I am a Postdoc researcher at UChicago in the
Madduri group at ANL, collaborating with the
Odunsi group.
My research explores the human genome in complex disorders and builds tools along the way.
My PhD focused on the role of tissue-specific transcript variants in health and cancer,
leveraging large language models (LLMs) to decode the regulatory logic of tissue specificity.
My work bridges bioinformatics, genomics, and AI to address critical challenges in precision medicine.
Research
TransTEx — tissue-specificity scoring
A statistical method that groups the human transcriptome into distinct expression
classes — tissue-specific, tissue-enhanced, widespread, lowly expressed, and null.
Presented at the Great Lakes Bioinformatics Conference (ISCB), Pittsburgh, PA.
A deep-learning framework that learns the DNA regulatory grammar behind tissue-specific
promoters across species, using interpretable attention to surface the motifs and
transcription-factor families that drive specificity. Published in
NAR Genomics and Bioinformatics.
Extends TransTEx to tumors, contrasting normal and cancer expression groups to nominate
transcript-level biomarkers — oncogenes, tumor suppressors, and cancer-testis antigens —
with applications in solid-tumor clustering and pan-glioma classification.
PGViS: Personal Genome Variant interpretation Score for lung cancer genomes
A framework that quantifies individual non-coding germline regulatory risk in non small cell lung cancer (NSCLC).
Each signal is weighted by cohort prevalence which are aggregated into a single ancestry matched, reference normalized score per patient.