I am currently working as a research assistant under the supervision of Dr. Carter Clinton.

• Analyzing metagenomic data from the historic New York African Burial Ground using Next Generation Sequencing and tools like Qiime2 and Kraken to reconstruct the history of the enslaved African population.
• Categorizing DNA sequences (human, bacterial, animal, etc.) using Bowtie2 and SAMTools; compare human DNA with public databases for genealogical links and disease markers, utilizing bash, CUDA, and HPC.

I am worked as a research assistant under the supervision of Dr. Rafael Guerrero.

• Developed a bioinformatics pipeline for protein thermal stability analysis, including UID fetching, sequence mapping, quality filtering, and multiple sequence alignment (MAFFT). Constructed phylogenetic trees (FastTree) and generated correlation matrices (vcv_matrix) and heat maps to visualize relationships for regression analysis.
• Integrated temperature data, optimized sequence validation using pairwise alignment scores. Conducted logistic regression and Bayesian modeling (brms), enhancing data accuracy by eliminating non-variable positions.

• Mentored 25 + students during internships on Data Science projects for rural organizations, enabling hands-on experience with real data, utilizing tools such as Python, R, and SQL, and improving nonprofit operations by 20%.
• Guided students in delivering impactful presentations using data visualization tools like PowerBI and Tableau, showcasing their findings and providing actionable recommendations to stakeholders.

• Guided high school students in analyzing complex HR and medical datasets from UNC Health Blue Ridge, leveraging advanced data science and machine learning techniques.
• Instructed weekly classes on Data Cleaning, Preprocessing, Clustering, Regression, Model Fitting, Supervised and Unsupervised Learning, and Visualizations.
• Mentored students in developing interactive visualizations (using tools like Tableau and Matplotlib) and predictive models, presenting their findings to UNC Health Blue Ridge, resulting in actionable insights for the hospital.

• Developed and maintained self-updating datasets sourced from real-time public data sources. Used APIs to connect with public data and create dynamic datasets.
• Documented codebooks for each dataset and maintaining workflow notes to help future progress by others.
• Proposed ideas for extracting insights and projects from the datasets to guide research and match course goals.
• Lead regular meetings to update on project status, milestones, and future plans of action.
• Published these datasets and their insights for the wider academic community.

• Assisted NC DHHS employees in the course “Data at Work: Data Analytics in Excel and Beyond” with key topics including ETL Tools, Data Warehousing, Microsoft Excel, SQL, PowerBI, Statistics, and Data Visualization.
• Conducted regular office hours providing guidance on course concepts, lab techniques, and assisting on their capstone projects.
• Graded lab assignments and student capstone projects.

• Collaborated with Tasmia Shahriar on the AI-based application Simstudent, using data analysis skills.
• Enhanced model accuracy through data coding, mirroring middle school perspectives.
• Improved Simstudent’s performance, benefiting many middle school students.

• Tutored and evaluated 60+ students in Python course using Minerva platform.
• Teaching Assistant for the course Probability and Statistics. Assisted in attending student queries and graded students assignments and final project to aid the professor.