Hi, I'm Nan 👋

📍 Pennsylvania | 🎲 Statistician | 🤖 Research Software Engineering

I work at the intersection of statistical methodology and research software engineering. My focus is on making late-stage clinical trials efficient, reproducible, and ready for regulatory review.

Software

• 🦄 ggsci - Scientific color palettes for ggplot2
• 🎨 py-ggsci - Scientific color palettes for plotnine
• 📦 pkglite - Compact R package representations for regulatory submissions
• 💿 py-pkglite - Pack and restore source packages as text files
• 📝 rtflite - Lightweight RTF composer for Python
• 🔌 pkgdown.offline - Build pkgdown websites without an internet connection
• 🚀 revdeprun - Rust CLI for R package reverse dependency checks
• 🔬 tinytopics - GPU-accelerated topic modeling via neural Poisson NMF
• 🧪 tinyvdiff - Minimalist visual regression testing plugin for pytest
• 📸 pytest-r-snapshot - Snapshot testing against R reference outputs
• 🧲 msaenet - Multi-step adaptive elastic-net for sparse regressions
• 🌳 stackgbm - Model stacking for xgboost, lightgbm, and catboost
• 🥇 oneclust - Maximum homogeneity clustering for univariate data
• 🧬 protr - Protein sequence feature extraction in R
• 🐳 liftr - Containerize R Markdown documents for reproducibility
• 🍭 vscode-textmate-rstheme - VS Code theme inspired by RStudio IDE default theme
• ✂️ vscode-markdown-stupefy - Convert smart punctuation to ASCII in VS Code
• 🔤 DM Mono Ligaturized - DM Mono font with Fira Code ligatures
• ⚡ r-base-shortcuts - Lesser-known base R idioms for concise and fast code
• 🐝 awesome-shiny-extensions - Curated list of Shiny UI/server components

Writing

• Introducing pytest-r-snapshot: Verifying Python code against R outputs at scale
• Reverse dependency check speedrun: a data.table case study
• ggsci 4.0.0: 400+ new color palettes
• Introducing py-ggsci: ggsci color palettes for plotnine in Python
• tinytopics: GPU-accelerated topic modeling via constrained neural Poisson NMF
• Group sequential trials in industry: a 30-year perspective
• eCTD submission with analysis using R
• Training tissue-specific gene embeddings on GTEx data

Recognition

• Statistics in Biopharmaceutical Research Best Paper Award 2025
• John M. Chambers Statistical Software Award, American Statistical Association
• Second place @ PrecisionFDA Brain Cancer Predictive Modeling and Biomarker Discovery Challenge
• First place @ PrecisionFDA BioCompute Object App-a-thon (Advanced Track)
• Published author and speaker (papers, books, talks)
• 2 million+ annual downloads across projects
• 3.5K+ GitHub stars across projects

Connect