Eur J Radiol Open. 2024 Dec 19;14:100626. doi: 10.1016/j.ejro.2024.100626. eCollection 2025 Jun.

ABSTRACT

OBJECTIVE: Immunotherapy has become an option for the first-line therapy of advanced gastric cancer (GC), with improved survival. Our study aimed to investigate unresectable GC from an imaging perspective combined with clinicopathological variables to identify patients who were most likely to benefit from immunotherapy.

METHOD: Patients with unresectable GC who were consecutively treated with immunotherapy at two different medical centers of Chinese PLA General Hospital were included and divided into the training and validation cohorts, respectively. A deep learning neural network, using a multimodal ensemble approach based on CT imaging data before immunotherapy, was trained in the training cohort to predict survival, and an internal validation cohort was constructed to select the optimal ensemble model. Data from another cohort were used for external validation. The area under the receiver operating characteristic curve was analyzed to evaluate performance in predicting survival. Detailed clinicopathological data and peripheral blood prior to immunotherapy were collected for each patient. Univariate and multivariable logistic regression analysis of imaging models and clinicopathological variables was also applied to identify the independent predictors of survival. A nomogram based on multivariable logistic regression was constructed.

RESULT: A total of 79 GC patients in the training cohort and 97 patients in the external validation cohort were enrolled in this study. A multi-model ensemble approach was applied to train a model to predict the 1-year survival of GC patients. Compared to individual models, the ensemble model showed improvement in performance metrics in both the internal and external validation cohorts. There was a significant difference in overall survival (OS) among patients with different imaging models based on the optimum cutoff score of 0.5 (HR = 0.20, 95 % CI: 0.10-0.37, P < 0.001). Multivariate Cox regression analysis revealed that the imaging models, PD-L1 expression, and lung immune prognostic index were independent prognostic factors for OS. We combined these variables and built a nomogram. The calibration curves showed that the C-index of the nomogram was 0.85 and 0.78 in the training and validation cohorts.

CONCLUSION: The deep learning model in combination with several clinical factors showed predictive value for survival in patients with unresectable GC receiving immunotherapy.

PMID:39807092 | PMC:PMC11728962 | DOI:10.1016/j.ejro.2024.100626

Math Biosci Eng. 2024 Dec 11;21(12):7830-7853. doi: 10.3934/mbe.2024344.

ABSTRACT

The hippocampus is a small, yet intricate seahorse-shaped tiny structure located deep within the brain's medial temporal lobe. It is a crucial component of the limbic system, which is responsible for regulating emotions, memory, and spatial navigation. This research focuses on automatic hippocampus segmentation from Magnetic Resonance (MR) images of a human head with high accuracy and fewer false positive and false negative rates. This segmentation technique is significantly faster than the manual segmentation methods used in clinics. Unlike the existing approaches such as UNet and Convolutional Neural Networks (CNN), the proposed algorithm generates an image that is similar to a real image by learning the distribution much more quickly by the semi-supervised iterative learning algorithm of the Deep Neuro-Fuzzy (DNF) technique. To assess its effectiveness, the proposed segmentation technique was evaluated on a large dataset of 18,900 images from Kaggle, and the results were compared with those of existing methods. Based on the analysis of results reported in the experimental section, the proposed scheme in the Semi-Supervised Deep Neuro-Fuzzy Iterative Learning System (SS-DNFIL) achieved a 0.97 Dice coefficient, a 0.93 Jaccard coefficient, a 0.95 sensitivity (true positive rate), a 0.97 specificity (true negative rate), a false positive value of 0.09 and a 0.08 false negative value when compared to existing approaches. Thus, the proposed segmentation techniques outperform the existing techniques and produce the desired result so that an accurate diagnosis is made at the earliest stage to save human lives and to increase their life span.

PMID:39807055 | DOI:10.3934/mbe.2024344

Curr Med Imaging. 2025 Jan 9. doi: 10.2174/0115734056326685250101113959. Online ahead of print.

ABSTRACT

OBJECTIVE: The objective of this research is to enhance pneumonia detection in chest X-rays by leveraging a novel hybrid deep learning model that combines Convolutional Neural Networks (CNNs) with modified Swin Transformer blocks. This study aims to significantly improve diagnostic accuracy, reduce misclassifications, and provide a robust, deployable solution for underdeveloped regions where access to conventional diagnostics and treatment is limited.

METHODS: The study developed a hybrid model architecture integrating CNNs with modified Swin Transformer blocks to work seamlessly within the same model. The CNN layers perform initial feature extraction, capturing local patterns within the images. At the same time, the modified Swin Transformer blocks handle long-range dependencies and global context through window-based self-attention mechanisms. Preprocessing steps included resizing images to 224x224 pixels and applying Contrast Limited Adaptive Histogram Equalization (CLAHE) to enhance image features. Data augmentation techniques, such as horizontal flipping, rotation, and zooming, were utilized to prevent overfitting and ensure model robustness. Hyperparameter optimization was conducted using Optuna, employing Bayesian optimization (Tree-structured Parzen Estimator) to fine-tune key parameters of both the CNN and Swin Transformer components, ensuring optimal model performance.

RESULTS: The proposed hybrid model was trained and validated on a dataset provided by the Guangzhou Women and Children's Medical Center. The model achieved an overall accuracy of 98.72% and a loss of 0.064 on an unseen dataset, significantly outperforming a baseline CNN model. Detailed performance metrics indicated a precision of 0.9738 for the normal class and 1.0000 for the pneumonia class, with an overall F1-score of 0.9872. The hybrid model consistently outperformed the CNN model across all performance metrics, demonstrating higher accuracy, precision, recall, and F1-score. Confusion matrices revealed high sensitivity and specificity with minimal misclassifications.

CONCLUSION: The proposed hybrid CNN-ViT model, which integrates modified Swin Transformer blocks within the CNN architecture, provides a significant advancement in pneumonia detection by effectively capturing both local and global features within chest X-ray images. The modifications to the Swin Transformer blocks enable them to work seamlessly with the CNN layers, enhancing the model's ability to understand complex visual patterns and dependencies. This results in superior classification performance. The lightweight design of the model eliminates the need for extensive hardware, facilitating easy deployment in resource-constrained settings. This innovative approach not only improves pneumonia diagnosis but also has the potential to enhance patient outcomes and support healthcare providers in underdeveloped regions. Future research will focus on further refining the model architecture, incorporating more advanced image processing techniques, and exploring explainable AI methods to provide deeper insights into the model's decision-making process.

PMID:39806960 | DOI:10.2174/0115734056326685250101113959

New Phytol. 2025 Jan 14. doi: 10.1111/nph.20384. Online ahead of print.

ABSTRACT

Lupins are promising protein crops that accumulate toxic quinolizidine alkaloids (QAs) in the seeds, complicating their end-use. QAs are synthesized in green organs (leaves, stems, and pods) and a subset of them is transported to the seeds during fruit development. The exact sites of biosynthesis and accumulation remain unknown; however, mesophyll cells have been proposed as sources, and epidermal cells as sinks. We investigated the exact sites of QA biosynthesis and accumulation in biosynthetic organs of narrow-leafed lupin (Lupinus angustifolius) using mass spectrometry-based imaging (MSI), laser-capture microdissection coupled to RNA-Seq, and precursor feeding studies coupled to LC-MS and MSI. We found that the QAs that accumulate in seeds ('core' QAs) were evenly distributed across tissues; however, their esterified versions accumulated primarily in the epidermis. Surprisingly, RNA-Seq revealed strong biosynthetic gene expression in the epidermis, which was confirmed in leaves by quantitative real-time polymerase chain reaction. Finally, feeding studies using a stably labeled precursor showed that the lower leaf epidermis is highly biosynthetic. Our results indicate that the epidermis is a major site of QA biosynthesis in narrow-leafed lupin, challenging the current assumptions. Our work has direct implications for the elucidation of the QA biosynthesis pathway and the long-distance transport network from source to seed.

PMID:39807565 | DOI:10.1111/nph.20384

Comput Struct Biotechnol J. 2024 Mar 1;23:1076-1087. doi: 10.1016/j.csbj.2024.02.019. eCollection 2024 Dec.

ABSTRACT

DNA holds immense potential as an emerging data storage medium. However, the recovery of information in DNA storage systems faces challenges posed by various errors, including IDS errors, strand breaks, and rearrangements, inevitably introduced during synthesis, amplification, sequencing, and storage processes. Sequence reconstruction, crucial for decoding, involves inferring the DNA reference from a cluster of erroneous copies. While most methods assume equal contributions from all reads within a cluster as noisy copies of the same reference, they often overlook the existence of contaminated sequences caused by DNA breaks, rearrangements, or mis-clustering reads. To address this issue, we propose RobuSeqNet, a robust multi-read reconstruction neural network specifically designed to robustly reconstruct multiple reads, accommodating noisy clusters with strand breakage, rearrangements, and mis-clustered strands. Leveraging the attention mechanism and an elaborate network design, RobuSeqNet exhibits resilience to highly-noisy clusters and effectively deals with in-strand IDS errors. The effectiveness and robustness of the proposed method are validated on three representative next-generation sequencing datasets. Results demonstrate that RobuSeqNet maintains high sequence reconstruction success rates of 99.74%, 99.58%, and 96.44% across three datasets, even in the presence of noisy clusters containing up to 20% contaminated sequences, outperforming known sequence reconstruction models. Additionally, in scenarios without contaminated sequences, it exhibits comparable performance to existing models, achieving success rates of 99.88%, 99.82%, and 97.68% across the three datasets.

PMID:39807110 | PMC:PMC11725466 | DOI:10.1016/j.csbj.2024.02.019

Endocr Metab Immune Disord Drug Targets. 2025 Jan 9. doi: 10.2174/0118715303313654241101042033. Online ahead of print.

ABSTRACT

BACKGROUND: There is still no conclusive understanding of whether the glucokinase regulator (GCKR) gene rs780094 and rs1260326 polymorphisms predispose to gestational diabetes mellitus (GDM).

OBJECTIVE: This systematic review and meta-analysis aimed to determine the effect of the GCKR polymorphisms on GDM susceptibility.

METHODS: Seven literature databases were searched (from inception to February 17, 2024) to locate relevant studies included in further meta-analysis. Odds ratio (OR) and 95% confidence intervals (CI) in the pooled population were estimated to assess the effects of the variant allele on GDM risk.

RESULTS: For the rs780094 polymorphism, 13 datasets with 3443 GDM cases and 5930 nondiabetic controls were included. The pooled estimates in the allele model (OR: 1.19, 95% CI: 1.07~1.32), homozygote model (OR: 1.27, 95% CI: 1.10~1.47), dominant model (OR: 1.16, 95% CI: 1.03~1.31), and recessive model (OR: 1.31, 95% CI: 1.09~1.57) suggested that the C allele carriers were prone to GDM. For the rs1260326 polymorphism, five datasets with 1495 cases and 2678 controls were integrated. The statistically significant effect of the C allele was evident in the allele model (OR: 1.12, 95% CI: 1.01~1.24) and the homozygote model (OR: 1.26, 95% CI: 1.03~1.54).

CONCLUSION: This meta-analysis suggested that the C allele of the rs780094 and rs1260326 polymorphisms in the GCKR gene are significantly associated with increased risk of GDM.

PMID:39806965 | DOI:10.2174/0118715303313654241101042033

Notice NOT-HL-24-032 from the NIH Guide for Grants and Contracts

Notice NOT-NS-25-009 from the NIH Guide for Grants and Contracts

Funding Opportunity PAR-25-313 from the NIH Guide for Grants and Contracts. The purpose of the NCI Pathway to Independence Award (K99/R00) program is to facilitate a timely transition of talented postdoctoral researchers with a research and/or clinical doctorate degree from mentored, postdoctoral research positions to independent, tenure-track or equivalent faculty positions. The program will provide independent NCI research support during this transition in order to help awardees to launch competitive, independent research careers.

Notice NOT-CA-25-022 from the NIH Guide for Grants and Contracts

Notice NOT-OD-25-064 from the NIH Guide for Grants and Contracts

Notice NOT-EY-25-005 from the NIH Guide for Grants and Contracts

Notice NOT-AG-24-032 from the NIH Guide for Grants and Contracts

Funding Opportunity RFA-AI-25-006 from the NIH Guide for Grants and Contracts. The purpose of this notice of funding opportunity (NOFO) is to support research studies of two or more vaccine adjuvants (combination adjuvants) in order to understand the mechanisms by which they work in concert. All adjuvants considered must have previously demonstrated immune modulating activity. The long-term goal of this research program is to improve the rational design of vaccines by predicting the immune profile elicited by combination adjuvants.

Funding Opportunity PAR-25-342 from the NIH Guide for Grants and Contracts. The purpose of this Notice of Funding Opportunity (NOFO) is to support innovative and interdisciplinary research teams focused on clinical, health services, and/or community-based interventions that address health and healthcare disparities related to non-communicable and chronic diseases (NCDs) with the highest burden and mortality in Latin America and among U.S. Hispanics/Latinos. Multidisciplinary research teams would be expected to meaningfully collaborate with key partners that must include at least one PI or MPI from institutions in Latin America.

Notice NOT-AG-24-089 from the NIH Guide for Grants and Contracts

Notice NOT-OD-25-059 from the NIH Guide for Grants and Contracts

JAMA Pediatr. 2025 Feb 1;179(2):197-202. doi: 10.1001/jamapediatrics.2024.5100.

ABSTRACT

IMPORTANCE: Cell and gene therapies are revolutionizing the treatment landscape for children and adults with rare diseases and can be life-changing for patients and their families. Successful implementation of these new therapies into clinical practice depends on their accessibility and affordability, particularly through publicly funded Medicaid agencies, which cover many children and adults with rare diseases.

OBJECTIVE: To provide a framework to broadly assess cell and gene therapies, evaluate payment options, and ensure equitable access through the lens of publicly funded Medicaid programs.

EVIDENCE REVIEW: This review draws on peer-reviewed articles, federal reports, and other relevant publications as well as the expertise of chief medical officers and medical directors of state Medicaid agencies across 5 diverse states.

FINDINGS: Twenty-nine articles and other references provide the foundation for this review. The recommendations presented focus on thoughtful implementation of cell and gene therapies, including policy recommendations in the domains of safety, effectiveness, population health, access, and budget.

CONCLUSIONS AND RELEVANCE: Proposed health care policy changes are intended to balance innovation, affordability, and equitable access for children and adults with rare diseases.

PMID:39804636 | DOI:10.1001/jamapediatrics.2024.5100

medRxiv [Preprint]. 2024 Oct 4:2024.10.04.24313542. doi: 10.1101/2024.10.04.24313542.

ABSTRACT

INTRODUCTION: Structural variants (SVs) of the nebulin gene (NEB), including intragenic duplications, deletions, and copy number variation of the triplicate region, are an established cause of recessively inherited nemaline myopathies and related neuromuscular disorders. Large deletions have been shown to cause dominantly inherited distal myopathies. Here we provide an overview of 35 families with muscle disorders caused by such SVs in NEB.

METHODS: Using custom Comparative Genomic Hybridization arrays, exome sequencing, short-read genome sequencing, custom Droplet Digital PCR, or Sanger sequencing, we identified pathogenic SVs in 35 families with NEB-related myopathies.

RESULTS: In 23 families, recessive intragenic deletions and duplications or pathogenic gains of the triplicate region segregating with the disease in compound heterozygous form, together with a small variant in trans, were identified. In two families the SV was, however, homozygous. Eight families have not been described previously. In 12 families with a distal myopathy phenotype, eight unique, large deletions encompassing 52 to 97 exons in either heterozygous (n = 10) or mosaic (n = 2) state were identified.In the families where inheritance was recessive, no correlation could be made between the types of variants and the severity of the disease. In contrast, all patients with large dominant deletions in NEB had milder, predominantly distal muscle weakness.

DISCUSSION: For the first time, we establish a clear and statistically significant association between large NEB deletions and a form of distal myopathy. In addition, we provide the hitherto largest overview of the spectrum of SVs in NEB.

PMID:39802796 | PMC:PMC11722492 | DOI:10.1101/2024.10.04.24313542

Sci Rep. 2025 Jan 13;15(1):1836. doi: 10.1038/s41598-024-83767-9.

ABSTRACT

Tyrosine-protein kinase Src plays a key role in cell proliferation and growth under favorable conditions, but its overexpression and genetic mutations can lead to the progression of various inflammatory diseases. Due to the specificity and selectivity problems of previously discovered inhibitors like dasatinib and bosutinib, we employed an integrated machine learning and structure-based drug repurposing strategy to find novel, targeted, and non-toxic Src kinase inhibitors. Different machine learning models including random forest (RF), k-nearest neighbors (K-NN), decision tree, and support vector machine (SVM), were trained using already available bioactivity data of Src kinase targeting compounds. The performance evaluation of these models demonstrated SVM as the best model, which was further utilized to shortlist 51 highly potent compounds by screening an FDA-approved library of 1040 drugs. Molecular docking and molecular dynamic simulation were subsequently employed to evaluate the binding affinity and stability of the proposed compounds. Orlistat, acarbose and afatinib were identified as the potent leads, demonstrating stable conformations and stronger interactions, validated by root mean square deviation (RMSD), root mean square fluctuation (RMSF), radius of gyration (RoG), and hydrogen bond analyses. Molecular Mechanics/Generalized Born Surface Area (MMGBSA) analysis validated their binding affinities by providing comparably lower binding free energies for orlistat (- 33.4743 ± 3.8908), acarbose (- 19.5455 ± 5.4702), and afatinib (- 36.4944 ± 5.4929) than the control, dasatinib (- 13.7785 ± 5.8058). Finally, toxicity analysis revealed orlistat and acarbose as the possible safer therapeutics by eliminating afatinib as it showed significant toxicity concerns. Our investigation supports the advance computational methods utilization in the field of drug discovery and suggest further experimental validation of proposed inhibitors of Src kinase for their safer use against inflammatory diseases. The ultimate aim of this study is to advance the development of effective treatments for inflammatory diseases, linked with Src overexpression.

PMID:39805859 | DOI:10.1038/s41598-024-83767-9