Y‐h. Taguchi

This study develops a deep learning application to classify single-cell gene regulatory networks from pancreatic islets, finding that VGG19 performs best in distinguishing healthy from T2D networks.

This paper introduces a kernel-based tensor decomposition method for unsupervised feature extraction and evaluates its performance on synthetic and real data, showing it outperforms or matches traditional tensor decomposition in large p small n scenarios.

This study uses tensor decomposition to analyze gene expression data and finds non-linear dose dependence can occur with single drugs, not just drug combinations.

This paper develops and evaluates deep learning models to detect metastatic breast cancer in axillary lymph nodes using digital pathology images, finding DenseNet121 achieves the highest performance.

This paper introduces a tensor-decomposition-based unsupervised feature extraction method for multiomics data, showing it outperforms existing methods in selecting biologically relevant genes.

The paper uses tensor decomposition to identify miRNA signatures and associated genes in kidney renal clear cell carcinoma, finding 23 genes correlated with patient survival and demonstrating better performance than traditional methods.

The paper applies tensor decomposition-based unsupervised feature extraction to gene expression data from drug-treated mouse tissues, identifying common drug effects across tissue groups.

The paper screens genes differentially expressed in Alzheimer's disease model mice and finds overlap with drug-treated human cell lines using tensor decomposition.

This paper applies tensor decomposition-based unsupervised feature extraction to integrate human and mouse scRNA-seq data, improving gene selection and identifying potential regulatory transcription factors.

The paper proposes tensor decomposition for multiomics data integration and compares it to DIABLO, showing successful integration of miRNA, mRNA, and proteome data.

This study uses tensor decomposition to identify miRNAs and genes associated with ovarian cancer by integrating miRNA expression and promoter methylation data from TCGA.

This study uses PCA-based unsupervised feature extraction to identify biologically relevant genes in scRNA-seq data from mouse and human embryonic brain development, outperforming existing methods.

The paper uses tensor decomposition on integrated gene expression data from heart failure and DrugMatrix datasets to identify drug candidates associated with heart failure.

The paper identifies miRNA-mRNA interactions in Wilms tumor using principal component analysis to find significant negative correlations between miRNA and mRNA expression.