Biodata Mining最新文献

Gliomas are primary malignant brain tumors with a typically poor prognosis, exhibiting significant heterogeneity across different cancer types. Each glioma type possesses distinct molecular characteristics determining patient prognosis and therapeutic options. This study aims to explore the molecular complexity of gliomas at the transcriptome level, employing a comprehensive approach grounded in network discovery. The graphical lasso method was used to estimate a gene co-expression network for each glioma type from a transcriptomics dataset. Causality was subsequently inferred from correlation networks by estimating the Jacobian matrix. The networks were then analyzed for gene importance using centrality measures and modularity detection, leading to the selection of genes that might play an important role in the disease. To explore the pathways and biological functions these genes are involved in, KEGG and Gene Ontology (GO) enrichment analyses on the disclosed gene sets were performed, highlighting the significance of the genes selected across several relevent pathways and GO terms. Spectral clustering based on patient similarity networks was applied to stratify patients into groups with similar molecular characteristics and to assess whether the resulting clusters align with the diagnosed glioma type. The results presented highlight the ability of the proposed methodology to uncover relevant genes associated with glioma intertumoral heterogeneity. Further investigation might encompass biological validation of the putative biomarkers disclosed.

Objectives: Bladder cancer (BLCA) is a tumor that affects men more than women. The biological function and prognostic value of androgen-responsive genes (ARGs) in BLCA are currently unknown. To address this, we established an androgen signature to determine the prognosis of BLCA.

Methods: Sequencing data for BLCA from the TCGA and GEO datasets were used for research. The tumor microenvironment (TME) was measured using Cibersort and ssGSEA. Prognosis-related genes were identified and a risk score model was constructed using univariate Cox regression, LASSO regression, and multivariate Cox regression. Drug sensitivity analysis was performed using Genomics of drug sensitivity in cancer (GDSC). Real-time quantitative PCR was performed to assess the expression of representative genes in clinical samples.

Results: ARGs (especially the CDK6, FADS1, PGM3, SCD, PTK2B, and TPD52) might regulate the progression of BLCA. The different expression patterns of ARGs may lead to different immune cell infiltration. The risk model indicates that patients with higher risk scores have a poorer prognosis, more stromal infiltration, and an enrichment of biological functions. Single-cell RNA analysis, bulk RNA data, and PCR analysis support the reliability of this risk model, and a nomogram was also established for clinical use. Drug prediction analysis showed that high-risk patients had a better response to fludarabine, AZD8186, and carmustine.

Conclusion: ARGs played an important role in the progression, immune infiltration, and prognosis of BLCA. The ARGs model has high accuracy in predicting the prognosis of BLCA patients and provides more effective medication guidelines.

Background: Long terminal repeats (LTRs) represent important parts of LTR retrotransposons and retroviruses found in high copy numbers in a majority of eukaryotic genomes. LTRs contain regulatory sequences essential for the life cycle of the retrotransposon. Previous experimental and sequence studies have provided only limited information about LTR structure and composition, mostly from model systems. To enhance our understanding of these key sequence modules, we focused on the contrasts between LTRs of various retrotransposon families and other genomic regions. Furthermore, this approach can be utilized for the classification and prediction of LTRs.

Results: We used machine learning methods suitable for DNA sequence classification and applied them to a large dataset of plant LTR retrotransposon sequences. We trained three machine learning models using (i) traditional model ensembles (Gradient Boosting), (ii) hybrid convolutional/long and short memory network models, and (iii) a DNA pre-trained transformer-based model using k-mer sequence representation. All three approaches were successful in classifying and isolating LTRs in this data, as well as providing valuable insights into LTR sequence composition. The best classification (expressed as F1 score) achieved for LTR detection was 0.85 using the hybrid network model. The most accurate classification task was superfamily classification (F1=0.89) while the least accurate was family classification (F1=0.74). The trained models were subjected to explainability analysis. Positional analysis identified a mixture of interesting features, many of which had a preferred absolute position within the LTR and/or were biologically relevant, such as a centrally positioned TATA-box regulatory sequence, and TG..CA nucleotide patterns around both LTR edges.

Conclusions: Our results show that the models used here recognized biologically relevant motifs, such as core promoter elements in the LTR detection task, and a development and stress-related subclass of transcription factor binding sites in the family classification task. Explainability analysis also highlighted the importance of 5'- and 3'- edges in LTR identity and revealed need to analyze more than just dinucleotides at these ends. Our work shows the applicability of machine learning models to regulatory sequence analysis and classification, and demonstrates the important role of the identified motifs in LTR detection.

Multimodal brain network analysis enables a comprehensive understanding of neurological disorders by integrating information from multiple neuroimaging modalities. However, existing methods often struggle to effectively model the complex structures of multimodal brain networks. In this paper, we propose a novel tensor-based graph convolutional network (TGNet) framework that combines tensor decomposition with multi-layer GCNs to capture both the homogeneity and intricate graph structures of multimodal brain networks. We evaluate TGNet on four datasets-HIV, Bipolar Disorder (BP), and Parkinson's Disease (PPMI), Alzheimer's Disease (ADNI)-demonstrating that it significantly outperforms existing methods for disease classification tasks, particularly in scenarios with limited sample sizes. The robustness and effectiveness of TGNet highlight its potential for advancing multimodal brain network analysis. The code is available at  https://github.com/rongzhou7/TGNet .

This research presents a predictive model aimed at estimating the progression of Amyotrophic Lateral Sclerosis (ALS) based on clinical features collected from a dataset of 50 patients. Important features included evaluations of speech, mobility, and respiratory function. We utilized an XGBoost regression model to forecast scores on the ALS Functional Rating Scale (ALSFRS-R), achieving a training mean squared error (MSE) of 0.1651 and a testing MSE of 0.0073, with R² values of 0.9800 for training and 0.9993 for testing. The model demonstrates high accuracy, providing a useful tool for clinicians to track disease progression and enhance patient management and treatment strategies.

Background: Timely identification of deteriorating patients is crucial to prevent the progression to cardiac arrest. However, current methods predicting emergency department cardiac arrest are primarily static, rule-based with limited precision and cannot accommodate time-series data. Deep learning has the potential to continuously update data and provide more precise predictions throughout the emergency department stay.

Methods: We developed and internally validated a deep learning-based scoring system, the Deep EDICAS for early prediction of cardiac arrest and a subset of arrest, cardiopulmonary resuscitation (CPR), in the emergency department. Our proposed model effectively integrates tabular and time series data to enhance predictive accuracy. To address data imbalance and bolster early prediction capabilities, we implemented data augmentation techniques.

Results: Our system achieved an AUPRC of 0.5178 and an AUROC of 0.9388 on on data from the National Taiwan University Hospital. For early prediction, our system achieved an AUPRC of 0.2798 and an AUROC of 0.9046, demonstrating superiority over other early warning scores. Moerover, Deep EDICAS offers interpretability through feature importance analysis.

Conclusion: Our study demonstrates the effectiveness of deep learning in predicting cardiac arrest in emergency department. Despite the higher clinical value associated with detecting patients requiring CPR, there is a scarcity of literature utilizing deep learning in CPR detection tasks. Therefore, this study embarks on an initial exploration into the task of CPR detection.

Background: Advances in high-throughput technologies have originated an ever-increasing availability of omics datasets. The integration of multiple heterogeneous data sources is currently an issue for biology and bioinformatics. Multiple kernel learning (MKL) has shown to be a flexible and valid approach to consider the diverse nature of multi-omics inputs, despite being an underused tool in genomic data mining.

Results: We provide novel MKL approaches based on different kernel fusion strategies. To learn from the meta-kernel of input kernels, we adapted unsupervised integration algorithms for supervised tasks with support vector machines. We also tested deep learning architectures for kernel fusion and classification. The results show that MKL-based models can outperform more complex, state-of-the-art, supervised multi-omics integrative approaches.

Conclusion: Multiple kernel learning offers a natural framework for predictive models in multi-omics data. It proved to provide a fast and reliable solution that can compete with and outperform more complex architectures. Our results offer a direction for bio-data mining research, biomarker discovery and further development of methods for heterogeneous data integration.

Background: Regulatory T cells (Tregs) play a critical role in shaping the immunosuppressive microenvironment within tumors. Investigating the role of Tregs in Clear cell renal cell carcinoma (ccRCC) is crucial for identifying prognostic markers and therapeutic targets for ccRCC.

Methods: Weighted gene co-expression network analysis (WGCNA) was utilized to pinpoint modules related to Treg infiltration in TCGA-KIRC samples. Following this, consensus clustering was employed to derive two clusters associated with Treg infiltration in ccRCC. A prognostic model was then developed using the gene module associated with Treg infiltration. We then evaluated the ability of the prognostic model to predict ccRCC overall survival and demonstrated that RCN1 can be used as a target to predict ccRCC prognosis.

Results: We deduce that the two clusters associated with Treg infiltration exhibit distinct compositions of the immune microenvironment, pathway activations, prognosis, and drug sensitivities commonly utilized in ccRCC treatment. Furthermore, a 7-gene model risk score, developed based on ccRCC Treg infiltration, proved to be a reliable prognostic marker in both training and validation cohorts. Additionally, survival analysis indicated that RCN1 serves as a reliable prognostic factor for ccRCC. Single-cell sequencing analysis revealed that RCN1 is predominantly expressed in tumor cells. A pan-cancer analysis highlighted that RCN1 is linked with poor prognosis and the activation of inflammatory response pathways across various cancers.

Conclusion: We developed a prognostic model associated with Treg infiltration, which facilitates the clinical categorization of ccRCC progression. Moreover, our findings underscore the significant potential of RCN1 as a ccRCC biomarker.

Alzheimer's disease (AD) is a highly heritable brain dementia, along with substantial failure of cognitive function. Large-scale genome-wide association studies (GWASs) have led to a set of SNPs significantly associated with AD and related traits. GWAS hits usually emerge as clusters where a lead SNP with the highest significance is surrounded by other less significant neighboring SNPs. Although functionality is not guaranteed even with the strongest associations in GWASs, lead SNPs have historically been the focus of the field, with the remaining associations inferred to be redundant. Recent deep genome annotation tools enable the prediction of function from a segment of a DNA sequence with significantly improved precision, which allows in-silico mutagenesis to interrogate the functional effect of SNP alleles. In this project, we explored the impact of top AD GWAS hits around APOE region on chromatin functions and whether it will be altered by the genetic context (i.e., alleles of neighboring SNPs). Our results showed that highly correlated SNPs in the same LD block could have distinct impacts on downstream functions. Although some GWAS lead SNPs showed dominant functional effects regardless of the neighborhood SNP alleles, several other SNPs did exhibit enhanced loss or gain of function under certain genetic contexts, suggesting potential additional information hidden in the LD blocks.