Hongyoon Choi

This study uses spatial transcriptomics to compare immune and metabolic differences between treatment-responsive and resistant non-small cell lung cancer tumors after neoadjuvant chemoimmunotherapy.

This paper introduces PGL, a large language model that generates synthetic single-cell RNA-seq data from metadata, enabling virtual cohort construction and reference-on-demand analysis.

This study uses spatial transcriptomics to identify SPP1+ macrophages as key contributors to CCRT resistance in hypopharyngeal SCC by modulating the tumor microenvironment.

This study identifies Pdgfd-Pdgfrb signaling as a driver of perineural invasion in pancreatic cancer by promoting cancer cell invasiveness and nerve engagement.

STopover analyzes spatial transcriptomics data to identify cell-cell interactions and colocalization patterns in the tumor microenvironment.

This paper develops SIRPα-expressing extracellular vesicles from engineered stem cells to treat acute liver failure by resolving necroptosis and promoting liver regeneration, showing reduced liver damage and improved survival in models.

IAMSAM is a web-based tool for analyzing spatial transcriptomics data, enabling tissue segmentation and downstream analysis like differential expression and cell type prediction.

The paper analyzes unmapped RNA-seq data from cancer spatial transcriptomes to study microbial RNA distribution and function in cancer tissues.

This study uses spatial transcriptomics to analyze cancer-associated fibroblasts in lung squamous cell carcinoma, linking their spatial organization to tumor progression and patient outcomes.

CELLama transforms single-cell and spatial transcriptomics data into embeddings using language model abilities, enabling flexible analysis without manual reference data.

SpatialSPM compares gene expression patterns across spatial transcriptomic datasets by aligning and analyzing multi-dimensional image matrices to identify differentially expressed regions.

This paper introduces SuperST, a deep learning method that reconstructs high-resolution spatial gene expression images from low-resolution barcode-based spatial transcriptomics data, improving alignment with immunofluorescence images.

GeneDART extends gene coverage in imaging-based spatial transcriptomics by combining it with barcode-based data using deep learning for domain adaptation.

The paper uses spatial transcriptomics to analyze brain cell changes in mouse dementia models after immunomodulation treatments and develops a new analysis tool.

The paper identifies molecular markers associated with nanomedicine distribution in tumor tissue using spatial transcriptomics and fluorescence imaging.

spSeudoMap maps cell types from spatial transcriptomics data using unmatched single-cell RNA-seq data by creating virtual cell mixtures and domain adaptation.

CellDART adapts neural networks to infer cell type spatial distribution from single-cell and spatial transcriptomic data, showing effectiveness in human and mouse tissues.

The paper identifies potential imaging and therapeutic targets for severe COVID-19 inflammation by analyzing single-cell RNA-seq data from patient samples.

This study characterizes spatiotemporal glial cell activation in an Alzheimer's disease model, revealing early white matter changes and later gray matter involvement.

The paper introduces SPADE, a method that integrates spatial transcriptomic data with deep learning features from tissue images to identify genes associated with morphological contexts.

The study links disease-associated microglia enrichment to neuronal subtype reconfiguration, particularly in cortical layer 4 excitatory neurons, in Alzheimer's disease.

The paper predicts age-related brain metabolic changes using a variational autoencoder and shows APOE4 status significantly affects metabolic degeneration in specific brain regions.

The paper develops a deep learning-based risk stratification model for lung adenocarcinoma using gene coexpression networks and validates its prognostic value across multiple datasets.