Comput Struct Biotechnol J. 2025 May 5;27:1838-1849. doi: 10.1016/j.csbj.2025.05.002. eCollection 2025.

ABSTRACT

Chagas disease is a neglected tropical zoonosis caused by the protozoan Trypanosoma cruzi. The two approved medications for treating this disease show variable efficacy in the chronic phase, highlighting the need for new therapeutic interventions. This study explores a bioinformatics-driven approach to drug discovery using AlphaFold-predicted protein structures. Starting from a virtual screening of approximately 30,000 compounds, 24 were experimentally tested, and two already approved drugs, pimecrolimus and ledipasvir, demonstrated significant antiparasitic activity. These compounds were predicted to target previously uncharacterized T. cruzi proteins, ledipasvir interacting with a calpain-like protein and pimecrolimus likely binding a mitotic cyclin. Molecular dynamics simulations showed that pimecrolimus remains stable in the predicted binding site, while ledipasvir exhibits a higher RMSD. While experimental validation of these targets is needed, these findings underscore the potential of integrating AlphaFold structures into drug discovery strategies to accelerate the identification of new compounds against Chagas disease and other neglected tropical diseases.

SUMMARY: We performed a virtual screening experiment with T. cruzi AlphaFold protein models and a compound collection of more than 30,000 compounds. We tested the top ranked compounds in an in vitro setting, and found two promising candidates for drug repurposing against Chagas disease: pimecrolimus and ledipasvir.

PMID:40470316 | PMC:PMC12136714 | DOI:10.1016/j.csbj.2025.05.002

Int J Pharm X. 2025 May 9;9:100336. doi: 10.1016/j.ijpx.2025.100336. eCollection 2025 Jun.

ABSTRACT

With advancements in drug repurposing, the search for effective and less harmful anticancer agents remains a critical endeavor. Raloxifene, although not a typical anticancer drug, holds promise in this context. However, its poor solubility poses a significant challenge to its therapeutic potential and formulation efficiency. Functional excipients such as cyclodextrins (e.g., β-cyclodextrin, hydroxy propyl β-cyclodextrin, and Captisol) and pH-modifying excipients (e.g., tartaric acid, azelaic acid, and arginine) were investigated to enhance solubility, dissolution, cytotoxicity and cellular uptakes employing Caco-2 cell lines through binary solid dispersions. In silico studies suggested the potential for salt formation with raloxifene-azelaic acid and raloxifene-tartaric acid, as well as inclusion complexes with cyclodextrins. Experimental results showed that pH-modifying excipients, particularly tartaric and azelaic acids, significantly improved solubility (up to an 800-fold increase), outperforming cyclodextrins (8-fold increase) compared to the untreated drug. Cytotoxicity studies on the human breast cancer (Michigan cancer foundation, MCF-7) cells revealed that raloxifene-tartaric acid significantly enhanced cell killing, achieving efficacy comparable to the standard anticancer drug Taxol. Additionally, both fluorescence-labeled raloxifene: hydroxy propyl β-cyclodextrin coprecipitated mixtures (Coppt) and raloxifene: tartaric acid Coppt exhibited concentration- and time-dependent cellular uptake, with mean fluorescence intensity increasing significantly at 24 h, indicating rapid internalization and sustained intracellular retention, especially at higher concentrations. More interestingly, the superior cellular uptake was in favor of the latter, indicating the pH-modifying excipient tartaric acid, and these findings correlated well with solubility and dissolution studies.

PMID:40470029 | PMC:PMC12136891 | DOI:10.1016/j.ijpx.2025.100336

Chem Biol Drug Des. 2025 Jun;105(6):e70138. doi: 10.1111/cbdd.70138.

ABSTRACT

Emergence of life-threatening fungal infections like systemic candidiasis concurrently with bacterial infections and limitations of current antifungal therapies warrant the discovery of novel inhibitors. We identified besifloxacin (BS), an FDA-approved antibacterial, as a potent antifungal inhibitor. A combination of besifloxacin with fluconazole showed a positive synergy (δ = 29.58) resulting in 80% inhibition of microbial growth. BS was able to reduce the MIC of FLC from 2 mg/L to 0.5 mg/L when used in combination. Additionally, in murine systemic Candida infection, BS reduced fungal load by 83% in mice kidneys at a dose of 100 mg/kg/day. The findings demonstrated the antifungal potential of BS, proposing its use in combination therapy with fluconazole to combat resistance through alternative mechanisms.

PMID:40468536 | DOI:10.1111/cbdd.70138

Front Neurosci. 2025 May 21;19:1591410. doi: 10.3389/fnins.2025.1591410. eCollection 2025.

ABSTRACT

BACKGROUNDS: This study innovatively enhances personalized emotional responses and user experience quality in traditional Chinese folding armchair (Jiaoyi chair) design through an interdisciplinary methodology.

GOAL: To systematically extract user emotional characteristics, we developed a hybrid research framework integrating web-behavior data mining.

METHODS: 1) the KJ method combined with semantic crawlers extracts emotional descriptors from multi-source social data; 2) expert evaluation and fuzzy comprehensive assessment reduce feature dimensionality; 3) random forest and K-prototype clustering identify three core emotional preference factors: "Flexible Refinement," "Uncompromising Quality," and "ergonomic stability."

DISCUSSION: A CNN-GRU-Attention hybrid deep learning model was constructed, incorporating dynamic convolutional kernels and gated residual connections to address feature degradation in long-term semantic sequences. Experimental validation demonstrated the superior performance of our model in three chair design preference prediction tasks (RMSE = 0.038953, 0.066123, 0.0069777), outperforming benchmarks (CNN, SVM, LSTM). Based on the top-ranked preference encoding, we designed a new Jiaoyi chair prototype, achieving significantly reduced prediction errors in final user testing (RMSE = 0.0034127, 0.0026915, 0.0035955).

CONCLUSION: This research establishes a quantifiable intelligent design paradigm for modernizing cultural heritage through computational design.

PMID:40470295 | PMC:PMC12133947 | DOI:10.3389/fnins.2025.1591410

Front Pharmacol. 2025 May 21;16:1564124. doi: 10.3389/fphar.2025.1564124. eCollection 2025.

ABSTRACT

Idiosyncratic hepatotoxicity is a type of drug-induced liver injury (DILI) that is unpredictable and clinically severe, and amoxicillin clavulanate (AC) is the most implicated drug in DILI worldwide. The clinical manifestations of amoxicillin clavulanate-induced liver injury (AC-DILI) are fatigue and jaundice, which some allergic features may accompany, but autoimmune phenomena are uncommon. Here, we describe a special case report of a patient with AC-DILI accompanied by autoimmune phenomena for the first time. The patient was a middle-aged Chinese woman who developed liver damage after taking AC for a period of time, with a RUCAM score of 6. The patient tested positive for antinuclear antibodies and had elevated levels of IgG. Human leukocyte antigen (HLA)-targeted sequencing results showed that the patient did not carry known AC-DILI-related HLA polymorphisms, but Sanger sequencing suggested that the patient had the ERAP2 rs1363907 mutation, which may be a pathogenic factor of AC-DILI in the patient. The patient's progress notes, disease diagnosis, and treatment are summarized, and the role of ERAP2 pathogenic mutation rs1363907 in AC-DILI is discussed.

PMID:40469972 | PMC:PMC12133467 | DOI:10.3389/fphar.2025.1564124

Front Oral Health. 2025 May 21;6:1489823. doi: 10.3389/froh.2025.1489823. eCollection 2025.

ABSTRACT

INTRODUCTION: Periodontitis is a chronic inflammatory disease characterized by the progressive destruction of the tooth's supporting tissues, driven by complex interactions between periodontopathogenic bacteria, environmental factors, and the host immune response. MicroRNAs (miRNAs) have emerged as key modulators of inflammatory pathways and are increasingly recognized for their role in the pathogenesis of periodontitis. Their deregulation in this disease suggests potential therapeutic applications targeting miRNA expression. Natural compounds such as isodrimeninol, derived from Drimys winteri (Dw), may offer novel approaches to modulate miRNA activity due to their antiinflammatory properties. However, no studies have previously linked this sesquiterpene to miRNA regulation in periodontitis. This study investigates the in vitro effects of isodrimeninol on six miRNAs (miR-17-3p, miR-21-3p, miR-21-5p, miR-146a-5p, miR-155-5p, and miR-223-3p) associated with periodontitis using two cellular models.

METHODS: Saos-2 cells (osteoblast-like cells) and periodontal ligament-derived mesenchymal stromal cells (hPDL-MSCs). Both cell types were stimulated with lipopolysaccharide (LPS) to induce inflammation and treated with isodrimeninol and resveratrol for comparison.

RESULTS: Isodrimeninol reduced Interleukin-1beta (IL-1β) and Interleukin-6 (IL-6) gene expression and caused differential expression patterns of the miRNAs examined, upregulating miR-146a-5p and miR-223-3p, while downregulating miR-17-3p, miR-21-3p, miR-21-5p, and miR-155-5p (p < 0.05).

CONCLUSION: These findings indicate a connection between miRNAs, periodontitis, and the regulation of inflammation by isodrimeninol, providing potential opportunities for the treatment. However, further validation is needed to confirm these results.

PMID:40469388 | PMC:PMC12133741 | DOI:10.3389/froh.2025.1489823

Front Immunol. 2025 May 21;16:1521794. doi: 10.3389/fimmu.2025.1521794. eCollection 2025.

ABSTRACT

Tumor necrosis factor alpha inhibitors (TNFi) are biologic drugs that target TNFα, a key pro-inflammatory cytokine, to suppress disease activity and alleviate symptoms of various autoimmune diseases, including inflammatory bowel disease. This review focuses on the five US FDA-approved TNFi including the monoclonal antibodies Infliximab, Adalimumab, Golimumab, Certolizumab pegol and the soluble TNFα receptor fusion protein Etanercept, with a brief mention of other available biosimilars to TNFi. The review aims to summarize the recent evidence on the pharmacokinetics, pharmacodynamics, and pharmacogenomics of TNFi with a particular focus on Human Leukocyte Antigen (HLA) variants in terms of their genetic contribution to the response to TNFi. HLA variants have been linked to heterogeneity in the efficacy and safety of TNFi among patients. Building on the summarized evidence, the last part of the review discusses the potential clinical utility of testing for pharmacogenetic variants that are linked to the response to TNFi prior to the drug prescription, and it also addresses the future directions to achieve personalized treatment for TNFi users.

PMID:40469293 | PMC:PMC12133927 | DOI:10.3389/fimmu.2025.1521794

Clin Pharmacol Ther. 2025 Jun 4. doi: 10.1002/cpt.3736. Online ahead of print.

ABSTRACT

Barriers to incorporating pharmacogenetics into routine clinical practice in the United States are well documented. Initial surveys by the Clinical Pharmacogenetics Implementation Consortium (CPIC) in 2009 and 2010 identified barriers across four key domains that have hindered the widespread adoption of clinical pharmacogenetic testing. These are presented verbatim as: (i) absence of a definition of the processes required to interpret genotype information and to translate genetic information into clinical actions; (ii) need for recommended drug/gene pairs to implement clinically now; (iii) clinician resistance to consider pharmacogenetic information at the bedside; and (iv) concerns about test costs and reimbursement. Over time, many of these challenges have been overcome, and clinical pharmacogenetic testing has subsequently reached broader implementation. Despite this progress, several barriers remain that block further adoption. This narrative review used authors' expertise and experience to identify and describe current barriers to pharmacogenetic implementation across seven domains in the United States: equity and inclusion; guidelines and supporting evidence; regulatory agency oversight; payer coverage and insurance; availability of quality pharmacogenetic tests; electronic health records; and provider and patient education. Within each domain, it revisits past successes and challenges and explores remaining barriers. We also propose solutions to address ongoing challenges across these domains, including further expansion of recommendations beyond pharmacogenetic-specific guidelines, standards for designing clinical decision support tools, and broader pharmacogenetics education. Addressing these remaining obstacles directs work to enable broader adoption of clinical pharmacogenetic implementation to ultimately improve patient outcomes.

PMID:40468601 | DOI:10.1002/cpt.3736

ERJ Open Res. 2025 Jun 2;11(3):00897-2024. doi: 10.1183/23120541.00897-2024. eCollection 2025 May.

ABSTRACT

BACKGROUND: Clinical trials with elexacaftor/tezacaftor/ivacaftor (ETI) in people with cystic fibrosis were associated with significant improvements in % predicted forced expiratory volume in 1 s (FEV1 % pred), sweat chloride, weight and quality of life in the respiratory domain from the cystic fibrosis questionnaire revised (CFQ-R). Limited data exist on its effect on structural lung disease and inflammatory cytokines.

METHODS: In a real-world setting with 61 people with cystic fibrosis, we prospectively recorded FEV1, sweat chloride, body mass index (BMI) and CFQ-R at baseline, 3 and 6 months after commencement of ETI. In addition, changes in ultra-low-dose (ULD) computed tomography (CT) Bhalla score, peripheral-blood and sputum inflammatory cytokines and patient-reported outcome measures (PROMs), including sino-nasal outcomes test-22 (SNOT-22) and fatigue scale (FACIT-Fatigue).

RESULTS: Significant improvements in FEV1 % pred (p=0.0001), sweat chloride (p<0.0001) and BMI (p=0.0147) after ETI treatment were noted. ULD-CT scores demonstrated reductions in peri-bronchial thickening, mucus plugging and total Bhalla score (p<0.001), and improvements in emphysema extent (p<0.0027). Improvements in systemic inflammatory status were seen with a reduction in interleukin (IL)-1β (p=0.0049), IL-6 and IL-8 (p<0.0001), and increasing IL-10 (p=0.004). Sputum cytokine analysis was not performed as only four of 61 patients spontaneously expectorated sputum after ETI. PROMs improved significantly for the SNOT-22 (p<0.0001), FACIT-Fatigue score (p=0.0001) and CFQ-R domains, including respiratory (p<0.0001), physical (p=0.007), vitality (p=0.0004), treatment burden (p=0.0028), health (p=0.0007), social (p=0.0073), weight (p=0.0068) and role/school domain (p=0.0018).

CONCLUSION: ETI responders, demonstrate significant improvements in CT imaging, circulating cytokines and PROMs, which may be of further use evaluating cystic fibrosis transmembrane conductance regulator modulation treatment response.

PMID:40470159 | PMC:PMC12134916 | DOI:10.1183/23120541.00897-2024

ERJ Open Res. 2025 Jun 2;11(3):00675-2024. doi: 10.1183/23120541.00675-2024. eCollection 2025 May.

ABSTRACT

BACKGROUND: There are limited data on optimal management of chronic lung allograft dysfunction (CLAD). We aimed to describe the variability of diagnostic and therapeutic practices in Europe.

METHODS: A structured questionnaire was sent to 71 centres in 24 countries. Questions were related to contemporary clinical practices for workup, monitoring and treatment of CLAD. The number of lung transplant procedures and patients in follow-up were collected.

RESULTS: 44 centres (62%) responded from 20 countries, representing 74% of European activity. The prevalence of CLAD was estimated at 9.1 cases per million population (25th and 75th percentiles of 4.4, 15.7). Preferred initial workup for probable CLAD consisted of chest computed tomography (CT) (inspiratory 91% and expiratory 74%), donor-specific antibody (DSA) measurement (86%), bronchoalveolar lavage (BAL) (85%) and transbronchial biopsy (81%). For monitoring of definite CLAD, inspiratory CT (67%), DSA (61%) and BAL (43%) were preferred. Body plethysmography was unavailable for 16% of cases. Prophylaxis was based on preventing infections (cytomegalovirus 99%, inhaled antibiotics 70% and antifungals 65%), tacrolimus-based immunosuppression (96%), azithromycin (72%) and universal proton pump inhibitor treatment (84%). First-line treatment of CLAD was based on azithromycin (82%) and steroid augmentation (74%). Photopheresis was used in 26% of cases.

CONCLUSION: Current European practice CLAD detection is based on spirometry, inspiratory CT and DSA, with limited access to plethysmography and expiratory CT. Prophylactic treatment is based on azithromycin, tacrolimus-based immunosuppression and treatment of risk factors. No single treatment strategy is universally used, highlighting the need for an effective treatment of CLAD. The preferred first-line strategy is azithromycin and steroid augmentation.

PMID:40470157 | PMC:PMC12134928 | DOI:10.1183/23120541.00675-2024

Pulm Med. 2025 May 28;2025:5683225. doi: 10.1155/pm/5683225. eCollection 2025.

ABSTRACT

Background: Therapeutic drug monitoring (TDM) for vancomycin (VAN) in adult people with cystic fibrosis (pwCF) historically has utilized trough concentrations. Recent VAN TDM guidelines recommend area under the curve (AUC) monitoring to reduce the risk of acute kidney injury (AKI), despite limited evidence to support this practice in adult pwCF. Methods: This single-center, retrospective, observational cohort study included 143 adult pwCF admitted from July 1, 2017, to July 1, 2022, with an acute pulmonary exacerbation that received VAN for at least 72 h with available VAN plasma concentrations for TDM for AUC (n = 39) or trough monitoring (n = 104). Eligible patients with multiple hospital admissions during the study period were incorporated as separate encounters. The primary outcome was the incidence of AKI. Results: Receipt of concurrent nephrotoxins was more common in the AUC cohort than in the trough cohort (97% vs. 81%, p = 0.01), but the rate of AKI was similar (7.7% vs. 10.6%, p = 0.76). AUC monitoring was associated with earlier achievement of TDM goal (median 0 days (IQR 0-2) vs. 2 days (IQR 0-4), p < 0.01), lower total daily doses (34.8 mg/kg/day (IQR 27.6-49) vs. 57.5 mg/kg/day (IQR 43.9-68.6), p < 0.01), and fewer regimen changes (median 1 change (IQR 0-2) vs. 2 changes (IQR 1-3), p < 0.01). In patients with MRSA, pulmonary function recovery, readmission, and mortality were similar. Conclusion: In adult pwCF, the incidence of AKI was similar between AUC and trough monitoring cohorts; however, AUC monitoring achieved therapeutic targets sooner with fewer regimen modifications without significantly increasing the number of concentrations compared to trough monitoring.

PMID:40469479 | PMC:PMC12136855 | DOI:10.1155/pm/5683225

World Allergy Organ J. 2025 May 9;18(5):101058. doi: 10.1016/j.waojou.2025.101058. eCollection 2025 May.

ABSTRACT

In recent years, it was recognized that type-2 inflammation connects nasal polyposis and severe asthma (SA) in addition to other type-2 diseases. Thus, some biological drugs developed for SA appeared to exert a favourable effect also in nasal polyposis. So far, there are several trials supporting this concept; therefore, some monoclonal antibodies already used for SA were assessed also in chronic rhinosinusistis with nasal polyposis (CRSwNP), with promising results. Since different specialists are involved in the management of nasal polyposis (eg, pulmonologists, ENT specialists, allergists, immunologists, pediatricians), it was felt that an updated educational and informative document was needed to better identify the indications of biological therapies in nasal polyposis. We collected the main Italian scientific societies, and prepared (under the umbrella of Allergic Rhinitis and its Impact on Asthma, ARIA) a document endorsed by all societies, to provide a provisional statement for the future use of monoclonal antibodies (MAbs) as a medical treatment for polyposis, possibly associated with SA. The above mentioned document was the first endorsed document on this aspect, and the additional evidence required an update. The current pathogenic knowledge and the experimental evidence are herein reviewed, and some suggestions for a correct prescription and follow-up are provided.

PMID:40469214 | PMC:PMC12136883 | DOI:10.1016/j.waojou.2025.101058

Clin Genet. 2025 Jun 5. doi: 10.1111/cge.14780. Online ahead of print.

ABSTRACT

This study assessed the effect of CFTR pathogenic variant status, detected during prenatal carrier screening, for the incidence and clinical recognition of cystic fibrosis-related phenotypes. Data were queried from the Vanderbilt University Medical Center clinical genetic database (CGdb), which includes clinically reported pathogenic variants and electronic health records (EHRs) from 2001 to 2023. Based on carrier screening results, we identified individuals heterozygous for a pathogenic CFTR variant and those who tested negative. Logistic regression tested associations between CFTR carrier status and 11 cystic fibrosis (CF)-related phenotypes. A phenome-wide association study (PheWAS) was performed to identify additional phenotypic associations, and manual chart review was conducted to evaluate recognition and clinical application of CFTR carrier status in patients diagnosed with pancreatitis. Among 12,082 women tested, CFTR carriers (n = 451) were at significantly higher risk of developing acute pancreatitis (p = 3.93 × 10-6; OR = 4.68 [2.43-9.00]). No other CF-related phenotypes were significantly associated in this female cohort. Manual chart review revealed that CFTR carrier screening results were not clinically correlated with pancreatitis diagnoses. In this large cohort of women tested for prenatal carrier screening, CFTR pathogenic variants relevant to pancreatitis were overlooked, despite informing etiology, management, and prognosis.

PMID:40468859 | DOI:10.1111/cge.14780

ArXiv [Preprint]. 2025 May 20:arXiv:2505.14507v1.

ABSTRACT

BACKGROUND: Deep learning has potential to improve the efficiency and consistency of radiation therapy planning, but clinical adoption is hindered by the limited model generalizability due to data scarcity and heterogeneity among institutions. Although aggregating data from different institutions could alleviate this problem, data sharing is a practical challenge due to concerns about patient data privacy and other technical obstacles.

PURPOSE: This work aims to address this dilemma by developing FedKBP+, a comprehensive federated learning (FL) platform for predictive tasks in real-world applications in radiotherapy treatment planning.

METHODS: We implemented a unified communication stack based on Google Remote Procedure Call (gRPC) to support communication between participants whether located on the same workstation or distributed across multiple workstations. In addition to supporting the centralized FL strategies commonly available in existing open-source frameworks, FedKBP+ also provides a fully decentralized FL model where participants directly exchange model weights to each other through Peer-to-Peer communication. We evaluated FedKBP+ on three predictive tasks using scale-attention network (SA-Net) as the predictive model.

CONCLUSIONS: Our results demonstrate that FedKBP+ is highly effective, efficient and robust, showing great potential as a federated learning platform for radiation therapy.

PMID:40470470 | PMC:PMC12136487

Front Plant Sci. 2025 May 21;16:1575038. doi: 10.3389/fpls.2025.1575038. eCollection 2025.

ABSTRACT

The rising costs and labor shortages have sparked interest in machine harvesting of fresh-market blueberries. A major drawback of machine harvesting is the occurrence of internal bruising, as the fruit undergoes multiple mechanical impacts during this process. Evaluating fruit internal bruising manually is a tedious and time-consuming process. In this study, we leveraged deep learning models to rapidly quantify berry fruit internal bruising. Blueberries from 61 cultivars of soft to firm types were subjected to bruise over a three-year period from 2021-2023. Dropped berries were sliced in half along the equator and digitally photographed. The captured images were first analyzed using the YOLO detection model to identify and isolate individual fruits with bounding boxes. Then YOLO segmentation models were performed on each fruit to obtain the fruit cross-section area and the bruising area, respectively. Finally, the bruising ratio was calculated by dividing the predicted bruised area by the predicted cross-sectional area. The mean Average Precision (mAP) of the bruising segmentation model was 0.94. The correlation between the bruising ratio and ground truth was 0.69 with a mean absolute percentage error (MAPE) of 15.87%. Moreover, analysis of bruising ratios of different cultivars revealed significant variability in bruising susceptibility and the mean bruising ratio of 0.22 could be an index to differentiate the bruise-resistant and bruise-susceptible cultivars. Furthermore, the mean bruising ratio was negatively correlated with mechanical texture parameter, Young's modulus 20% Burst Strain. Overall, this study presents an effective and efficient approach with a user-friendly interface to evaluate blueberry internal bruising using deep learning models, which could facilitate the breeding of blueberry genotypes optimized for machine harvesting. The models are available at https://huggingface.co/spaces/c-tan/blueberrybruisingdet.

PMID:40470370 | PMC:PMC12133755 | DOI:10.3389/fpls.2025.1575038

Front Plant Sci. 2025 May 21;16:1588901. doi: 10.3389/fpls.2025.1588901. eCollection 2025.

ABSTRACT

INTRODUCTION: The accurate identification of maize varieties is of great significance to modern agricultural management and breeding programs. However, traditional maize seed classification methods mainly rely on single modal data, which limits the accuracy and robustness of classification. Additionally, existing multimodal methods face high computational complexity, making it difficult to balance accuracy and efficiency.

METHODS: Based on multi-modal data from 11 maize varieties, this paper presents DualCMNet, a novel dual-branch deep learning framework that utilizes a one-dimensional convolutional neural network (1D-CNN) for hyperspectral data processing and a MobileNetV3 network for spatial feature extraction from images. The framework introduces three key improvements: the HShuffleBlock feature transformation module for feature dimension alignment and information interaction; the Channel and Spatial Attention Mechanism (CBAM) to enhance the expression of key features; and a lightweight gated fusion module that dynamically adjusts feature weights through a single gate value. During training, pre-trained 1D-CNN and MobileNetV3 models were used for network initialization with a staged training strategy, first optimizing non-pre-trained layers, then unfreezing pre-trained layers with differentiated learning rates for fine-tuning.

RESULTS: Through 5-fold cross-validation evaluation, the method achieved a classification accuracy of 98.75% on the validation set, significantly outperforming single-modal methods. The total model parameters are only 2.53M, achieving low computational overhead while ensuring high accuracy.

DISCUSSION: This lightweight design enables the model to be deployed in edge computing devices, allowing for real-time identification in the field, thus meeting the practical application requirements in agricultural Internet of Things and smart agriculture scenarios. This study not only provides an accurate and efficient solution for maize seed variety identification but also establishes a universal framework that can be extended to variety classification tasks of other crops.

PMID:40470359 | PMC:PMC12133733 | DOI:10.3389/fpls.2025.1588901

Data Brief. 2025 May 2;60:111610. doi: 10.1016/j.dib.2025.111610. eCollection 2025 Jun.

ABSTRACT

Advancements in computer vision and deep learning have transformed ecological monitoring and species identification, enabling automated and accurate data labelling. Despite these advancements, robust AI-driven solutions for avian species recognition remain limited, primarily due to the scarcity of high-quality annotated datasets. To address this gap, this article introduces IBERBIRDS-a comprehensive and publicly accessible dataset specifically designed to facilitate automatic detection and classification of flying bird species in the Iberian Peninsula under real-world conditions. The dataset comprises 4000 images representing 10 ecologically significant medium to large-sized bird species, with each image annotated using bounding box coordinates in the YOLO detection format. Unlike existing datasets that typically feature close-up or ideal-condition imagery, IBERBIRDS focuses on mid-to-long range photographs of birds in flight, providing a more realistic and challenging representation of scenarios commonly encountered in birdwatching, conservation, and ecological monitoring. Images were sourced from publicly available, expert-validated ornithology platforms and underwent rigorous quality control to ensure annotation accuracy and consistency. This process included homogenizing color profiles and formats, as well as manual refinement to ensure that each image contains a single bird specimen. Additionally, detailed provenance and taxonomic metadata for each image has been systematically integrated into the dataset. The lack of pre-annotated datasets has significantly restricted large-scale ecological analysis and the development of automated techniques in avian research, hindering the progress of AI-driven solutions tailored for bird species recognition. By addressing this gap, this dataset serves as a comprehensive benchmark for avian studies, fostering advancements in various applications such as conservation initiatives, environmental impact assessments, biodiversity preservation strategies, real-time tracking systems, and video-based analysis. Additionally, IBERBIRDS constitutes a resource for computer vision applications, supporting educational programs tailored to ornithologists and birdwatching communities. By openly providing this dataset, IBERBIRDS promotes scientific collaboration and technological advancements, ultimately contributing to the preservation and understanding of avian biodiversity.

PMID:40470349 | PMC:PMC12136710 | DOI:10.1016/j.dib.2025.111610

Data Brief. 2025 Apr 28;60:111593. doi: 10.1016/j.dib.2025.111593. eCollection 2025 Jun.

ABSTRACT

This dataset is an expanded version of a previously published collection of high-resolution RGB images of Urochloa spp. genotypes, initially designed to facilitate automated classification of phenological stages and raceme identification in forage breeding trials. The original dataset included 2400 images of 200 genotypes captured under controlled conditions, supporting the development of computer vision models for High-Throughput Phenotyping (HTP). In this updated release, 139 additional images and 24,983 new annotations have been added, bringing the dataset to a total of 2539 images and 47,323 raceme annotations. This version introduces increased diversity in image-capture conditions, with data collected from two geographic locations (Palmira, Colombia, and Ocozocoautla de Espinosa, Mexico) and a range of image-capture devices, including smartphones (e.g. Realme C53 and Oppo Reno 11), a Nikon D5600 camera, and a Phantom 4 Pro V2 drone. Images now vary in perspective (nadir, high-angle, and frontal) and capture distance (1-3 meters), enhancing the dataset applicability for robust Deep Learning (DL) models. Compared to the original dataset, raceme density per plant has nearly doubled in some samples, offering higher raceme overlap for advanced instance segmentation tasks. This expanded dataset supports deeper exploration of phenotypic variation in Urochloa spp. and offers greater potential for developing adaptable models in crop phenotyping.

PMID:40470345 | PMC:PMC12136700 | DOI:10.1016/j.dib.2025.111593

Data Brief. 2025 Apr 28;60:111587. doi: 10.1016/j.dib.2025.111587. eCollection 2025 Jun.

ABSTRACT

Breast cancer is one of the most prevalent cancers affecting women worldwide. Early detection and treatment are crucial in significantly reducing mortality rates Microcalcifications (MCs) are of particular importance among the various breast lesions. These tiny calcium deposits within breast tissue are present in approximately 30% of malignant tumors and can serve as critical indirect indicators of early-stage breast cancer. Three or more MCs within an area of 1 cm² are considered a Microcalcification Cluster (MCC) and assigned a BI-RADS category 4, indicating a suspicion of malignancy. Mammography is the most used technique for breast cancer detection. Approximately one in two mammograms showing MCCs is confirmed as cancerous through biopsy. MCCs are challenging to detect, even for experienced radiologists, underscoring the need for computer-aided detection tools such as Convolutional Neural Networks (CNNs). CNNs require large amounts of domain-specific data with consistent resolutions for effective training. However, most publicly available mammogram datasets either lack resolution information or are compiled from heterogeneous sources. Additionally, MCCs are often either unlabeled or sparsely represented in these datasets, limiting their utility for training CNNs. In this dataset, we present the MEXBreast, an annotated MCCs Mexican digital mammogram database, containing images from resolutions of 50, 70, and 100 microns. MEXBreast aims to support the training, validation, and testing of deep learning CNNs.

PMID:40470344 | PMC:PMC12136707 | DOI:10.1016/j.dib.2025.111587

Comput Struct Biotechnol J. 2025 Apr 29;27:1809-1817. doi: 10.1016/j.csbj.2025.04.034. eCollection 2025.

ABSTRACT

BACKGROUND AND OBJECTIVE: In recent years, DNA methylation-tumor classification based on artificial intelligence algorithms has led to a notable improvement in diagnostic accuracy compared to traditional machine learning methods. In cancer, the methylation pattern likely reflects both the cell of origin and somatically acquired DNA methylation changes, making this epigenetic modification an ideal tool for tumor classification. We propose an in-depth method based on the Convolutional Neural Network for the DNA methylation-based classification of papillary thyroid carcinoma (PTC) and its follicular (fvPTC) and classical (cvPTC) subtypes.

METHODS: To address this issue, we first performed a pan-cancer analysis to train a convolutional 1-D Neural Network (CNN) using supervised learning. Then, we evaluated the robustness of the net on an independent PTC dataset and assessed its ability to classify normal (N=56) versus tumor (N=461) samples and fvPTC (N=102) versus cvPTC (N=359). We then compared its performance with 4 machine learning models (logistic regression with elastic net penalty, quadratic discriminant analysis, support vector classifier with RBF kernel, and random forest).

RESULTS: By using RELU activation function and leaving out liquid tumors, our results show a remarkable performance of the neural network in classifying cancer and normal samples when applied to pan-cancer data (Validation AUC = 0.9903 and Validation Loss = 0.112). When applied to the thyroid independent dataset, the proposed Neural Net architecture successfully discriminates tumor versus normal samples (AUC = 0.91 +/- 0.05) and follicular versus classical PTC subtypes (AUC = 0.80 +/- 0.05), outperforming traditional machine learning algorithms.

CONCLUSIONS: In conclusion, the study highlights the effectiveness of CNNs in the methylation based classification of thyroid tumors and their subtypes, demonstrating its ability to capture subtle epigenetic differences with minimal preprocessing.This versatility makes the model adaptable for classifying other tumor types. Also, the findings emphasize the potential relevance of AI algorithms in addressing complex diagnostic challenges and supporting clinical decisions.This research lays the foundation for developing robust and generalizable models that can advance precision oncology in cancer diagnostics.

PMID:40470317 | PMC:PMC12136774 | DOI:10.1016/j.csbj.2025.04.034