Y‐h. Taguchi

The paper introduces a two-stage deep learning approach for gene expression analysis in esophageal adenocarcinoma, identifying more expressed genes than traditional methods.

This paper develops a tensor decomposition framework to integrate single-cell four-omics data, revealing cell-type-specific enhancer-promoter programs that cannot be identified by individual modalities.

The paper introduces a tensor decomposition method for integrating CITE-seq RNA and ADT data without modality-weight tuning, showing competitive but not superior performance compared to existing methods.

This paper introduces a 4D tensor decomposition method to integrate transcriptome, Ribo-seq, and proteome data, identifying gene clusters related to ribosome stacking and translational buffering.

The paper presents an AI-based pipeline for predicting bevacizumab response in ovarian cancer using digital pathology images, achieving improved AUC performance compared to existing models.

This study uses tensor decomposition to analyze CRISPR-Cas9 knockout screens, distinguishing essential from non-essential genes with performance comparable to JACKS without requiring control samples or logarithmic transformations.

The paper re-analyzes sleep deprivation and recovery gene expression data to identify somatostatin-expressing neurons as potentially key regulators of sleep behavior.

The paper compares gene expression profiles from sleep and anaesthesia-induced unconsciousness to identify gene sets associated with specific neuronal populations and pathways.

The paper develops a deep learning approach to analyze drug resistance in melanoma using scRNA-seq data, identifying key genes and drugs associated with resistance.

This paper introduces a tensor decomposition-based method for cell-type deconvolution in Visium spatial transcriptomics data, showing success where conventional methods fail due to inclusion of multiple minor cell types in reference profiles.

This paper introduces a tensor decomposition method to automatically determine common optimal bin sizes for integrating multiple Hi-C datasets without manual parameter tuning.

This study introduces a novel AI-based method using tensor decomposition to identify drug-gene-disease interactions from protein-protein interactions without prior disease or drug information.

This paper develops a deep transfer learning approach to classify healthy and SARS-CoV-2 infected human alveolar type II cells using electron microscopy images, achieving high accuracy and speed.

The paper uses TDbasedUFE to analyze scATAC-seq data from S. aureus sepsis patients, identifying genes with differential responses between methicillin-resistant and sensitive strains and their functional associations.

The paper introduces maGENEgerZ, an AI-based framework that identifies more expressed genes and biological insights related to breast cancer drug response using support vector machines.

The paper introduces two Bioconductor packages for tensor decomposition-based unsupervised feature extraction, showing they outperform existing methods in gene expression analysis and multi-omics integration.

The paper integrates gene expression and protein-protein interaction data using tensor decomposition, improving classification and enrichment across 27 cancer types from TCGA.

The paper introduces a method combining tensor decomposition and PCA to identify histone modifications from genomic data, outperforming existing methods.

The paper introduces GENEvaRX, a computational framework that identifies critical genes and drugs for lichen planus using gene expression data and enrichment analysis.

This study uses tensor decomposition to address data sparsity in scATAC-seq and identifies tissue-specific patterns and gene associations.

The paper introduces a method combining principal component analysis and tensor decomposition to identify differentially methylated cytosines, outperforming existing methods and showing functional relevance.

This study compares hypothesis-driven and data-driven analyses using tensor decomposition on human blood metabolome data, finding that tensor decomposition can extract similar biological features more efficiently.

The paper presents a computational framework using machine learning to identify therapeutic targets and influential genes in pancreatic islet cells, finding 44 unique genes and 10 transcription factors related to pancreatic islet functions and diseases.

The paper optimizes standard deviation in tensor decomposition and PCA to improve differential gene selection, achieving better alignment with the null hypothesis and increased biological reliability.

This paper explains why PCA and tensor decomposition work well for feature selection in genomic data by relating them to projection pursuit and empirical P-value thresholds.

The paper improves a tensor decomposition method for integrating gene expression profiles from multiple tissues and identifies disease associations beyond individual tissue analyses.

This paper introduces an advanced kernel tensor decomposition method for multi-omics data analysis, showing improved performance and feature attribution.

The paper uses principal component analysis to identify differentially expressed genes in cells exposed to a collagen-glycosaminoglycan mesh compared to controls, finding enriched biological terms and better performance than linear regression.

This study applies tensor-decomposition-based unsupervised feature extraction to integrate single-cell multiomics data without filling missing values, producing biologically relevant embeddings.

This study uses tensor decomposition-based unsupervised feature extraction to identify differentially expressed transcripts in planarian RNA-seq data with a highly redundant de novo transcriptome, outperforming conventional methods.