracy of 0.9579, an AUC-ROC of 0.9565, a Matthews Correlation Coefficient (MCC) of 0.9171, and an F1-score of 0.9577.

DISCUSSION: These findings suggest that the NeSyDPP-4 model not only delivered high predictive performance but also demonstrated generalizability to external datasets. This approach presents a cost-effective and reliable alternative to traditional vivo screening, offering valuable support for the identification and classification of biologically active DPP-4 inhibitors in the treatment of type 2 diabetes mellitus (T2DM).

PMID:40761758 | PMC:PMC12319772 | DOI:10.3389/fbinf.2025.1603133

Front Plant Sci. 2025 Jul 21;16:1645490. doi: 10.3389/fpls.2025.1645490. eCollection 2025.

ABSTRACT

INTRODUCTION: Microplastics (MPs), as emerging environmental contaminants, pose a significant threat to global food security. In order to rapidly screen and diagnosis rice seedling under MPs stress at an early stage, it is essential to develop efficient and non-destructive detection methods.

METHODS: In this study, rice seedlings exposed to different concentrations (0, 10, and 100 mg/L) of polyethylene terephthalate (PET), polystyrene (PS), and polyvinyl chloride (PVC) MPs stress were constructed. Two complementary spectroscopic techniques, visible/near-infrared hyperspectral imaging (VNIR-HSI) and synchrotron radiation-based Fourier Transform Infrared spectroscopy (SR-FTIR), were employed to capture the biochemical changes of leaf organic molecules.

RESULTS: The spectral information of rice seedlings under MPs stress was obtained by using VNIR-HSI, and the low-dimensional clustering distribution analysis of the original spectra was conducted. An improved SE-LSTM full-spectral detection model was proposed, and the detection accuracy rate was greater than 93.88%. Characteristic wavelengths were extracted to build a simplified detection model, and the SHapley Additive exPlanations (SHAP) framework was applied to interpret the model by identifying the bands associated with chlorophyll, carotenoids, water content, and cellulose. Meanwhile, SR-FTIR spectroscopy was used to investigate compositional changes in both leaf lamina and veins, and two-dimensional correlation spectroscopy (2DCOS) was employed to reveal the sequential interactions among molecular components.

DISCUSSION: In conclusion, the combination of spectral technology and deep learning to capture the physiological and biochemical reactions of leaves could provide a rapid and interpretable method for detecting rice seedlings under MPs stress. This method could provide a solution for the early detection of external stress on other crops.

PMID:40761567 | PMC:PMC12318996 | DOI:10.3389/fpls.2025.1645490

Front Plant Sci. 2025 Jul 21;16:1640806. doi: 10.3389/fpls.2025.1640806. eCollection 2025.

ABSTRACT

INTRODUCTION: Accurate wheat yield estimation is crucial for efficient crop management. This study introduces the Spatio-Temporal Fusion Mixture of Experts (STF-MoE) model, an innovative deep learning framework built upon an LSTM-Transformer architecture.

METHODS: The STF-MoE model incorporates a heterogeneous Mixture of Experts (MoE) mechanism with an adaptive gating network. This design dynamically processes fused multi-source remote sensing features (e.g., near-infrared vegetation reflectance, NIRv; fraction of photosynthetically active radiation absorption, Fpar) and environmental variables (e.g., relative humidity, digital elevation model) across multiple expert networks. The model was applied to estimate wheat yield in six major Chinese provinces.

RESULTS: The STF-MoE model demonstrated exceptional accuracy in the most recent estimation year (R² = 0.827, RMSE = 547.7 kg/ha) and exhibited robust performance across historical years and extreme climatic events, outperforming baseline models. Relative humidity and digital elevation model were identified as the most critical yield-influencing factors. Furthermore, the model accurately estimated yield 1-2 months before harvest by identifying key phenological stages (March to June).

DISCUSSION: STF-MoE effectively handles multi-source spatiotemporal complexity via its dynamic gating and expert specialization. While underestimation persists in extreme-yield regions, the model provides a scalable solution for pre-harvest yield estimation. Future work will optimize computational efficiency and integrate higher-resolution data.

PMID:40761564 | PMC:PMC12318938 | DOI:10.3389/fpls.2025.1640806

Front Plant Sci. 2025 Jul 21;16:1583526. doi: 10.3389/fpls.2025.1583526. eCollection 2025.

ABSTRACT

Pod numbers are important for assessing soybean yield. How to simplify the traditional manual process and determine the pod number phenotype of soybean maturity more quickly and accurately is an urgent challenge for breeders. With the development of smart agriculture, numerous scientists have explored the phenotypic information related to soybean pod number and proposed corresponding methods. However, these methods mainly focus on the total number of pods, ignoring the differences between different pod types and do not consider the time-consuming and labor-intensive problem of picking pods from the whole plant. In this study, a deep learning approach was used to directly detect the number of different types of pods on non-disassembled plants at the maturity stage of soybean. Subsequently, the number of pods wascorrected by means of a metric learning method, thereby improving the accuracy of counting different types of pods. After 200 epochs, the recognition results of various object detection algorithms were compared to obtain the optimal model. Among the algorithms, YOLOX exhibited the highest mean average precision (mAP) of 83.43% in accurately determining the counts of diverse pod categories within soybean plants. By improving the Siamese Network in metric learning, the optimal Siamese Network model was obtained. SE-ResNet50 was used as the feature extraction network, and its accuracy on the test set reached 93.7%. Through the Siamese Network model, the results of object detection were further corrected and counted. The correlation coefficients between the number of one-seed pods, the number of two-seed pods, the number of three-seed pods, the number of four-seed pods and the total number of pods extracted by the algorithm and the manual measurement results were 92.62%, 95.17%, 96.90%, 94.93%, 96.64%,respectively. Compared with the object detection algorithm, the recognition of soybean mature pods was greatly improved, evolving into a high-throughput and universally applicable method. The described results show that the proposed method is a robust measurement and counting algorithm, which can reduce labor intensity, improve efficiency and accelerate the process of soybean breeding.

PMID:40761559 | PMC:PMC12319039 | DOI:10.3389/fpls.2025.1583526

Data Brief. 2025 Jul 11;61:111867. doi: 10.1016/j.dib.2025.111867. eCollection 2025 Aug.

ABSTRACT

Beaches are recognized as major sinks of plastic litter and key sites where litter fragments into countless small pieces. Because those fine particles are almost impossible to remove from the natural environment, it is essential to monitor macroplastic litter on beaches before they degrade. To observe the distribution of this litter in detail, it is essential to have automated and objective image-processing methods that can be applied to images captured by remote sensing devices, such as web cameras and drones. To develop such an automated analysis method, a deep learning-based approach has recently become mainstream, and clarifying technical issues based on case studies is vital. The preparation of training data for those practices is critical but laborious. The BePLi Dataset v2 is updated from BePLi Dataset v1, comprises 3722 original images of beach plastic litter and 118,572 manually processed annotations. All original images were obtained from the natural coastal environment on the Northwest Japan coast, and annotation for plastic litter was provided at both the pixel and individual levels. The plastic litter objects are categorized into thirteen representative plastic object classes: "pet_bottle," "other_bottle," "plastic_bag," "box_shaped_case," "other_container," "rope," "other_string," "fishing_net," "buoy," "other_fishing_gear," "styrene_foam," "others" and "fragment." The BePLi Dataset v2 allows users to develop an instance segmentation and object detection method detecting macro beach plastic litter individually and at the pixel level. Depending on the user, this dataset can serve multiple purposes at different levels of technology development, from counting objects to estimating litter coverage, as it provides both bounding box- and pixel-based annotations.

PMID:40761540 | PMC:PMC12320089 | DOI:10.1016/j.dib.2025.111867

Bioimpacts. 2025 Jun 28;15:31226. doi: 10.34172/bi.31226. eCollection 2025.

ABSTRACT

INTRODUCTION: Identifying gene-disease associations is crucial for advancing medical research and improving clinical outcomes. Nevertheless, the rapid expansion of biomedical literature poses significant obstacles to extracting meaningful relationships from extensive text collections.

METHODS: This study uses deep learning techniques to automate this process, using publicly available datasets (EU-ADR, GAD, and SNPPhenA) to classify these associations accurately. Each dataset underwent rigorous pre-processing, including entity identification and preparation, word embedding using pre-trained Word2Vec and fastText models, and position embedding to capture semantic and contextual relationships within the text. In this research, three deep learning-based hybrid models have been implemented and contrasted, including CNN-LSTM, CNN-GRU, and CNN-GRU-LSTM. Each model has been equipped with attentional mechanisms to enhance its performance.

RESULTS: Our findings reveal that the CNN-GRU model achieved the highest accuracy of 91.23% on the SNPPhenA dataset, while the CNN-GRU-LSTM model attained an accuracy of 90.14% on the EU-ADR dataset. Meanwhile, the CNN-LSTM model demonstrated superior performance on the GAD dataset, achieving an accuracy of 84.90%. Compared to previous state-of-the-art methods, such as BioBERT-based models, our hybrid approach demonstrates superior classification performance by effectively capturing local and sequential features without relying on heavy pre-training.

CONCLUSION: The developed models and their evaluation data are available at https://github.com/NoorFadhil/Deep-GDAE.

PMID:40761527 | PMC:PMC12319213 | DOI:10.34172/bi.31226

Cogn Neurodyn. 2025 Dec;19(1):123. doi: 10.1007/s11571-025-10304-3. Epub 2025 Aug 2.

ABSTRACT

Emotion recognition is a difficult problem mainly because emotions are presented in different modalities including; speech, face, and text. In light of this, in this paper, we introduce a novel framework known as Audio, Visual, and Text Emotions Fusion Network that will enhance the approaches to analyzing emotions that can incorporate these dissimilar types of inputs efficiently for the enhancement of the existing approaches to analyzing emotions. Using specialized techniques, each modality in this framework shows Graph Attention Network-based Transformer Network by employing Graph Attention Networks to detect dependencies in facial regions; Hybrid Wav2Vec 2.0 and Convolutional Neural Network combines Wav2Vec 2.0, and Convolutional Neural Network to extract informative temporal and frequency domain audio features. Contextual and sequential text semantics are captured by Bidirectional Encoder Representations from Transformers with Bidirectional Gated Recurrent Unit. They are fused based on a novel attention-based mechanism that distributes weights depending on the emotional context and improves cross-modal interactions. Moreover, the Audio, Visual, and Text Emotions Fusion Network system effectively identifies emotions, and the result section that contains overall accuracy at 98.7%, precision at 98.2%, recall, at 97.2%, and F1-score of 97.49% makes the proposed approach strong and efficient for real-time emotion recognition strategies.

PMID:40761311 | PMC:PMC12317966 | DOI:10.1007/s11571-025-10304-3