CV

Harvard University | A.M. in Statistics

Graduate School of Arts and Sciences (GSAS)

Harvard University | A.B. in Statistics, Molecular and Cellular Biology

Joint degree program in the Faculty of Arts and Sciences (FAS)

Harvard T.H. Chan School of Public Health

Researcher, Xihong Lin laboratory

• Developing robust polygenic risk scores (PRS) for early disease diagnosis and reliable patient stratification, leveraging mixed effects model framework. Our method correctly accounts for longitudinal data and cryptic/familial relatedness.
• Validating method via simulation and empirically using UK Biobank data to show that predictions produced are consistently more accurate than current state-of-the-art approaches.

Regeneron

Analytical Genetics Intern, Regeneron Genetics Center (RGC)

• Developed efficient methods for computing polygenic overlap at biobank-scale from GWAS summary data. Implementing Monte Carlo and Bayesian methods for rapid and efficient computation. Validating method empirically in UK Biobank.
• Manager: Goncalo Abecasis, VP RGC Chief Genomics & Data Sciences Officer

Biotia

Bioinformatics Consultant

• Developed and tested AMR (antimicrobial resistance) machine learning (ML) identification pipeline for metagenomic diagnostic samples.
• Developed unsupervised ML model to predict AMR from protein structural disruptions in protein variants. AlphaFold was leveraged for protein structure prediction and de novo AMR gene discovery.

Brigham and Women's Hospital

Researcher, David Kwiatkowski laboratory

• Led broad scientific mission to unravel the genomic landscape of a rare, aggressive tumor type known as PEComa and provide diagnostic markers (extensive experience analyzing WES/WGS, RNA-seq, and ChIP-seq data).
• Co-authored 5 manuscripts reporting new somatic genetic events (SNVs, indels, CNVs) and mutational signatures that contribute to the development and progression of malignant PEComa with metastatic potential.

Preverna

Data Scientist, Computational genomics

• Built end-to-end machine learning pipeline to identify kinase drug targets and extract relevant features from multi-omics (e.g. proteomic) data associated with disease onset, progression, and survival for several cancer types.
• Identified novel biomarker candidates to support drug discovery using in-house and publicly available datasets.
• Continually presented methods to internal and external stakeholders and made a case for advancing discoveries from in-silico to in-vitro and in-vivo trials.

Massachusetts Institute of Technology (M.I.T.)

Student Researcher, Manolis Kellis laboratory

• Developed multi-omics machine learning model to predict Alzheimer's disease (AD) onset and progression from genetic (XGBoost), neuroimaging (3D CNN), and clinical data (MLP) to facilitate rapid and precise diagnosis.

Harvard Medical School

Research Intern, Debora Marks laboratory

• Selected as one of 82 students around the world to conduct research at the RSI 2019 program.
• Integrated publicly available single-cell RNA sequencing data sets to investigate differentiation pathways and cell fate determination signals. Explored effects of simultaneous biological systems on fate decision-making during differentiation by modeling organelle development relative to cell development.

Lawrence University

Researcher, Brian Piasecki laboratory

• Studied evolutionary behavior of bacteria in antibiotics and Manuka honey. Characterized the bactericidal properties of honey and the role of osmotic stress. Modeled genetic basis and patterns of gaining antibiotic resistance.

Harvard Faculty of Arts and Sciences (FAS)

Teaching Fellow

• Served as a Teaching Fellow for several courses in the statistics, computer science, and biology departments, including Statistics 111 (Statistical Inference), Statistics 110 (Probability), Statistics 185 (Unsupervised Learning), MCB 112 (Biological Data Analysis), CS 181 (Machine Learning), and Statistics 117 (Biostatistics). Led weekly review sections for students and hosted weekly office hours.

Harvard Data Analytics Group (HDAG)

Chief Consulting Officer (CCO)

• Led and organized sourcing process for HDAG data consulting services. Pitched to hundreds of Fortune 500 companies, NGOs, and local startups across several industries (Roche, WHO, NBA) and collectively sourced engagements worth $250k+ each semester.
• Organized and managed case teams of 100+ competitively recruited undergrads to conduct data projects for signed clients.

Harvard Open Data Project (HODP)

Nonprofits Director

• Organized and managed teams of trained undergraduate data scientists and journalists to conduct pro bono data projects for local nonprofits across a variety of industries (e.g. government, computer software).

Harvard Student Agencies (HSA)

Tutor

• Subjects taught include statistics, computer science, biology, chemistry, and mathematics.