Python · R · Scanpy · Seurat · DESeq2 · PyTorch · SHAP · Docker · HPC/SLURM
Bioinformatics chose me the moment I realized biology's biggest questions live inside data too complex to read by hand.
I genuinely love what I do. There is something deeply satisfying about starting with a raw count matrix and working through the noise until something real emerges — a cell population, a survival biomarker, a variant that matters. That moment of biological clarity from computational work is what keeps me going.
My focus is on building pipelines that are reproducible, interpretable, and actually answer the question they were built to answer. I work across scRNA-seq, bulk RNA-seq, somatic variant analysis, and survival biomarker discovery, always on real datasets, always with the biological question front and center.
Right now I am extending that into multi-omics deep learning for AMR prediction, bringing in SHAP explainability so the model output means something beyond an accuracy score.
- 🎓 MS Bioinformatics — Northeastern University (Dec 2025)
- 🔬 scRNA-seq · Bulk RNA-seq · Variant Annotation · Survival Analysis
- 📍 Boston, MA — open to roles across the US
| Project | Stack |
|---|---|
| Single-Cell RNA-seq Pipeline — QC → clustering → cell-type annotation on 10x PBMC | Scanpy · UMAP · Leiden |
| CPTAC Breast Cancer RNA-seq — Bulk DE pipeline on real CPTAC transcriptomics data | Python · DESeq2 · GDC API |
| LUAD Survival Biomarker Discovery — Cox regression + ML biomarkers in lung adenocarcinoma | Python · survival · TCGA |
| Cancer Variant Annotation Pipeline — Somatic variant annotation + burden analysis | Python · cBioPortal |
open to work · Boston, MA · patel.panktijr@gmail.com