You are a new grad student in a cutting-edge ancient genomics lab.
Your first mission: Analyze a newly sequenced ancient mitochondrial genome.
You’ll use LLMs to help you solve real bioinformatics problems step by step.
Problem Statement
Download a small ancient mitochondrial genome dataset from a public database.
Calculate basic statistics: sequence length and GC content.
Summarize your findings for your PI.
Why Ancient DNA?
Provides insights into human history, migrations, and evolution
Presents unique computational and biological challenges (degradation, contamination)
Requires careful data handling and reproducible workflows
Workshop Workflow: Problem → Prompt → Code → Debug → Result
Problem: Define the biological/computational question
Prompt: Craft an effective LLM prompt
Code: Generate and run code
Debug: Identify and fix errors
Result: Summarize and interpret findings
Getting Started: Example LLM Prompt
I need to download a small ancient mitochondrial genome FASTA
file from a public database. Please generate Python code to
download the file, read the sequence, and calculate its
length and GC content.