Chi-Yun Wu

This paper develops a machine learning pipeline to discover novel antibacterial compounds with distinct mechanisms of action, finding that training data bias limits the discovery of mechanistically novel antibiotics.

Clonalscope detects cancer subclones using DNA copy number data from single-cell and spatial omic sequencing, identifying spatially segregated subclones and validating them with matched scDNA-seq data.

The paper introduces niche-differential expression analysis to identify context-dependent cell-cell interactions in spatial transcriptomics data and applies it to colorectal cancer metastases.

Alleloscope analyzes allele-specific copy number and chromatin accessibility in single-cell cancer data, revealing complex copy number events and their role in intratumor heterogeneity.