Computers in biology and medicine最新文献

Obesity is a chronic disease correlated with numerous risk factors that not only negatively affect all body functions but also increase the chances of developing chronic diseases and the associated morbidity and mortality rates. This study proposes a novel system that bridges the gap between healthcare providers and patients by offering both parties some tools for navigating the intricacies of dietary planning. In this system, machine learning techniques are used to determine the required calories before starting an obesity treatment. A hybrid precision model with minimal parameters is also developed to estimate the appropriate number of calories for losing weight and to formulate a healthy diet plan. A real dataset of 15 anthropometric measurements is analyzed using SVR, LR, and DTR regression models, and all the data are preprocessed before analysis to enhance model performance. Results show that the required calories can be estimated with a high correlation (R = 0.985) from independent measurements. The proposed model also calculates the healthy daily percentages of fats, proteins, and carbohydrates based on a knowledge base of medical rules and functions, thus facilitating the sequential treatment of obese patients. In sum, this study applies different models to design a practical, cost-effective approach for accurately determining the required calories and formulating valuable diet plans for obesity treatment and management.

Carrion's disease, caused by the bacterium Bartonella bacilliformis, is a serious public health problem in Peru, Ecuador and Colombia. Currently there is no available vaccine against B. bacilliformis. While antibiotics are the standard treatment, resistant strains have been reported, and there is a potential spread of the vector that transmits the bacteria. This study aimed to design a multi-epitope vaccine candidate against the causative agent of Carrion's disease using immunoinformatics tools. Predictions of B-cell epitopes, as well as CD4⁺ and CD8⁺T cell epitopes, were performed from the entire proteome of B. bacilliformis KC583 using the most frequent alleles from Peru, Ecuador, Colombia, and worldwide. B-cell epitopes and T-cell nested epitopes from outer membrane and virulence-associated proteins were selected. Epitopes were filtered out based on promiscuity, non-allergenicity, conservation, non-homology and non-toxicity. Two vaccine constructs were assembled using linkers. The tertiary structure of the constructs was predicted, and their stability was evaluated through molecular dynamics simulations. The most stable construct was selected for molecular docking with the TLR4 receptor. This study proposes a vaccine construct evaluated in silico as a potential vaccine candidate against Bartonella bacilliformis.

Gastric cancer (GC) is a common cancer worldwide. Therefore, searching for effective treatments is essential, and drug repositioning can be a promising strategy to find new potential drugs for GC therapy. For the first time, we sought to identify molecular alterations and validate new mechanisms related to Mebendazole (MBZ) treatment in GC cells through transcriptome analysis using microarray technology. Data revealed 1066 differentially expressed genes (DEGs), of which 345 (2.41 %) genes were upregulated, 721 (5.04 %) genes were downregulated, and 13,231 (92.54 %) genes remained unaltered after MBZ exposure. The overexpressed genes identified were CCL2, IL1A, and CDKN1A. In contrast, the H3C7, H3C11, and H1-5 were the top 3 underexpressed genes. Gene set enrichment analysis (GSEA) identified 8 pathways significantly overexpressed in the treated group (p < 0.05 and FDR<0.25). The validation of the expression of top desregulated genes by RT-qPCR confirmed the transcriptome results, where MBZ increased the CCL2, IL1A, and CDKN1A and reduced the H3C7, H3C11, and H1-5 transcript levels. Expression analysis in samples from TCGA databases correlated that the lower ILI1A and higher H3C11 and H1-5 gene expression are associated with decreased overall survival rates in patients with GC, indicating that MBZ treatment can improve the prognosis of patients. Thus, the data demonstrated that the drug MBZ alters the transcriptome of the AGP-01 lineage, mainly modulating the expression of histone proteins and inflammatory cytokines, indicating a possible epigenetic and immunological effect on tumor cells, these findings highlight new mechanisms of action related to MBZ treatment. Additional studies are still needed to better clarify the epigenetic and immune mechanism of MBZ in the therapy of GC.

Breast mass segmentation plays a crucial role in early breast cancer detection and diagnosis, and while Convolutional Neural Networks (CNN) have been widely used for this task, their reliance on local receptive fields limits ability to capture long-range dependencies. Vision Transformers (ViTs), on the other hand, excel in this area by leveraging multi-head self-attention mechanisms to generate attention maps that dynamically gather global spatial information, significantly outperforming CNN-based architectures in various tasks. However, traditional transformer-based models come with challenges, including high computational complexity due to the self-attention mechanism and inefficiency in the static MLP fusion process. To overcome these issues, the Hybrid Transformer U-Net (HTU-net) model is proposed for breast mass segmentation in mammography. Channel and spatial enhanced self-attention mechanisms are integrated with convolutions layers in HTU-Net, creating a hybrid architecture that combines the strengths of both CNNs and ViTs. The introduction of a multiscale attention mechanism further improves the model's ability to fuse information from different resolutions, enhancing the decoder's capacity to reconstruct fine details in the segmented output. By using both local texture-based features and global contextual information, HTU-Net excels in capturing essential features, thus improving segmentation performance. The experimental results across multiple datasets, including CBIS-DDSM and INbreast, demonstrate that HTU-Net outperforms several state-of-the-art methods, achieving superior accuracy, dice similarity coefficient, and intersection over union. This work highlights the potential of hybrid architectures in advancing computer-aided diagnosis systems, particularly in improving segmentation quality and reliability for breast cancer detection.

Single-cell RNA sequencing (scRNA-seq) technology establishes a unique view for elucidating cellular heterogeneity in various biological systems. Yet the scRNA-seq data is compromised by a high dropout rate due to the technological limitation, and the substantial data loss poses computational challenges on subsequent analyses. This study introduces a novel graph clustering autoencoder (GCAE)-based imputation approach (GraCEImpute) to address the challenge of missing data in scRNA-seq data. Our comprehensive evaluation demonstrates that the GraCEImpute model outperforms existing approaches in accurately imputing dropout zeros within scRNA-seq data. The proposed GraCEImpute model also demonstrates the significantly enhanced quality of downstream scRNA-seq data analyses, including clustering, differential gene expression (DEG) analysis, and cell trajectory inference. These improvements underscore the GraCEImpute model's potential to facilitate a deeper understanding of cellular processes and heterogeneity through the scRNA-seq data analyses. The source code is released at https://www.healthinformaticslab.org/supp/.

N-palmitoylethanolamine (PEA) is an endogenous bioactive compound recognized for its anti-inflammatory effects and its role in tissue protection and repair. Despite the proposal of peroxisome proliferator-activated receptor alpha (PPARα) as a potential receptor for PEA, direct evidence of binding remains insufficient. This study offers a comprehensive analysis of human nuclear receptors (NRs) through structural bioinformatics and molecular docking, evaluating a total of 367 unique NR structures across 47 subfamilies. To explore the stability and binding affinity of PEA with selected nuclear receptors, we conducted molecular dynamics simulations following initial docking assessments. The results revealed Hepatocyte Nuclear Factor 4-alpha (HNF4α) as the highest-ranking receptor with a global score of 0.884, closely followed by Hepatocyte Nuclear Factor 4-gamma (HNF4γ) at 0.871 and Retinoic Acid Receptor gamma-1 (RARγ-1) at 0.829. Among these, HNF4γ demonstrated the strongest affinity for PEA, supported by consistent simulation results. In contrast, the PPARα receptor ranked 44th with a global score of 0.519, indicating that PEA may engage more effectively with other nuclear receptors. In conclusion, this study underscores PEA's potential as a multi-target therapeutic agent through its interactions with various nuclear receptors, particularly HNF4γ and the Mineralocorticoid Receptor (MR). The ability of PEA to influence multiple signaling pathways suggests its promise in addressing complex diseases associated with inflammation and metabolic disorders. Additionally, the integration of Root Mean Square Deviation (RMSD) and Gibbs free energy (ΔG) analyses further elucidates the stability and binding affinities of PEA, providing a foundation for future research into its therapeutic applications.