I am a Ph.D. candidate in Bioinformatics & Genomics at Penn State (graduating May 2026), specializing in deep learning for regulatory genomics, multimodal sequence–chromatin modeling, and large-scale ML pipelines.

My work includes developing CNN/Transformer models to characterize FOXA1/AP-1 binding synergy (Molecular Cell 2024) and creating the SEM algorithm for nucleosome subtype inference (Genome Research 2024). These projects required building scalable training datasets (HDF5/WebDataset), optimizing GPU-based training on HPC systems, and applying interpretability frameworks such as DeepLIFT/SHAP and TF-MoDISco.

I also develop practical research software, including Seqchromloader (PyTorch/WebDataset toolkit for genomic ML datasets) and Snakemake pipelines for routine ATAC-seq, ChIP-seq, RNA-seq, and MNase-seq preprocessing. These tools are actively used by other members of my lab.

Short CV: Click to Download

Academic CV: Click to Download