S. Stephen Yi

The paper develops a model to predict NMD outcomes for protein-truncating variants using RNA-seq data, achieving ~78% ROC-AUC and identifying non-canonical determinants.

eSIG-Net predicts how single mutations affect protein interactions using a sequence-based interaction language model, outperforming existing methods.

This study identifies NMD-escape variants as a distinct class of disease-causing mutations, showing that altered C-terminal regions drive pathogenicity through phase separation.

This study systematically profiles 95 viral transcriptional regulators (vTRs) across multiple assays, revealing their diverse mechanisms of rewiring host pathways to promote viral replication and disease links.

This study shows that mutant NPM1 forms nuclear condensates called C-bodies, which are essential for leukemic gene expression and cell survival, and identifies them as potential therapeutic targets.

The paper identifies trans-heterozygous digenic variants in laterality defect genes using exome/genome sequencing data from CHD cohorts, finding significant enrichment in laterality cases compared to controls.

This study identifies PRMT1 as a critical survival dependency in multiple myeloma cells, showing that its inhibition reduces cell survival and impairs tumor growth.

This paper develops an iPSC platform to rapidly generate alpha-synuclein inclusions and investigates their formation, subtypes, and molecular interactions.

This paper introduces SCORPION, a tool for reconstructing gene regulatory networks from single-cell RNA-seq data, showing it outperforms existing methods and detects consistent regulatory differences in colorectal cancer.

This study identifies RNA binding proteins as novel drivers of homologous recombination deficiency in tumors, expanding the known genetic causes beyond BRCA1/2 mutations.

This study uses single-cell RNA-seq based transfer learning to prioritize synergistic drug combinations for cancer treatment by aligning patient tumor cells with similar cell lines.

The paper develops a deep learning model integrating multi-omics data to stratify breast cancer patients by prognosis and identify potential therapeutic targets.

e-MutPath identifies edgetic mutations that perturb functional pathways, revealing cancer vulnerability genes and drug targets through network-based analysis.

The paper systematically analyzes the impact of somatic mutations on miRNA regulatory networks across 30 cancer types, identifying driver mutations that perturb these networks and function as tumor suppressors.