Yu Amanda Guo

This study performs a transcriptome-wide meta-analysis to identify determinants of immune checkpoint blockade response, finding that stromal factors, not cancer-cell intrinsic features, are key predictors across tumor types.

Fragle quantifies ctDNA from fragment length profiles using deep learning, showing high accuracy and improved detection limits across multiple datasets and sequencing types.

MutSpot identifies non-coding mutation hotspots in cancer genomes by analyzing epigenetic and sequence features across thousands of genomes.

SMuRF improves somatic variant calling accuracy by combining multiple callers using Random Forest, working across cancer types and data types.