Yu‐Chiao Chiu

The paper develops RIZLiver to infer zonal identity from gene expression in liver disease, showing loss of zone-3 identity in MASLD and therapeutic potential through zonal restoration.

spatiAlytica enables non-programmer biologists to perform interactive spatial omics analysis using natural language and a viewer-centric agentic system.

This study shows that deleting both Sox9 and Yap1 eliminates cholangiocarcinoma by blocking transcriptional compensation, suggesting co-targeting as a therapeutic strategy.

STiLE automates TMA dearraying using cell centroid coordinates, achieving high accuracy and robustness across platforms and artifacts.

This study identifies IL-1/IRAK1/4 signaling as a therapeutic target in AML stem cells, showing that UR241-2 inhibits LSC clonogenicity and engraftment in both diagnosis and relapse.

This paper develops a high-throughput screening method to identify drugs targeting polyploid giant cancer cells in breast cancer, combining empirical assays with a machine learning model for virtual screening.

reguloGPT constructs a knowledge graph of molecular regulatory pathways using GPT-4 for entity recognition and relationship extraction, improving over existing methods and demonstrating utility in cancer research.

DepLink links genetic and pharmacologic dependencies in cancer by integrating CRISPR, pharmacologic, and expression data through an R Shiny app.

CancerSiamese improves cancer type prediction using one-shot learning with gene expression data, achieving 8% and 4% accuracy gains over 1-NN for primary and metastatic tumors.

The paper introduces MR-GAN, a GAN-based model for predicting epitranscriptome modification sites using unsupervised learning, showing significant improvement over one-hot encoding and SRAMP.

This paper designs an ancestry informative marker panel using whole exome sequencing data to estimate genetic ancestry in Hispanic populations, achieving high accuracy in admixture proportion estimation.