Skeletal Radiol. 2025 Mar 28. doi: 10.1007/s00256-025-04917-2. Online ahead of print.

ABSTRACT

OBJECTIVE: This study aims to establish a large degenerative cervical myelopathy cohort and develop deep learning models for predicting cervical canal stenosis from sagittal T2-weighted MRI.

MATERIALS AND METHODS: Data was collected retrospectively from patients who underwent a cervical spine MRI from January 2007 to December 2022 at a single institution. Ground truth labels for cervical canal stenosis were obtained from sagittal T2-weighted MRI using Kang's grade, a four-level scoring system that classifies stenosis with the degree of subarachnoid space obliteration and cord indentation. ResNet50, VGG16, MobileNetV3, and EfficientNetV2 were trained using threefold cross-validation, and the models exhibiting the largest area under the receiver operating characteristic curve (AUC) were selected to produce the ensemble model. Gradient-weighted class activation mapping was adopted for qualitative assessment. Models that incorporate demographic features were trained, and their corresponding AUCs on the test set were evaluated.

RESULTS: Of 8676 patients, 7645 were eligible for developing deep learning models, where 6880 (mean age, 56.0 ± 14.3 years, 3480 men) were used for training while 765 (mean age, 56.5 ± 14.4 years, 386 men) were set aside for testing. The ensemble model exhibited the largest AUC of 0.95 (0.94-0.97). Accuracy was 0.875 (0.851-0.898), sensitivity was 0.885 (0.855-0.915), and specificity was 0.861 (0.824-0.898). Qualitative analyses demonstrated that the models accurately pinpoint radiologic findings suggestive of cervical canal stenosis and myelopathy. Incorporation of demographic features did not result in a gain of AUC.

CONCLUSION: We have developed deep learning models from a large degenerative cervical myelopathy cohort and thoroughly explored their robustness and explainability.

PMID:40152984 | DOI:10.1007/s00256-025-04917-2

Am J Respir Crit Care Med. 2025 Mar 28. doi: 10.1164/rccm.202410-1934OC. Online ahead of print.

ABSTRACT

Rationale: Idiopathic pulmonary fibrosis (IPF) is characterized by excessive deposition of type 1 collagen. 68Ga-CBP8, a type 1 collagen positron emission tomography (PET) probe, measures collagen accumulation and shows higher collagen deposition in patients with IPF. Bexotegrast (PLN-74809) is an oral, once-daily, dual-selective inhibitor of αvβ6 and αvβ1 integrins under late-stage evaluation for treatment of IPF. Objectives: Evaluate changes in type 1 collagen in the lungs of participants with IPF following treatment with bexotegrast. Methods: In this Phase 2 (NCT05621252), single-center, double-blind, placebo-controlled study, adults with IPF received bexotegrast 160mg or placebo for 12 weeks. Primary endpoint was the change in whole-lung standardized uptake value (SUV) of 68Ga-CBP8 PET. Changes in lung dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) parameters, forced vital capacity (FVC), cough severity, and biomarkers of collagen synthesis and progressive disease were also assessed. Measurements and Main Results: Of 10 participants, 7 received bexotegrast and 3 placebo. At Week 12, mean change from baseline in top quartile of 68Ga-CBP8 whole-lung SUV was -1.2% with bexotegrast vs 6.6% with placebo; greatest mean changes were observed in subpleural lung regions in both groups (bexotegrast, -3.7%; placebo, 10.3%). DCE-MRI demonstrated numerically increased peak enhancement and faster contrast washout rate in bexotegrast-treated participants, suggesting improvements in lung microvasculature and decreased extravascular extracellular volume. Bexotegrast treatment resulted in numerical improvements in FVC, cough severity, and biomarker levels. Conclusions: The reduced uptake of 68Ga-CBP8 in the lungs of participants with IPF indicates an antifibrotic effect of bexotegrast, suggesting the potential for favorable lung remodeling.

PMID:40153543 | DOI:10.1164/rccm.202410-1934OC

Naunyn Schmiedebergs Arch Pharmacol. 2025 Mar 28. doi: 10.1007/s00210-025-04076-0. Online ahead of print.

ABSTRACT

The molecular link between endoplasmic reticulum stress (ERS) and idiopathic pulmonary fibrosis (IPF) remains elusive. Our study aimed to uncover core mechanisms and new therapeutic targets for IPF. By analyzing gene expression profiles from the Gene Expression Omnibus (GEO) database, we identified 1519 differentially expressed genes (DEGs) and 11 ERS-related genes (ERSRGs) diagnostic for IPF. Using weighted gene co-expression network analysis (WGCNA) and differential expression analysis, key genes linked to IPF were pinpointed. CIBERSORT was used to assess immune cell infiltration, while the Gene Ontology (GO) and the Kyoto Encyclopedia of Genes and Genomes (KEGG) analyses were performed to explore biological mechanisms. In three GEO datasets (GSE150910, GSE92592, and GSE124685), the receiver operating characteristic (ROC) curve analysis showed area under the ROC curve (AUC) > 0.7 for all ERSRGs. The Connectivity Map (CMap) database was used to predict small molecules modulating IPF signatures. The molecular docking energies of mirdametinib with protein targets ranged from - 5.1643 to - 8.0154 kcal/mol, while those of linsitinib ranged from - 5.6031 to - 7.902 kcal/mol. Molecular docking and animal experiments were performed to validate the therapeutic potential of identified compounds, with mirdametinib showing specific effects in a murine bleomycin-induced pulmonary fibrosis model. In vitro experiments indicated that mirdametinib may alleviate pulmonary fibrosis by reducing ERS via the PI3K/Akt/mTOR pathway. Our findings highlight 11 ERSRGs as predictors of IPF and demonstrate the feasibility of bioinformatics in drug discovery for IPF treatment.

PMID:40153017 | DOI:10.1007/s00210-025-04076-0

Sci Adv. 2025 Mar 28;11(13):eadt9287. doi: 10.1126/sciadv.adt9287. Epub 2025 Mar 28.

ABSTRACT

Photorespiration causes a substantial decrease in crop yield because of mitochondrial decarboxylation. Alternative pathways (APs) have been designed to relocate the decarboxylation step or even fix additional carbon. To improve the success of transferring those engineered APs from model species to crops, we must understand how they will interact with metabolism and how plant physiology affects their performance. Here, we used multiple mathematical modeling techniques to analyze and compare existing AP designs. We show that carbon-fixing APs are the most promising candidates to replace native photorespiration in major crop species. Our results demonstrate the different metabolic routes that APs use to increase yield and which plant physiology can profit the most from them. We anticipate our results to guide the design of new APs and to help improve existing ones.

PMID:40153498 | DOI:10.1126/sciadv.adt9287

Bull Math Biol. 2025 Mar 28;87(5):60. doi: 10.1007/s11538-025-01439-9.

ABSTRACT

A framework for parameter estimation and uncertainty quantification is crucial for understanding the mechanisms of biological interactions within complex systems and exploring their dynamic behaviors beyond what can be experimentally observed. Despite recent advances, challenges remain in achieving the high accuracy of parameter estimation and uncertainty quantification at moderate computational costs. To tackle these challenges, we developed a novel approach that integrates the quantile method with Physics-Informed Neural Networks (PINNs). This method utilizes a network architecture with multiple parallel outputs, each corresponding to a distinct quantile, facilitating a comprehensive characterization of parameter estimation and its associated uncertainty. The effectiveness of the proposed approach was validated across three study cases, where it was compared to the Monte Carlo dropout (MCD) and the Bayesian methods. Furthermore, a larger-scale model was employed to further demonstrate the excellent performance of the proposed approach. Our approach exhibited significantly superior efficacy in parameter estimation and uncertainty quantification. This highlights its great promise to broaden the scope of applications in system biology modeling.

PMID:40153179 | DOI:10.1007/s11538-025-01439-9

Cardiovasc Toxicol. 2025 Mar 28. doi: 10.1007/s12012-025-09987-1. Online ahead of print.

ABSTRACT

The pharmaceutical industry is evolving with the use of human induced pluripotent stem cell-derived cardiomyocytes (hiPSC-CM) for in vitro cardiac safety screening. Traditional reliance on QT-interval prolongation as a main arrhythmogenicity marker is being challenged. In addition, the Comprehensive In Vitro Proarrhythmia Assay (CiPA) initiative recommends using computer modeling and in silico platforms as a more comprehensive approach for arrhythmogenicity testing in conjunction with hiPSC-CM in vitro screening. Our study presents an innovative platform that integrates in vitro hiPSC-CM propagation test with in silico models to assess the potential arrhythmogenic effect of drug-induced impact on ionic currents and electrophysiological intercellular coupling. Utilizing the electrophysiological and morphological characteristics of hiPSC-CM, we offer a thorough evaluation of potential drug-induced cardiac risks by computer modeling. We show, using the examples of lidocaine (100-300 μM) and Cyclophosphamide (639, 852 μM), that with the use of an integrative experimental and computer platform, it is possible to correctly display the clinical manifestations of side effects in advance.

PMID:40153244 | DOI:10.1007/s12012-025-09987-1

Med Lett Drugs Ther. 2025 Mar 31;67(1725):e56. doi: 10.58347/tml.2025.1725d.

NO ABSTRACT

PMID:40152724 | DOI:10.58347/tml.2025.1725d

Cochrane Database Syst Rev. 2025 Mar 28;3:CD015313. doi: 10.1002/14651858.CD015313.pub2.

ABSTRACT

BACKGROUND: Chronic suppurative lung disease (CSLD) is an umbrella term to define the spectrum of endobronchial suppurative lung disease, including bronchiectasis and protracted bacterial bronchitis (PBB), associated with chronic wet or productive cough. Research that explores new therapeutic options in children with CSLD has been identified by clinicians and patients as one of the top research priorities. Mucolytic agents work to improve mucociliary clearance and interrupt the vicious vortex of airway infection and inflammation, hence they have potential as a therapeutic option.

OBJECTIVES: To assess the effects of mucolytics for reducing exacerbations, improving quality of life and other clinical outcomes in children with CSLD (including PBB and bronchiectasis), and to assess the risk of harm due to adverse events.

SEARCH METHODS: An Information Specialist searched the Cochrane Airways Trials Register to June 2022, and a review author searched the Cochrane Central Register of Controlled Trials (CENTRAL), MEDLINE and Embase databases to 27 September 2024. Other review authors handsearched respiratory journals.

SELECTION CRITERIA: We included randomised controlled trials (RCTs), of both cross-over and parallel design, that compared a mucolytic with a placebo or 'no intervention' control group and included children (aged 18 years and under) with any type of CSLD (including PBB and bronchiectasis). We excluded studies with adult participants and studies in children with cystic fibrosis, empyema, pulmonary abscess or bronchopulmonary fistula.

DATA COLLECTION AND ANALYSIS: Two authors independently reviewed titles and abstracts to assess eligibility for inclusion. The authors then assessed study quality and extracted data. They assessed the quality of the study using the Cochrane risk of bias tool (RoB 2), and used GRADE to assess the certainty of evidence. Outcomes of interest to be analysed included: i) for maintenance or stable state: rate of exacerbations, ii) for exacerbation state: time to resolution of respiratory exacerbation, iii) lung function - forced expiratory volume in one second (FEV1) and forced vital capacity (FVC), iv) quality of life and v) adverse events. Only one study met the inclusion criteria, so we could not perform a meta-analysis. Data were continuous, so we reported outcomes as mean differences.

MAIN RESULTS: The sole included RCT was a cross-over study of 63 children in the total cohort, with reported data and analysis of only 52 children (26 per arm) with non-cystic fibrosis bronchiectasis. The study compared 3% hypertonic saline nebulised before chest physiotherapy with a control arm (physiotherapy alone), with each phase lasting eight weeks. Children in the hypertonic saline arm had a mean age of 9.80 (SD 2.97) years and 42.3% were male; those in the control arm had a mean age of 9.10 (SD 2.40) years and 38.4% were male. Only results of the first arm of the cross-over study were included in this review. The RCT reported a clinically important difference between the groups for our review's primary outcome: rate of respiratory exacerbations. The mean number of exacerbations per child-year was 2.50 (SD 0.64) in the intervention group and 7.80 (SD 1.05) in the control group (mean difference (MD) -5.30, 95% CI -5.77 to -4.83; 1 study, 52 participants; very low-certainty evidence). The RCT also reported that the percentage point improvement in mean % predicted FEV1 and FVC from baseline to week eight was better with hypertonic saline compared to control. Mean FEV1 improvement was 14.15% (SD 5.50) in the intervention group versus 5.04% (SD 5.55) in the control group (MD 9.11%, 95% CI 6.11 to 12.11; 1 study, 52 participants; very low-certainty evidence). While for FVC, the mean improvement was 13.77% (SD 5.73) compared with 7.54% (SD 4.90), respectively (MD 6.23%, 95% CI 3.33 to 9.13; 1 study, 52 participants; very low-certainty evidence). Quality of life measures were not used. We judged the study to have a high risk of bias due to unblinding, missing data, deviation from the intended intervention and reporting bias with measurement and selection of outcome measures. The authors reported that there were no dropouts due to adverse events. No data were available regarding quality of life. The included study assessed mucolytic use during a stable state, and we found no studies of mucolytic use during an exacerbation. We also found no studies assessing oral mucolytics, other inhaled mucolytics, use in PBB, or in settings other than hospital outpatients. We also found two ongoing studies, one using hypertonic saline and one using an oral mucolytic agent erdosteine, which will potentially be included in future updates of this review.

AUTHORS' CONCLUSIONS: This systematic review is limited to a single small study, which we judged to be at high risk of bias. It remains uncertain whether regular nebulised hypertonic saline during a stable state reduces exacerbations or improves lung function. Further multi-centre, well-designed RCTs of longer duration that investigate various mucolytics are required to answer this important clinical question.

PMID:40152354 | DOI:10.1002/14651858.CD015313.pub2

Pediatr Pulmonol. 2025 Apr;60(4):e71067. doi: 10.1002/ppul.71067.

NO ABSTRACT

PMID:40152078 | DOI:10.1002/ppul.71067

J Comput Biol. 2025 Mar 28. doi: 10.1089/cmb.2024.0872. Online ahead of print.

ABSTRACT

Gleason grading of prostate histopathology images is widely used by pathologists for diagnosis and prognosis. Spatial characteristics of cell and tissues through staining images is essential for accurate grading of prostate cancer. Although considerable efforts have been made to train grading models, they mainly rely on basic preprocessed images and largely overlook the intricate multiple staining aspects of histopathology images that are crucial for spatial information capture. This article proposes a novel deep learning model for automated prostate cancer grading by integrating several staining characteristics. Image deconvolution is applied to separate the multiple staining channels in the histopathology image, thereby enabling the model to identify effective feature information. A channel and pixel attention-based encoder is designed to extract cell and tissue structure information from multiple staining channel images. We propose a dual-branch decoder, where the classical convolutional neural network branch specializes in local feature extraction and the Transformer branch focuses on global feature extraction, to effectively fuse and refine features from different staining channels. Taking full advantage of the complementarity of multiple staining channels makes the features more compact and discriminative, leading to precise grading. Extensive experiments on relevant public datasets demonstrate the effectiveness and scalability of the proposed model.

PMID:40152893 | DOI:10.1089/cmb.2024.0872

Transl Vis Sci Technol. 2025 Mar 3;14(3):27. doi: 10.1167/tvst.14.3.27.

ABSTRACT

PURPOSE: The purpose of this study was to develop models that predict which patients with glaucoma will progress to require surgery, combining structured data from electronic health records (EHRs) and retinal fiber layer optical coherence tomography (RNFL OCT) scans.

METHODS: EHR data (demographics and clinical eye examinations) and RNFL OCT scans were identified for patients with glaucoma from an academic center (2008-2023). Comparing the novel TabNet deep learning architecture to a baseline XGBoost model, we trained and evaluated single modality models using either EHR or RNFL features, as well as fusion models combining both EHR and RNFL features as inputs, to predict glaucoma surgery within 12 months (binary).

RESULTS: We had 1472 patients with glaucoma who were included in this study, of which 29.9% (N = 367) progressed to glaucoma surgery. The TabNet fusion model achieved the highest performance on the test set with an area under the receiver operating characteristic curve (AUROC) of 0.832, compared to the XGBoost fusion model (AUROC = 0.747). EHR only models performed with an AUROC of 0.764 and 0.720 for the deep learning model and XGBoost models, respectively. RNFL only models performed with an AUROC of 0.624 and 0.633 for the deep learning and XGBoost models, respectively.

CONCLUSIONS: Fusion models which integrate both RNFL with EHR data outperform models only utilizing one datatype or the other to predict glaucoma progression. The deep learning TabNet architecture demonstrated superior performance to traditional XGBoost models.

TRANSLATIONAL RELEVANCE: Prediction models that utilize the wealth of structured clinical and imaging data to predict glaucoma progression could form the basis of future clinical decision support tools to personalize glaucoma care.

PMID:40152766 | DOI:10.1167/tvst.14.3.27

Spine (Phila Pa 1976). 2025 Mar 28. doi: 10.1097/BRS.0000000000005280. Online ahead of print.

ABSTRACT

STUDY DESIGN: Retrospective single-institution study.

OBJECTIVE: To develop and validate an automated convolutional neural network (CNN) to measure the Cobb angle, T1 tilt angle, coronal balance, clavicular angle, height of the shoulders, T5-T12 Cobb angle, and sagittal balance for accurate scoliosis diagnosis.

SUMMARY OF BACKGROUND DATA: Scoliosis, characterized by a Cobb angle >10°, requires accurate and reliable measurements to guide treatment. Traditional manual measurements are time-consuming and have low inter- and intra-observer reliability. While some automated tools exist, they often require manual intervention and focus primarily on the Cobb angle.

METHODS: In this study, we utilized four datasets comprising the anterior-posterior (AP) and lateral radiographs of 1682 patients with scoliosis. The CNN includes coarse segmentation, landmark localization, and fine segmentation. The measurements were evaluated using the dice coefficient, mean absolute error (MAE), and percentage of correct key-points (PCK) with a 3-mm threshold. An internal testing set, including 87 adolescent (7-16 years) and 26 older adult patients (≥60 years), was used to evaluate the agreement between automated and manual measurements.

RESULTS: The automated measures by the CNN achieved high mean dice coefficients (>0.90), PCK of 89.7%-93.7%, and MAE for vertebral corners of 2.87 mm-3.62 mm on AP radiographs. Agreement on the internal testing set for manual measurements was acceptable, with an MAE of 0.26 mm/°-0.51 mm/° for the adolescent subgroup and 0.29 mm/°-4.93 mm/° for the older adult subgroup on AP radiographs. The MAE for the T5-T12 Cobb angle and sagittal balance, on lateral radiographs, was 1.03° and 0.84 mm, respectively, in adolescents, and 4.60° and 9.41 mm, respectively, in older adults. Automated measurement time was significantly shorter compared to manual measurements.

CONCLUSION: The deep learning automated system provides rapid, accurate, and reliable measurements for scoliosis diagnosis, which could improve clinical workflow efficiency and guide scoliosis treatment.

THE LEVEL OF EVIDENCE OF THIS STUDY: Level 3.

PMID:40152470 | DOI:10.1097/BRS.0000000000005280

ACS Sens. 2025 Mar 28. doi: 10.1021/acssensors.5c00403. Online ahead of print.

ABSTRACT

In the field of flexible sensors, the development of multifunctional, highly sensitive, wide detection range, and excellent durability sensors remains a significant challenge. This paper designs and fabricates a dual-mode ion gel sensor based on the spider's sensing mechanism, integrating both wind speed and pressure detection. The wind speed sensor employs magnetic fiber flocking and inductive resonance principles, providing accurate detection within a wind speed range of 2 to 11.5 m/s, with good linear response and high sensitivity. The impedance signal exhibits a maximum variation of 6.89 times. The pressure sensor, combining microstructured ion gel and capacitive design, demonstrates high sensitivity (15.93 kPa-1) and excellent linear response within a pressure range of 0.5 Pa to 40 kPa, with strong adaptability and good stability. The sensor shows outstanding performance in human motion monitoring, accurately capturing physiological signals such as joint movements and respiratory frequency, offering robust support for motion health management. Furthermore, combined with deep learning algorithms, the sensor achieves an accuracy of 96.83% in an intelligent motion recognition system, effectively enhancing the precision of motion performance analysis. This study provides a new solution for flexible motion monitoring and health management systems, with broad application prospects.

PMID:40152352 | DOI:10.1021/acssensors.5c00403

Phys Chem Chem Phys. 2025 Mar 28. doi: 10.1039/d4cp04605f. Online ahead of print.

ABSTRACT

Due to their inherently stochastic nature, microscopic configurations and conductance values of nano-junctions fabricated using break-junction techniques vary and fluctuate in and between experiments. Unfortunately, it is extremely difficult to observe the structural evolution of nano-junctions while measuring their conductance, a fact that prevents the establishment of their structure-conductance relationship. Herein, we conduct classical molecular dynamics (MD) simulations with neural-network potentials to simulate the stretching of Au and Ag nanowires followed by training a transformer-based neural network to predict their conductance. In addition to achieving an accuracy comparable to ab initio molecular dynamics within a computational cost similar to classical force fields, our approach can acquire the conductance of a large number of junction structures efficiently. Our calculations show that the transformer-based neural network, leveraging its self-attention mechanism, exhibits remarkable stability, accuracy and scalability in the prediction of zero-bias conductance of longer, larger and even structurally different gold nanowires when trained only on smaller systems. The simulated conductance histograms of gold nanowires are highly consistent with experiments. By examining the MD trajectories of gold nanowires simulated at 150 K and 300 K, we find that the formation probability of a three-strand planar structure appearing at 300 K is much higher than that at 150 K. This may be the dominating factor for the observed blueshift of the main peak positioned between 1.5-2G0 in the conductance histogram following the temperature increase. Moreover, our transformer-based neural network pretrained on Au has an excellent transferability, which can be fine-tuned to predict accurately the conductance of Ag nanowires with much less training data. Our findings pave the way for using deep learning techniques in molecule-scale electronics and are helpful for elucidating the conducting mechanism of molecular junctions and improving their performance.

PMID:40152302 | DOI:10.1039/d4cp04605f

Sci Prog. 2025 Jan-Mar;108(1):368504251331706. doi: 10.1177/00368504251331706. Epub 2025 Mar 28.

ABSTRACT

BackgroundMonkeypox (mpox) is a zoonotic infectious disease caused by the mpox virus and characterized by painful body lesions, fever, headaches, and exhaustion. Since the report of the first human case of mpox in Africa, there have been multiple outbreaks, even in nonendemic regions of the world. The emergence and re-emergence of mpox highlight the critical need for early detection, which has spurred research into applying deep learning to improve diagnostic capabilities.ObjectiveThis research aims to develop a robust hybrid long short-term memory (LSTM)-convolutional neural network (CNN) model with a Convolutional Block Attention Module (CBAM) to provide a potential tool for the early detection of mpox.MethodsA hybrid LSTM-CNN multi-stream deep learning model with CBAM was developed and trained using the Mpox Skin Lesion Dataset Version 2.0 (MSLD v2.0). We employed LSTM layers for preliminary feature extraction, CNN layers for further feature extraction, and CBAM for feature conditioning. The model was evaluated with standard metrics, and gradient-weighted class activation maps (Grad-CAM) and local interpretable model-agnostic explanations (LIME) were used for interpretability.ResultsThe model achieved an F1-score, recall, and precision of 94%, an area under the curve of 95.04%, and an accuracy of 94%, demonstrating competitive performance compared to the state-of-the-art models. This robust performance highlights the reliability of our model. LIME and Grad-CAM offered insights into the model's decision-making process.ConclusionThe hybrid LSTM-CNN multi-stream deep learning model with CBAM successfully detects mpox, providing a promising early detection tool that can be integrated into web and mobile platforms for convenient and widespread use.

PMID:40152267 | DOI:10.1177/00368504251331706

Bioinformatics. 2025 Mar 27:btaf135. doi: 10.1093/bioinformatics/btaf135. Online ahead of print.

ABSTRACT

MOTIVATION: Advances in bacterial promoter predictors based on ML have greatly improved identification metrics. However, existing models overlooked the impact of negative datasets, previously identified in GC-content discrepancies between positive and negative datasets in single-species models. This study aims to investigate whether multiple-species models for promoter classification are inherently biased due to the selection criteria of negative datasets. We further explore whether the generation of synthetic random sequences (SRS) that mimic GC-content distribution of promoters can partly reduce this bias.

RESULTS: Multiple-species predictors exhibited GC-content bias when using CDS as negative dataset, suggested by specificity and sensibility metrics in a species-specific manner, and investigated by dimensionality reduction. We demonstrated a reduction in this bias by employing the SRS dataset, with less detection of background noise in real genomic data. In both scenarios DNABERT showed the best metrics. These findings suggest that GC-balanced datasets can enhance the generalizability of promoter predictors across Bacteria.

AVAILABILITY AND IMPLEMENTATION: The source code of the experiments is freely available at https://github.com/maigonzalezh/MultispeciesPromoterClassifier.

PMID:40152247 | DOI:10.1093/bioinformatics/btaf135

Bioinformatics. 2025 Mar 27:btaf137. doi: 10.1093/bioinformatics/btaf137. Online ahead of print.

ABSTRACT

MOTIVATION: Single-cell RNA sequencing (scRNA-seq) analysis relies heavily on effective clustering to facilitate numerous downstream applications. Although several machine learning methods have been developed to enhance single-cell clustering, most are fully unsupervised and overlook the rich repository of annotated datasets available from previous single-cell experiments. Since cells are inherently high-dimensional entities, unsupervised clustering can often result in clusters that lack biological relevance. Leveraging annotated scRNA-seq datasets as a reference can significantly enhance clustering performance, enabling the identification of biologically meaningful clusters in target datasets.

RESULTS: In this paper, we propose Single Cell MUlti-Source CLustering (scMUSCL), a novel transfer learning method designed to identify cell clusters in a target dataset by leveraging knowledge from multiple annotated reference datasets. scMUSCL employs a deep neural network to extract domain- and batch-invariant cell representations, effectively addressing discrepancies across various source datasets and between source and target datasets within the new representation space. Unlike existing methods, scMUSCL does not require prior knowledge of the number of clusters in the target dataset and eliminates the need for batch correction between source and target datasets. We conduct extensive experiments using 20 real-life datasets, demonstrating that scMUSCL consistently outperforms existing unsupervised and transfer learning-based methods. Furthermore, our experiments show that scMUSCL benefits from multiple source datasets as learning references and accurately estimates the number of clusters.

AVAILABILITY: The Python implementation of scMUSCL is available at https://github.com/arashkhoeini/scMUSCL.

SUPPLEMENTARY INFORMATION: Supplementary data are available and include additional experimental details, performance evaluations, and implementation guidelines.

PMID:40152244 | DOI:10.1093/bioinformatics/btaf137

J Chem Inf Model. 2025 Mar 28. doi: 10.1021/acs.jcim.5c00004. Online ahead of print.

ABSTRACT

With the breakthroughs in protein structure prediction technology, constructing atomic structures from cryo-electron microscopy (cryo-EM) density maps through structural fitting has become increasingly critical. However, the accuracy of the constructed models heavily relies on the precision of the structure-to-map fitting. In this study, we introduce DEMO-EMfit, a progressive method that integrates deep learning-based backbone map extraction with a global-local structural pose search to fit atomic structures into density maps. DEMO-EMfit was extensively evaluated on a benchmark data set comprising both cryo-electron tomography (cryo-ET) and cryo-EM maps of protein and nucleic acid complexes. The results demonstrate that DEMO-EMfit outperforms state-of-the-art approaches, offering an efficient and accurate tool for fitting atomic structures into density maps.

PMID:40152222 | DOI:10.1021/acs.jcim.5c00004

Plant Cell Environ. 2025 Mar 28. doi: 10.1111/pce.15464. Online ahead of print.

ABSTRACT

Plant stem cells, residing in the shoot and root apical meristems, are fundamental for continuous growth and organ formation throughout the plant life cycle. Their regulation is driven by the convergence of endogenous developmental cues and exogenous environmental signals, making them pivotal to overall plant growth and development. Auxin, a key phytohormone, serves as a major internal signal, orchestrating stem cell initiation, maintenance, differentiation, and environmental adaptation through intricate biosynthesis, transport, and signaling networks. This review summarizes recent progress in understanding the cellular and molecular mechanisms by which auxin guides stem cell functions in both the shoot and root apical meristems. Through these insights, we explore how plants utilize auxin-driven pathways to optimize growth in ever-changing environments.

PMID:40152539 | DOI:10.1111/pce.15464

J Immunol. 2025 Mar 27:vkaf026. doi: 10.1093/jimmun/vkaf026. Online ahead of print.

ABSTRACT

Increased myeloid lineage production, termed myeloid skewing, leading to decreased tumor immunity, is a hallmark of aberrant hematopoiesis associated with cancer. It is believed that myeloid skewing may occur at the hematopoietic stem and progenitor cells (HSPCs) level to elicit hematopoietic changes. However, our understanding of the underlying molecular mechanisms remains incomplete. Here, we characterize the transcriptional and chromatin accessibility landscapes of bone marrow and splenic hematopoietic progenitors in the MMTV-PyMT mouse model of breast cancer using single-cell ATAC + RNA sequencing. We show that HSPCs in the bone marrow (BM) of the tumor-bearing mice show a modest upregulation of the myeloid-bias transcriptional signature without significant chromatin accessibility changes. By contrast, dendritic cell (DC) progenitors exhibit the most prominent transcriptional and chromatin changes, showing a signature of STAT3, CEBP, and non-DC myeloid gene activation. Compared to BM, splenic HSPCs exhibit a Notch signaling signature associated with erythroid commitment rather than further upregulation of the myeloid-bias signature. In addition, we also identify a cluster of splenic HSPCs in tumor-bearing animals with a transcriptional signature of mobilization. Our paired chromatin data suggest that AP-1 factors play a crucial role in driving this HSPC mobilization signature. Overall, we provide a comprehensive dataset for understanding the hematopoietic consequences of cancer.

PMID:40152115 | DOI:10.1093/jimmun/vkaf026