close
Skip to content
View Toshihiko-tan's full-sized avatar

Block or report Toshihiko-tan

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Toshihiko-tan/README.md

Hi, I'm Samuel (Junyan) Tan 🧬

Personal WebsiteLinkedInEmail


🔭 Research & Development

I am an incoming PhD student in Quantitative and Computational Biology at the University of Southern California (Fall 2026). Currently, I'm finishing an Accelerated Master's in Biostatistics at the University of Michigan.

My work focuses on the intersection of Population Genetics and Machine Learning, specifically building high-performance tools for demographic inference and biological time-series forecasting.

  • 🧬 Recent Project: demesinfer — A JAX-based Python toolkit for rapid demographic inference.
  • 🤖 Honors Thesis: Gluco-LLM — Zero-shot LLM framework with RAG for CGM time-series forecasting.
  • 🎓 Education: M.S. Biostatistics (U-M), B.S. (Hons.) Data Science & Stats (U-M, Phi Beta Kappa).

🛠️ Technical Stack

  • Languages: Python, R, C++, C, SQL, Java, JavaScript.
  • Specialties: Demographic Inference, LLMs/RAG, Phylodynamics, MCMC, HMMs.
  • Tools: High-Performance Computing (HPC), Pytorch, JAX, Tensorflow, Google Cloud Platform (GCP).

⚡ Fun Facts

  • 🎸 Music: 5-string bassist/guitarist; former DJ at KCSB-FM in Santa Barbara.
  • ⚔️ Martial Arts: Kendo Shodan (1st Degree Black Belt).
  • 🏍️ Travel: Recently completed a solo motorcycle tour around Okinawa, Japan (39/47 prefectures visited).
  • 🗣️ Languages: Fluent in English, Chinese, Japanese, and French; learning Spanish.

Pinned Loading

  1. demesinfer demesinfer Public

    Forked from jthlab/demesinfer

    Jupyter Notebook

  2. Gluco-LLM Gluco-LLM Public

    LLM-based methods for Continuous Glucose Monitoring (CGM) data Forecasting

    Python

  3. IrinaStatsLab/Awesome-CGM IrinaStatsLab/Awesome-CGM Public

    List of CGM datasets

    R 236 50

  4. rvf-architecture rvf-architecture Public

    Forked from Weile-Zheng/rvf-architecture

    Designing and Fine-Tuning a Custom Neural Network for Real vs. Fake Faces Classification

    Jupyter Notebook

  5. iglu iglu Public

    Forked from irinagain/iglu

    R package for Interpreting GLUcose data from CGMs (Continuous Glucose Monitors)

    R

  6. Analytics-Dashboard-with-GCP-implementation Analytics-Dashboard-with-GCP-implementation Public

    STATS 507 Final Project at the University of Michigan. By: Han Yang, Haoyu Zhao, Jingyan Zhang, Junyan(Samuel) Tan, Yingxi Chen

    Jupyter Notebook