Comput Struct Biotechnol J. 2025 Jan 2;27:265-277. doi: 10.1016/j.csbj.2024.12.030. eCollection 2025.

ABSTRACT

Despite the wealth of single-cell multi-omics data, it remains challenging to predict the consequences of novel genetic and chemical perturbations in the human body. It requires knowledge of molecular interactions at all biological levels, encompassing disease models and humans. Current machine learning methods primarily establish statistical correlations between genotypes and phenotypes but struggle to identify physiologically significant causal factors, limiting their predictive power. Key challenges in predictive modeling include scarcity of labeled data, generalization across different domains, and disentangling causation from correlation. In light of recent advances in multi-omics data integration, we propose a new artificial intelligence (AI)-powered biology-inspired multi-scale modeling framework to tackle these issues. This framework will integrate multi-omics data across biological levels, organism hierarchies, and species to predict genotype-environment-phenotype relationships under various conditions. AI models inspired by biology may identify novel molecular targets, biomarkers, pharmaceutical agents, and personalized medicines for presently unmet medical needs.

PMID:39886532 | PMC:PMC11779603 | DOI:10.1016/j.csbj.2024.12.030

Ophthalmol Sci. 2024 Nov 22;5(2):100658. doi: 10.1016/j.xops.2024.100658. eCollection 2025 Mar-Apr.

ABSTRACT

OBJECTIVE: To quantitatively assess the retinal vascular tortuosity of patients with sickle cell disease (SCD) and retinopathy (SCR) using an automated deep learning (DL)-based pipeline.

DESIGN: Cross-sectional study.

SUBJECTS: Patients diagnosed with SCD and screened for SCR at an academic eye center between January 2015 and November 2022 were identified using electronic health records. Eyes of unaffected matched patients (i.e., no history of SCD, hypertension, diabetes mellitus, or retinal occlusive disorder) served as controls.

METHODS: For each patient, demographic data, sickle cell diagnosis, types and total number of sickle cell crises, SCD medications used, ocular and systemic comorbidities, and history of intraocular treatment were extracted. A previously published DL algorithm was used to calculate retinal microvascular tortuosity using ultrawidefield pseudocolor fundus imaging among patients with SCD vs. controls.

MAIN OUTCOME MEASURES: Cumulative tortuosity index (CTI).

RESULTS: Overall, 64 patients (119 eyes) with SCD and 57 age- and race-matched controls (106 eyes) were included. The majority of the patients with SCD were females (65.6%) and of Black or African descent (78.1%), with an average age of 35.1 ± 20.1 years. The mean number of crises per patient was 3.4 ± 5.2, and the patients took 0.7 ± 0.9 medications. The mean CTI for eyes with SCD was higher than controls (1.06 ± vs. 1.03 ± 0.02, P < 0.001). On subgroup analysis, hemoglobin S, hemoglobin C, and HbS/beta-thalassemia variants had significantly higher CTIs compared with controls (1.07 vs. 1.03, P < 0.001), but not with sickle cell trait variant (1.04 vs. 1.03 control, P = .2). Univariable analysis showed a higher CTI in patients diagnosed with proliferative SCR, most significantly among those with sea-fan neovascularization (1.06 ± 0.02 vs. 1.04 ± 0.01, P < 0.001) and those with >3 sickle cell crises (1.07 ± 0.02 vs. 1.05 ± 0.02, P < 0.001).

CONCLUSIONS: A DL-based metric of cumulative vascular tortuosity associates with and may be a potential biomarker for SCD and SCR disease severity.

FINANCIAL DISCLOSURES: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

PMID:39886358 | PMC:PMC11780102 | DOI:10.1016/j.xops.2024.100658

JACC Asia. 2024 Dec 10;5(1):88-98. doi: 10.1016/j.jacasi.2024.10.012. eCollection 2025 Jan.

ABSTRACT

BACKGROUND: Heart failure should be diagnosed as early as possible. Although deep learning models can predict one or more echocardiographic findings from electrocardiograms (ECGs), such analyses are not comprehensive.

OBJECTIVES: This study aimed to develop a deep learning model for comprehensive prediction of echocardiographic findings from ECGs.

METHODS: We obtained 229,439 paired ECG and echocardiography data sets from 8 centers. Six centers contributed to model development and 2 to external validation. We identified 12 echocardiographic findings related to left-sided cardiac abnormalities, valvular heart diseases, and right-sided cardiac abnormalities. These findings were predicted using convolutional neural networks, and a composite label was analyzed using logistic regression. A positive composite label indicated positivity in any of the 12 findings.

RESULTS: For the composite findings label, the area under the receiver-operating characteristic curve was 0.80 (95% CI: 0.80-0.81) on hold-out validation and 0.78 (95% CI: 0.78-0.79) on external validation. The composite findings label applying logistic regression had an area under the receiver-operating characteristic curve of 0.80 (95% CI: 0.80-0.81) with accuracy of 73.8% (95% CI: 73.2-74.4), sensitivity of 81.1% (95% CI: 80.5-81.8), and specificity of 60.7% (95% CI: 59.6-61.8).

CONCLUSIONS: We have developed convolutional neural network models that predict a wide range of echocardiographic findings, including left-sided cardiac abnormalities, valvular heart diseases, and right-sided cardiac abnormalities from ECGs and created a model to predict a composite findings label by logistic regression analysis. This model has potential to serve as an adjunct for early diagnosis and treatment of previously undetected cardiac disease.

PMID:39886205 | PMC:PMC11775793 | DOI:10.1016/j.jacasi.2024.10.012

JACC Asia. 2025 Jan 7;5(1):99-100. doi: 10.1016/j.jacasi.2024.11.017. eCollection 2025 Jan.

NO ABSTRACT

PMID:39886196 | PMC:PMC11775781 | DOI:10.1016/j.jacasi.2024.11.017

Phys Imaging Radiat Oncol. 2024 Dec 28;33:100694. doi: 10.1016/j.phro.2024.100694. eCollection 2025 Jan.

ABSTRACT

BACKGROUND AND PURPOSE: Daily magnetic resonance image (MRI)-guided radiotherapy plan adaptation requires time-consuming manual contour edits of targets and organs at risk in the online workflow. Recent advances in auto-segmentation promise to deliver high-quality delineations within a short time frame. However, the actual time benefit in a clinical setting is unknown. The current study investigated the feasibility and time gain of implementing online artificial intelligence (AI)-based delineations at a 1.5 T MRI-Linac.

MATERIALS AND METHODS: Fifteen consecutive prostate cancer patients, treated to 60 Gy in 20 fractions at a 1.5 T MRI-Linac, were included in the study. The first 5 patients (Group 1) were treated using the standard contouring workflow for all fractions. The last 10 patients (Group 2) were treated with the standard workflow for fractions 1 up to 3 (Group 2 - Standard) and an AI-based workflow for the remaining fractions (Group 2 - AI). AI delineations were delivered using an in-house developed AI inference service and an in-house trained nnU-Net.

RESULTS: The AI-based workflow reduced delineation time from 9.8 to 5.3 min. The variance in delineation time seemed to increase during the treatment course for Group 1, while the delineation time for the AI-based workflow was constant (Group 2 - AI). Fewer occurrences of readaptation due to target movement occurred with the AI-based workflow.

CONCLUSION: Implementing an AI-based workflow at the 1.5 T MRI-Linac is feasible and reduces the delineation time. Lower variance in delineation duration supports a better ability to plan daily treatment schedules and avoids delays.

PMID:39885904 | PMC:PMC11780162 | DOI:10.1016/j.phro.2024.100694

BMC Pharmacol Toxicol. 2025 Jan 30;26(1):23. doi: 10.1186/s40360-025-00856-9.

ABSTRACT

PURPOSE: This study aims to assess the risks associated with drug-induced macular edema and to examine the epidemiological characteristics of this condition.

METHODS: This study analyzed data from the U.S. Food and Drug Administration (FDA) Adverse Event Reporting System (FAERS) database from January 2004 to June 2024 to conduct a disproportionality analysis identifying drugs with positive signals of drug-induced ME. Additionally, the onset time of ME associated with these drugs was examined.

RESULTS: In the FAERS database, a total of 490 drugs were reported to pose a risk of drug-induced ME. Disproportional analysis and screening further identified 8 drugs that significantly increased this risk. Among these, one is ophthalmic drugs, including Latanoprost (ROR = 5.51), and ten are non-ophthalmic drugs, including Cefuroxime (ROR = 75.93), Fingolimod (ROR = 30.69), and Siponimod (ROR = 20.51).

CONCLUSIONS: This study utilizes the FAERS database to investigate potential associations between drug use and the occurrence of ME, rapidly identify drugs that may induce the condition, and propose research strategies. These findings hold significant value for guiding clinical medication practices.

PMID:39885611 | DOI:10.1186/s40360-025-00856-9

Plant Mol Biol. 2025 Jan 31;115(1):29. doi: 10.1007/s11103-025-01558-w.

ABSTRACT

The applicability of a deep learning model for the virtual staining of plant cell structures using bright-field microscopy was investigated. The training dataset consisted of microscopy images of tobacco BY-2 cells with the plasma membrane stained with the fluorescent dye PlasMem Bright Green and the cell nucleus labeled with Histone-red fluorescent protein. The trained models successfully detected the expansion of cell nuclei upon aphidicolin treatment and a decrease in the cell aspect ratio upon propyzamide treatment, demonstrating its utility in cell morphometry. The model also accurately documented the shape of Arabidopsis pavement cells in both wild type and the bpp125 triple mutant, which has an altered pavement cell phenotype. Metrics such as cell area, circularity, and solidity obtained from virtual staining analyses were highly correlated with those obtained by manual measurements of cell features from microscopy images. Furthermore, the versatility of virtual staining was highlighted by its application to track chloroplast movement in Egeria densa. The method was also effective for classifying live and dead BY-2 cells using texture-based machine learning, suggesting that virtual staining can be applied beyond typical segmentation tasks. Although this method still has some limitations, its non-invasive nature and efficiency make it highly suitable for label-free, dynamic, and high-throughput analyses in quantitative plant cell biology.

PMID:39885095 | DOI:10.1007/s11103-025-01558-w

J Imaging Inform Med. 2025 Jan 30. doi: 10.1007/s10278-025-01423-8. Online ahead of print.

ABSTRACT

Adenoid hypertrophy, characterized by the abnormal enlargement of adenoid tissue, is a condition that can cause significant breathing and sleep disturbances, particularly in children. Accurate diagnosis of adenoid hypertrophy is critical, yet traditional methods, such as imaging and manual interpretation, are prone to errors. This study uses an ensemble deep learning-based approach for adenoid classification. It utilizes a unique dataset sourced from Batman Training and Research Hospital. The dataset is composed of masked and non-masked X-ray images. It is used to train and compare the performance of multiple convolutional neural network (CNN) models. By comparing classification accuracy between masked and non-masked datasets, the study reveals the importance of image preprocessing. Six deep learning models-EfficientNet, MobileNet, ResNet50, ResNet152, VGG16, and Xception-are tested, with ResNet50 achieving the highest accuracy (100% on masked images), while Xception performs the worst (65% F1-score). The results indicate that masking significantly enhances the accuracy and reliability of adenoid classification. ResNet50 and EfficientNet show strong generalization capabilities. Conversely, the lower performance of models like Xception highlights the variability in model suitability for this task. This research provides valuable insights into optimizing deep learning models for medical image classification and it advances the field of AI-based adenoid detection.

PMID:39885079 | DOI:10.1007/s10278-025-01423-8

Clin Neuroradiol. 2025 Jan 30. doi: 10.1007/s00062-025-01498-4. Online ahead of print.

ABSTRACT

PURPOSE: Myocardial injury, indicated by an elevation of high-sensitive cardiac Troponin (hs-cTnT), is a frequent stroke-related complication. Most studies investigated patients with ischemic stroke, but only little is known about its occurrence in patients with intracerebral hemorrhage (ICH). This study aimed to assess the frequency, predictors, and implications of myocardial injury in ICH patients.

METHODS: Our retrospective analysis included 322 ICH patients. We defined myocardial injury as an elevation of hs-cTnT above the 99th percentile (i.e. 14 ng/L). Acute myocardial injury was defined as either a changing pattern of > 50% within 24 h or an excessive elevation of initial hs-cTnT (> 52 ng/L). 3D brain scans were assessed for ICH visually and quantitatively by a deep learning algorithm. Multiple regression models and Voxel-based Lesion-Symptom Mapping (VLSM) were applied.

RESULTS: 63.0% (203/322) of patients presented with myocardial injury, which was associated with more severe strokes and worse outcomes during the in-hospital phase (P < 0.01). Acute myocardial injury occurred in 24.5% (79/322) of patients. The only imaging finding associated with acute myocardial injury was midline shift (69.8% vs. 44.6% for normal or stable hs-cTnT, P < 0.01), which also independently predicted it (odds ratio 3.29, confidence interval 1.38-7.87, P < 0.01). In contrast, VLSM did not identify any specific brain region significantly associated with acute myocardial injury. Acute myocardial injury did not correlate with preexisting cardiac diseases; however, the frequency of adverse cardiac events was higher in the acute myocardial injury group (11.4% vs. 4.1% in patients with normal and/or stable patterns of hs-cTnT, P < 0.05).

CONCLUSION: Myocardial injury occurs frequently in ICH and is linked to poor outcomes. Acute myocardial injury primarily correlates to space-occupying effects of ICH but is less dependent on premorbid cardiac status. Nonetheless, it is associated with a higher rate of adverse cardiac events.

PMID:39884976 | DOI:10.1007/s00062-025-01498-4

J Transl Med. 2025 Jan 30;23(1):133. doi: 10.1186/s12967-024-06015-8.

ABSTRACT

BACKGROUND: Psoriasis is a common chronic, recurrent, immune-mediated disease involved in the skin or joints or both. However, deeper insight into the genetic susceptibility of psoriasis is still unclear.

METHODS: Here we performed the largest multi-ancestry meta-analysis of genome-wide association study including 28,869 psoriasis cases and 443,950 healthy controls.

RESULTS: We identified 74 genome-wide significant loci for psoriasis. Of 74 loci, 32 were novel psoriasis risk loci. Across 74 loci, 801 likely causal genes are indicated and 164 causal genes are prioritized. SNP-based heritability analyses demonstrated that common variants explain 15% of genetic risk for psoriasis. Gene-set analyses and the genetic correlation revealed that psoriasis-related genes have the positive correlations with autoimmune diseases such as ulcerative colitis, inflammatory bowel diseases, and Crohn's disease. Gene-drug interaction analysis suggested that psoriasis-associated genes overlapped with targets of current medications for psoriasis. Finally, we used the multi-ancestry meta-analysis to explore drug repurposing and the potential targets for psoriasis.

CONCLUSIONS: We identified 74 genome-wide significant loci for psoriasis. Based on 74 loci, we provided new biological insights to the etiology of psoriasis. Of clinical interest, we gave some hints for 76 potential targets and drug repurposing for psoriasis.

PMID:39885523 | DOI:10.1186/s12967-024-06015-8

Mol Cell Proteomics. 2025 Jan 28:100919. doi: 10.1016/j.mcpro.2025.100919. Online ahead of print.

ABSTRACT

Understanding dysregulated genes and pathways in cancer is critical for precision oncology. Integrating mass spectrometry-based proteomic data with transcriptomic data presents unique opportunities for systematic analyses of dysregulated genes and pathways in pan-cancer. Here, we compiled a comprehensive set of datasets, encompassing proteomic data from 2,404 samples and transcriptomic data from 7,752 samples across 13 cancer types. Comparisons between normal or adjacent normal tissues (ANTs) and tumor tissues identified several dysregulated pathways including mRNA splicing, interferon pathway, fatty acid metabolism, and complement coagulation cascade in pan-cancer. Additionally, pan-cancer up- and down-regulated genes (PCUGs and PCDGs) were also identified. Notably, RRM2 and ADH1B, two genes belong to PCUGs and PCDGs, respectively, were identified as robust pan-cancer diagnostic biomarkers. TNM stage-based comparisons revealed dysregulated genes and biological pathways involved in cancer progression, among which the dysregulation of complement coagulation cascade and epithelial-mesenchymal transition are frequent in multiple types of cancers. A group of pan-cancer continuously up- and down-regulated proteins in different tumor stages (PCCUPs and PCCDPs) were identified. We further constructed prognostic risk stratification models for corresponding cancer types based on dysregulated genes, which effectively predict the prognosis for patients with these cancers. Drug prediction based on PCUPs and PCDPs as well as PCCUPs and PCCDPs revealed that small molecule inhibitors targeting CDK, HDAC, MEK, JAK, PI3K, and others might be effective treatments for pan-cancer, thereby supporting drug repurposing. We also developed web tools for cancer diagnosis, pathologic stage assessment, and risk evaluation. Overall, this study highlights the power of combining proteomic and transcriptomic data to identify valuable diagnostic and prognostic markers as well as drug targets and treatments for cancer.

PMID:39884577 | DOI:10.1016/j.mcpro.2025.100919

Pharmacol Res. 2025 Jan 28:107633. doi: 10.1016/j.phrs.2025.107633. Online ahead of print.

ABSTRACT

There is an urgent need for mechanistically novel and more efficacious treatments for schizophrenia, especially those targeting negative and cognitive symptoms with a more favorable side-effect profile. Drug repurposing-the process of identifying new therapeutic uses for already approved compounds-offers a promising approach to overcoming the lengthy, costly, and high-risk process of traditional CNS drug discovery. This review aims to update our previous findings on the clinical drug repurposing pipeline in schizophrenia. We examined studies conducted between 2018 and 2024, identifying 61 trials evaluating 40 unique repurposed drug candidates. These encompassed a broad range of pharmacological mechanisms, including immunomodulation, cognitive enhancement, and hormonal, metabolic, and neurotransmitter modulation. A notable development is the combination of the muscarinic modulators xanomeline, a compound with antipsychotic properties, and trospium, included to mitigate peripheral side effects, now approved by the FDA as the first antipsychotic drug in decades with a fundamentally novel mechanism of action. Moving beyond the traditional dopaminergic paradigm of schizophrenia, such findings highlight opportunities to improve treatment-resistant symptoms and alleviate adverse effects. Overall, the evolving drug repurposing landscape illustrates a significant shift in the rationale for schizophrenia drug development, highlighting the potential of in silico strategies, biomarker-based patient stratification, and personalized treatments that align with underlying pathophysiological processes.

PMID:39884448 | DOI:10.1016/j.phrs.2025.107633

Comput Biol Med. 2025 Jan 29;187:109729. doi: 10.1016/j.compbiomed.2025.109729. Online ahead of print.

ABSTRACT

Precision medicine aims to provide personalized therapies by analyzing patient molecular profiles, often focusing on gene expression data. However, effectively linking these data to actionable drug discovery for clinical application remains challenging. In this paper, we introduce ExPDrug, a neural network (NN) model that integrates biological pathways from transcriptomic data with a biomedical knowledge graph to facilitate pathway-based drug repurposing. ExPDrug enhances disease phenotype prediction by capturing the complex relationships between genes and pathways. Using layer-wise relevance propagation (LRP), the model interprets the contribution of each pathway using relevance scores applied in a random walk-with-restart (RWR) algorithm to prioritize potential drug candidates in the biomedical network. ExPDrug outperforms existing methods in predicting phenotypes for the three diseases and identifying drug candidates, as supported by the literature. This model offers a transformative approach for advancing precision medicine by linking transcriptomic insights directly to clinical drug repurposing, thereby potentially improving treatment strategies for complex diseases.

PMID:39884058 | DOI:10.1016/j.compbiomed.2025.109729

Drug Metab Dispos. 2025 Jan;53(1):100011. doi: 10.1124/dmd.124.001923. Epub 2024 Nov 22.

ABSTRACT

Many factors cause interperson variability in the activity and expression of the cytochrome P450 (CYP) drug-metabolizing enzymes in the liver, leading to variable drug exposure and treatment outcomes. Several liver-enriched transcription factors are associated with CYP expression, with estrogen receptor α (ESR1) and constitutive androstane receptor (CAR or NR1I3) being the 2 top factors. ESR1 and NR1I3 undergo extensive alternative splicing that results in numerous splice isoforms, but how these splice isoforms associate with CYP expression is unknown. Here, we quantified 18 NR1I3 splice isoforms and the 3 most abundant ESR1 isoforms in 260 liver samples derived from African Americans (n = 125) and European Americans (n = 135). Our results showed variable splice isoform populations in the liver for both NR1I3 and ESR1. Multiple linear regression analyses revealed that compared with gene-level NR1I3, isoform-level NR1I3 expression better predicted the mRNA expression of most CYPs and 3 UDP-glucuronosyltransferases (UGTs), whereas ESR1 isoforms improved predictive models for the UGTs and CYP2D6 but not for most CYPs. Also, different NR1I3 isoforms were associated with different CYPs, and the associations varied depending on sample ancestry. Surprisingly, noncanonical NR1I3 isoforms having retained introns (introns 2 or 6) were abundantly expressed and associated with the expression of most CYPs and UGTs, whereas the reference isoform (NR1I3-205) was only associated with CYP2D6. Moreover, NR1I3 isoform diversity increased during the differentiation of induced pluripotent stem cells to hepatocytes, paralleling increasing CYP expression. These results suggest that isoform-level transcription factor expression may help to explain variation in CYP or UGT expression between individuals. SIGNIFICANCE STATEMENT: We quantified 18 NR1I3 splice isoforms and the 3 most abundant ESR1 splice isoforms in 260 liver samples derived from African American and European American donors and found variable NR1I3 and ESR1 splice isoform expression in the liver. Multiple linear regression analysis showed that, compared with gene-level expression, isoform-level expression of NR1I3 and ESR1 better predicted the mRNA expression of some cytochrome P450s and UDP-glucuronosyltransferases, highlighting the importance of isoform-level analyses to enhance our understanding of gene transcriptional regulatory networks controlling the expression of drug-metabolizing enzymes.

PMID:39884819 | DOI:10.1124/dmd.124.001923

Drug Metab Dispos. 2025 Jan;53(1):100023. doi: 10.1124/dmd.124.001916. Epub 2024 Nov 23.

ABSTRACT

Remimazolam (Byfavo, Acacia Pharma), a recent Food and Drug Administration-approved ester-linked benzodiazepine, offers advantages in sedation, such as rapid onset and predictable duration, making it suitable for broad anesthesia applications. Its favorable pharmacological profile is primarily attributed to rapid hydrolysis, the primary metabolism pathway for its deactivation. Thus, understanding remimazolam hydrolysis determinants is essential for optimizing its clinical use. This study aimed to identify the enzyme(s) and tissue(s) responsible for remimazolam hydrolysis and to evaluate the influence of genetic polymorphisms and drug-drug interactions on its hydrolysis in the human liver. An initial incubation study with remimazolam and PBS, human serum, and the S9 fractions of human liver and intestine demonstrated that remimazolam was exclusively hydrolyzed by human liver S9 fractions. Subsequent incubation studies utilizing a carboxylesterase inhibitor (bis(4-nitrophenyl) phosphate), recombinant human carboxylesterase 1 (CES1) and carboxylesterase 2 confirmed that remimazolam is specifically hydrolyzed by CES1 in human liver. Furthermore, in vitro studies with wild-type CES1 and CES1 variants transfected cells revealed that certain genetic polymorphisms significantly impair remimazolam deactivation. Notably, the impact of CES1 G143E was verified using individual human liver samples. Moreover, our evaluation of the drug-drug interactions between remimazolam and several other substrates/inhibitors of CES1-including simvastatin, enalapril, clopidogrel, and sacubitril-found that clopidogrel significantly inhibited remimazolam hydrolysis at clinically relevant concentrations, with CES1 genetic variants potentially influencing the interactions. In summary, CES1 genetic variants and its interacting drugs are crucial factors contributing to interindividual variability in remimazolam hepatic hydrolysis, holding the potential to serve as biomarkers for optimizing remimazolam use. SIGNIFICANCE STATEMENT: This investigation demonstrates that remimazolam is deactivated by carboxylesterase 1 (CES1) in the human liver, with CES1 genetic variants and drug-drug interactions significantly influencing its metabolism. These findings emphasize the need to consider CES1 genetic variability and potential drug-drug interactions in remimazolam use, especially in personalized pharmacotherapy to achieve optimal anesthetic outcomes.

PMID:39884809 | DOI:10.1124/dmd.124.001916

Sci Rep. 2025 Jan 30;15(1):3738. doi: 10.1038/s41598-025-86515-9.

ABSTRACT

Pyomelanogenic P. aeruginosa, frequently isolated from patients with urinary tract infections and cystic fibrosis, possesses the ability to withstand oxidative stress, contributing to virulence and resulting in persistent infections. Whole genome sequence analysis of U804, a pyomelanogenic, multidrug-resistant, clinical isolate, demonstrates the mechanism underlying pyomelanin overproduction. Seven essential oils (EOs) were screened for pyomelanin inhibition. Garlic, cinnamon and thyme EOs were selected for further studies based on their significant anti-virulent properties, like inhibition of pyomelanin production and biofilm formation. Additionally, downregulation of the expression of virulence genes regulated by quorum sensing (QS) and a decrease in levels of the QS signaling molecule, C12-HSL, were also observed. The EO treatment inhibited the survival of U804 in human blood and increased survival of C. elegans, a whole animal model of pathogenesis. EO treatment also resulted in a significant reduction of efflux pump activity, indicative of their effect on antibiotic sensitization. Garlic oil enhanced the permeability of the bacterial membrane, resulting in decreased survival, when combined with sub-MIC concentrations of colistin. This study demonstrates that thyme, cinnamon and garlic EOs can attenuate pyomelanogenic P. aeruginosa virulence traits. Additionally, garlic potentiates drug sensitivity, suggesting its promising therapeutic use in combating pyomelanogenic MDR infections.

PMID:39885214 | DOI:10.1038/s41598-025-86515-9

J Cyst Fibros. 2025 Jan 29:S1569-1993(25)00007-4. doi: 10.1016/j.jcf.2025.01.008. Online ahead of print.

ABSTRACT

BACKGROUND: People with cystic fibrosis (CF) are recommended to wear face-masks when in healthcare settings. We previously demonstrated that face-masks significantly reduce the release of Pseudomonas aeruginosa (P. aeruginosa) aerosols during coughing in adults with CF. There is a knowledge gap in relation to the impact of mask wear in children with CF. This study aimed to examine the tolerability and effectiveness in lowering emissions of hospital-grade surgical and one type of commercially available cotton face-mask in children with CF.

METHODS: Twenty children with CF and P. aeruginosa infection were recruited. Participants performed three cough manoeuvres in a validated cough aerosol system both with and without face-masks of differing wear time. Cough aerosols were sampled at two meters using an Andersen Cascade Impactor. Quantitative sputum and aerosol bacterial cultures were performed. Participants also rated the comfort levels of the face-masks.

RESULTS: P. aeruginosa was cultured from the sputum in eight participants (40 %). During uncovered coughing (reference manoeuvre), seven of the 20 participants produced aerosols containing bacterial pathogens. There was a reduction in aerosolised bacterial load during coughing with both surgical and cotton face-masks. The mean percent reduction in CFU with both types of face-masks was 82 % (95 % CI 56 - 108) during the immediate face-mask wear test compared to the uncovered cough test. Face-masks were generally well tolerated.

CONCLUSIONS: Face-masks are well tolerated and effective in reducing cough-generated bacterial aerosols in children with CF.

PMID:39884883 | DOI:10.1016/j.jcf.2025.01.008

BMJ Open Respir Res. 2025 Jan 30;12(1):e002522. doi: 10.1136/bmjresp-2024-002522.

ABSTRACT

BACKGROUND: Cystic fibrosis (CF) is associated with a historically high treatment burden which causes anxiety and exhaustion for parents of children with CF, especially in the early years of a child's life. Recently, a new medication, elexacaftor/tezacaftor/ivacaftor (ETI), has become available to some people with CF, which has had a significant impact on the quality of life of older children and adults. This medication will soon be available for children ages 2-5 in the UK. This study investigated parents' perspectives before their children could start ETI.

METHOD: 10 parents of young children with CF participated in semistructured online focus groups. The data were analysed using thematic analysis to identify key themes.

RESULTS: Three reviewers identified four main themes: (1) The 'roller coaster' of parental emotions: Shock, hope, uncertainty and anticipation, (2) The dark side of the unknown, side effects and burden of decision making, (3) The value of simple pleasures in a life with CF; treatment burden, normality, future, family life and (4) Reforming clinical care in the new era of CF care; support, communication and the future.

CONCLUSION: Parents experience a range of emotions from the day of diagnosis. While ETI brings hope and positivity, parents are concerned about the medication's safety. Parents have clear hopes and wishes for their child's future and reflect on the need for clinicians to consider reforming clinical care in the new era of CF for those eligible for new therapies.

PMID:39884719 | DOI:10.1136/bmjresp-2024-002522

BioData Min. 2025 Jan 30;18(1):11. doi: 10.1186/s13040-025-00425-0.

ABSTRACT

BACKGROUND: This study employs a LSTM-FC neural networks to address the critical public health issue of child undernutrition in Ethiopia. By employing this method, the study aims classify children's nutritional status and predict transitions between different undernutrition states over time. This analysis is based on longitudinal data extracted from the Young Lives cohort study, which tracked 1,997 Ethiopian children across five survey rounds conducted from 2002 to 2016. This paper applies rigorous data preprocessing, including handling missing values, normalization, and balancing, to ensure optimal model performance. Feature selection was performed using SHapley Additive exPlanations to identify key factors influencing nutritional status predictions. Hyperparameter tuning was thoroughly applied during model training to optimize performance. Furthermore, this paper compares the performance of LSTM-FC with existing baseline models to demonstrate its superiority. We used Python's TensorFlow and Keras libraries on a GPU-equipped system for model training.

RESULTS: LSTM-FC demonstrated superior predictive accuracy and long-term forecasting compared to baseline models for assessing child nutritional status. The classification and prediction performance of the model showed high accuracy rates above 93%, with perfect predictions for Normal (N) and Stunted & Wasted (SW) categories, minimal errors in most other nutritional statuses, and slight over- or underestimations in a few instances. The LSTM-FC model demonstrates strong generalization performance across multiple folds, with high recall and consistent F1-scores, indicating its robustness in predicting nutritional status. We analyzed the prevalence of children's nutritional status during their transition from late adolescence to early adulthood. The results show a notable decline in normal nutritional status among males, decreasing from 58.3% at age 5 to 33.5% by age 25. At the same time, the risk of severe undernutrition, including conditions of being underweight, stunted, and wasted (USW), increased from 1.3% to 9.4%.

CONCLUSIONS: The LSTM-FC model outperforms baseline methods in classifying and predicting Ethiopian children's nutritional statuses. The findings reveal a critical rise in undernutrition, emphasizing the need for urgent public health interventions.

PMID:39885567 | DOI:10.1186/s13040-025-00425-0

BMC Bioinformatics. 2025 Jan 30;26(1):34. doi: 10.1186/s12859-024-06008-w.

ABSTRACT

BACKGROUND: Biomedical text mining is a technique that extracts essential information from scientific articles using named entity recognition (NER). Traditional NER methods rely on dictionaries, rules, or curated corpora, which may not always be accessible. To overcome these challenges, deep learning (DL) methods have emerged. However, DL-based NER methods may need help identifying long-distance relationships within text and require significant annotated datasets.

RESULTS: This research has proposed a novel model to address the challenges in natural language processing. The Improved Green anaconda-assisted Bi-GRU based Hierarchical ResNet BNER model (IGa-BiHR BNERM) is the model. IGa-BiHR BNERM model has shown promising results in accurately identifying named entities. The MACCROBAT dataset was obtained from Kaggle and underwent several pre-processing steps such as Stop Word Filtering, WordNet processing, Removal of non-alphanumeric characters, stemming Segmentation, and Tokenization, which is standardized and improves its quality. The pre-processed text was fed into a feature extraction model like the Robustly Optimized BERT -Whole Word Masking model. This model provides word embeddings with semantic information. Then, the BNER process utilized an Improved Green Anaconda-assisted Bi-GRU-based Hierarchical ResNet BNER model (IGa-BiHR BNERM).

CONCLUSION: To improve the training phase of the IGa-BiHR BNERM, the Improved Green Anaconda Optimization technique was used to select optimal weight parameter coefficients for training the model parameters. After the model was tested using the MACCROBAT dataset, it outperformed previous models with a tremendous accuracy rate of 99.11%. This model effectively and accurately identifies biomedical names within the text, significantly advancing this field.

PMID:39885428 | DOI:10.1186/s12859-024-06008-w