Fda-Orise Bioinformatics Fellow
CurrentBioinformatics Analyst Fellow with Food & Drug Administration's High-performance Integrated Virtual Environment (HIVE) team, leading complex Next Generation Sequencing (NGS) analyses and collaborating with scientists across multiple FDA offices and centers.Developed and implemented comprehensive bioinformatics pipelines specializing in bulk and single-cell RNA-seq and ChIP-seq data analysis, utilizing BASH, R (Tidyverse, Seurat, DESeq2, etc.), and Python (NumPy, Pandas, ScanPy, etc.) frameworks.Team member pioneering machine learning initiatives to create an in-house, balanced, cell-type annotation tool for FDA-CBER-HIVE; leveraging open source LLMs (SQLCoder-8b, Mistral-8B) to process and analyze scRNA-seq data through curated public datasets.Managed complete analysis workflows including data wrangling, quality control, and statistical modeling, delivering actionable insights through customized HTML reports and visualizations/figures utilizing RMarkdown and Quarto packages.Demonstrated expertise in High Performance Computing (HPC) through technical seminars and client presentations, showcasing advanced capabilities in multi-spectral data analysis and FDA-validated bioinformatics approaches.Maintained high standards of reproducibility and code quality through meticulous environment documentation (renv) and version control practices (Gitlab) while effectively operating within Agile sprint methodologies.Regularly presented research findings at internal and external conferences, delivering clear technical communications and strategic advisory services for project planning, statistical power analysis, and goal achievement.