• Performed raw data cleaning and preprocessing on a dataset with over 50,000 participants in R. Created data visualizations such as spaghetti plots to support exploratory data analysis.• Collected covariates from prior research to reduce confounding. Applied multiple imputation with chained equations (MICE) to handle missing covariates and improve statistical analysis robustness.• Employed longitudinal data analysis methods, including linear mixed-effects models and generalized estimating equations to study hearing/vision impairment, resulting in a conference presentation.

• Analyzed the Monkeypox genomes using dN/dS ratio and identified genes under positive selection as critical therapeutic targets.• Led high-throughput virtual screening of over one million small molecules on a computing cluster, identifying Nilotinib as a potential antiviral candidate.• Performed molecular dynamics simulations with GROMACS to verify ligand-protein complex stability and predicted binding free energy with the MM/GBSA method.

• Received systematic training in Good Manufacturing Practice (GMP), Good Documentation Practice (GDP), and Standard Operating Procedures (SOP), ensuring stringent compliance with industrial standards.• Led the development of a streamlined cash settlement system using Automation Anywhere and VBA scripts, resulting in a 67% reduction in the quarterly processing time for the Finance Team.• Designed and prototyped a chatbot leveraging Microsoft Azure to answer frequently asked questions within the company. Reduced the non-response rate to 10% through iterative development cycles and enhanced internal communication support.

• Performed feature engineering with min-max standardization for training data. Applied PCA and t-SNE for high-dimensional instance space visualization and utilized K-means to identify clusters in Python.• Trained and fine-tuned a collaborative filtering-based recommender system with curated molecular docking data, leading to a 32% improvement in docking scores.• Produced publication-quality data visualizations for a manuscript. Contributed as a co-author in a peer-reviewed publication.