Projects
Things I've built
Research and other projects I've worked on.
Applying Protein Language Models to Raw Tumor Sequencing Data for Cancer Variant Studies
In progress...
Using Protein Language Models to Analyze Missense Mutations in the Human TP53 Gene
Analyzed all 7,467 possible single amino acid substitutions in the human TP53 gene using the ESM-C protein language model, comparing predicted mutation effects with ClinVar classifications to test whether protein sequence context can help identify disruptive variants related to cancer.
PythonBioinformaticsProtein Language Models
Association of Unhealthy Levels of Sleep Duration (>7 Hours) with Blood Pressure Hypertension, Sleep Apnea, or Low Levels of Activity
A group research project analyzing whether hypertension, physical activity level, or sleep apnea is most strongly associated with reduced sleep duration in 374 adults, using Kruskal-Wallis testing on the "Health and Sleep Relation 2024" dataset.
BiostatisticsPublic HealthData Analysis