How I analyzed my DNA with Claude Code

Yes, I fed it my own raw DNA file

Claude Code

If you try to replicate it, you do so at your own risk.

1. First, your genes need to be digitized: I used 23andMe, spat in a tube and sent it off by DHL courier. After analysis, the service mostly gave me entertaining lines like "You're likely to prefer vanilla over chocolate ice cream" - but no meaningful health information (my guess is their lawyers won't allow it). 2. I went into my 23andMe account settings and downloaded the Raw Data.

Technically, it was a 16.6 MB .txt file, not my full DNA. Full genome sequencing involves about 3 billion nucleotide pairs - that file would be around 100 GB.

But all humans are 99.9% identical. Companies like 23andMe don't read the entire genome - they record only specific variations, SNPs (single nucleotide polymorphisms). So those 16 MB are an "encyclopedia of Pavel Gurov's mutations" - the variations that define my uniqueness.

3. The next problem was size: about 650,000 lines, roughly 4.5 million tokens. A standard ChatGPT will choke on that (or worse, hallucinate results). An agent can break the file into smaller chunks and process it locally.

I used the Claude Code agent, which is currently one of the stronger options on the market for security. Claude Code can work with genetic code as well as software code.

4. I created an isolated folder on my computer, uploaded the DNA file there, granted the agent access, and gave it the big fat prompt:

Instead of uploading 650,000 lines to the cloud, the AI agent autonomously wrote a Python script and executed it locally on the Apple Silicon M2 chip, so the raw DNA file stayed on my hard drive.

It returned a large dossier covering:

• my sensitivity to anticoagulant drugs
• my susceptibility to some viruses
• likelihood of age-related degeneration of eyesight
• folate metabolism (relevant to cancer risk)
• Alzheimer's risk, and much more.

Instead of guessing directly from the raw file, the model ran a deterministic script and cross-referenced databases, which removes one major source of hallucination.

If you have your genome data lying around, this is now surprisingly cheap - Claude Pro is roughly $20.

Claude Science

Anthropic just shipped a new desktop app, and I've been using it non-stop: Claude Science, a research workbench built around AI agents rather than a new model. Ask a question in plain English and it queries scientific sources - papers, gene and protein databases, molecular structures - then runs the analysis and can return a chart or a 3D model.

More than 60 databases are wired in, so you don't have to jump between PubMed, a terminal, and five separate viewers.

What I did with it: I fed it my own raw DNA file. Claude Science read 631,454 SNPs and checked them against a large public database of genetic studies (the GWAS Catalog).

A few minutes later it handed me a clean chart showing where I carry more or fewer risk-linked variants than the population average, across things like blood pressure, cholesterol, type 2 diabetes, coronary artery disease, and body mass index.

Seeing my own genome mapped against decades of published research, in one plain-language session, is not something I could easily do myself a year ago.

Limitations

• The 23andMe download is a genotype file covering selected markers, not a full genome or a clinical test.²
• Claude Code ran the Python script locally, but Claude itself was not offline: prompts and context were processed through Anthropic's API.³
• The Claude Science chart was exploratory. Genome-wide association matches are not a validated polygenic risk score or a diagnosis.⁴⁵⁶