At Baylor Genetics, I optimize bulk and single-cell RNA-seq workflows for TCGA cancer cohorts, reducing pipeline runtime by about 35% through parallelization on HPC/SLURM. I also apply interpretable machine learning to prioritize biomarkers, achieving AUROC above 0.89 on held-out test sets.
My work spans multi-omics analysis, clinical and genomic datasets, and reproducible pipeline development in Python and R. In projects, I built workflows for drought-stress analysis in maize, single-cell breast cancer analysis, and renal fibrosis prediction using KPMP data.

