Please describe your level of experience with Bioinformatics.

I run full NGS and single-cell RNA-seq pipelines—from raw FASTQ through QC (FastQC, TrimGalore), alignment (STAR, Cell Ranger), normalization, clustering, and differential expression (DESeq2/Scanpy). I created two open-source packages that automate cell-type annotation on millions of cells (sc2Assign in R, scTRaCT in Python). My day-to-day work blends scripting, and deep-learning model development for real biomedical questions (e.g., predicting diabetic-foot-ulcer healing from scRNA-seq).

Please describe your level of experience with Human Genetics.

My research focuses on expression-based genomics rather than variant calling. I routinely integrate human scRNA-seq datasets, map gene identifiers, perform pathway enrichment, and prioritize candidate genes for follow-up experiments (e.g., diabetic-foot-ulcer healing markers). While I have not yet led large-scale GWAS or rare-variant burden studies, I understand core concepts and am eager to apply and deepen these skills in a setting like Genentech’s AMD genetics program.

Please describe your level of experience with statistical analyses.

I use classical statistics—linear/logistic regression, ANOVA, multiple-testing correction (Benjamini–Hochberg)—alongside ML methods (PCA, UMAP, k-means, XGBoost) and deep-learning losses (Focal Loss) for imbalanced data. I design cross-validation schemes, interpret ROC/PR curves and F1 scores, and document results in R Markdown/Jupyter for full reproducibility.