I am a computational statistician and bioinformatics researcher. I hold a Master of Statistics (2026) from the Indian Statistical Institute, Kolkata, where I specialized in Biostatistics and also completed my Bachelor of Statistics (2024).

I am a PhD student in Statistics and Data Science at the National University of Singapore, supported by the NUS Industry-Relevant PhD Scholarship (NUS-IRP), under the supervision of Dr. Jonathan Göke and Dr. Alexandre Thiéry. My research attachment is with the Göke Lab at the ASTAR Genome Institute of Singapore (ASTAR GIS).

My research focus is long-read transcriptomics. My earlier work is in single-cell transcriptomics, building scalable computational tools for the analysis of high-dimensional genomic data.

• scAICME: As part of my master's thesis, I developed this open-source Python package for the semi-supervised annotation of single-cell RNA sequencing data. Built on the scverse ecosystem, it avoids the common pitfalls of standard pipelines by robustly identifying expression patterns for canonical marker sets. A manuscript detailing the underlying mathematical models, scAICME: Adaptive Marker-Guided Annotation of Single-Cell RNA-seq with Applications to Spatial Transcriptomics, is currently in preparation.

I actively contribute to the broader open-source software ecosystem, working across different languages and deployment environments.

• PLINK Packager: I maintain the PLINK genetics analysis software package for the Arch Linux distribution via the AUR and BioArchLinux.
• Bioconductor: Contributing to core infrastructure packages, such as S4Vectors, and to biocthis, which automates package setup for Bioconductor.
• r-lib: Contributing to styler and lintr, the R code formatter and linter.
• Zotero: Contributed quality of life improvements to the Android application for self-hosted setups, such as trusting user-installed certificate authorities in release builds (#204).
• Stirling-PDF: Fixed the multi-tool advert ignoring SYSTEM_ROOTURIPATH in sub-path deployments, and zero-padded numeric suffixes on archived split files so that they sort correctly (#3776, #4265).
• Heroic Games Launcher: Delivered continuous integration improvements, codebase refactoring, and UI/UX features using React and Node.js.

• Languages: Python, R, C/C++ with CUDA, Kotlin, etc.
• Data & ML: tidyverse, pandas, polars, scikit-learn, statsmodels, PyTorch, PyMC, Stan, matplotlib, seaborn
• Bioinformatics: PLINK, scverse ecosystem, Bioconductor
• Web Development: React, Svelte, GitHub Pages
• Infrastructure & Tools: Git, Docker, Linux, CMake, GitHub Actions, Cloudflare Workers

Feel free to reach out via email for collaborations or discussions around computational biology, statistical genomics, or open-source software development.