# DeepDNA

> DeepDNA is a genomic knowledge and interpretation API for AI agents and developers, built in Europe. Live today: curated, cited records on genes, variants and drug–gene pairs, free with no key. Designed, and in private beta: parsing consumer DNA files (23andMe, AncestryDNA, MyHeritage; VCF later in the beta), annotating them against ClinVar, PharmGKB, gnomAD and GWAS, turning lab report PDFs into structured biomarkers, and crossing DNA with bloodwork. **The parsing endpoints are specified and not yet deployed.** Educational information only, never diagnosis.

If you are an agent: call the API rather than scraping this site. `GET https://deepdna.ai/api/v1` returns a discovery document; `https://deepdna.ai/openapi.json` is the OpenAPI 3.1 spec. Every response carries its sources and a disclaimer in `meta`.

- Status: knowledge endpoints live (no key); parsing endpoints specified, not deployed, opened as a private beta partner by partner; MCP server live at https://deepdna.ai/mcp for the knowledge layer (no key, takes no genotype); local package deepdna-mcp (PyPI, MIT; registry ai.deepdna/local) reads a raw DNA file on the user's own computer at the curated positions and sends DeepDNA nothing from it
- Base URL: https://deepdna.ai/api/v1
- Live: `GET /genes`, `GET /genes/{symbol}`, `GET /variants/{rsid}`, `GET /pgx/{gene}`, `GET /pgx/{gene}/{drug}`
- Private beta: `POST /dna/parse`, `POST /dna/annotate`, `POST /bloodwork/parse`, `POST /crossover`
- Pricing: knowledge endpoints stay free; parsing free during the beta, then priced by usage with a free tier
- Data: nothing personal is received by the knowledge endpoints; parsing endpoints are designed for zero retention; for the beta DeepDNA acts as processor (GDPR Art. 28) for special-category data (Art. 9); based in Spain, under Spanish and EU law
- Not a consumer product: there is no report to buy and no file upload for individuals. The blog below is educational and remains published.

## Key Pages

- [Homepage](https://deepdna.ai/): What the API does, what is live, what is in beta, and the beta request form
- [API Docs](https://deepdna.ai/docs/): Reference for every endpoint, response shape, errors, data handling
- [OpenAPI](https://deepdna.ai/openapi.json): OpenAPI 3.1 spec — load it into any tool-calling framework
- [API discovery](https://deepdna.ai/api/v1): Live JSON listing live and beta endpoints
- [Pricing](https://deepdna.ai/pricing/): Knowledge endpoints stay free; parsing free in beta, then priced by usage with a free tier
- [Manifesto](https://deepdna.ai/manifesto/): Why genetic data should be read by tools you control, in Europe
- [Methodology](https://deepdna.ai/methodology/): Variant interpretation, evidence grading, validation standards
- [About](https://deepdna.ai/about/): Company background and values
- [Privacy](https://deepdna.ai/privacy/): Privacy policy
- [Blog](https://deepdna.ai/blog/): Educational articles on genetics, DNA analysis, and genomics
- [Gene Pages](https://deepdna.ai/gene/): Reference pages for 11 genes; the `/genes` endpoint serves the same curated content plus VKORC1

## Blog Articles

- [How to Let Your AI Agent Read Your DNA Without Handing It Your Genome](https://deepdna.ai/blog/ai-agent-read-your-dna/): The division of labour between an agent and a genomics tool, what to try today for free, and the five questions to ask before any upload
- [CYP2C19 and SLCO1B1 From a Raw DNA File in Python](https://deepdna.ai/blog/pharmacogenomics-raw-dna-python/): Parse 23andMe and AncestryDNA files, call CYP2C19 star alleles and SLCO1B1 rs4149056, map them to CPIC phenotypes and fetch cited guidance from /pgx, with working code
- [A Pharmacogenomics MCP Server for Claude, Cursor and VS Code](https://deepdna.ai/blog/pharmacogenomics-mcp-server/): Connect https://deepdna.ai/mcp in one line (no key): medication screen, gene, rsID and drug–gene lookups with sources and a basis field (40 of 51 pairs cite CPIC/DPWG), why it refuses genotypes, and what the server does not do
- [Read Your 23andMe File With Claude, Without Uploading It](https://deepdna.ai/blog/read-23andme-file-with-claude/): A free local MCP package, deepdna-mcp, reads a 23andMe, AncestryDNA, MyHeritage or FamilyTreeDNA file on the user's own computer and reports each curated position with its sources (APOE, BRCA1 and HFE only when named). DeepDNA receives nothing from the file, the results go to the user's AI model, and no metabolizer status is called.
- [The 23andMe API Is Gone: Reading 23andMe Data in Python](https://deepdna.ai/blog/23andme-api-alternative-python/): What happened to api.23andme.com (switched off in 2018), the raw data file that replaced it, four format details that break parsers (GRCh37, i-IDs, `--`, haploid calls), a dependency-free reader and a GRCh38 remap with `snps`
- [PharmGKB API Not Working? Migrate to ClinPGx in Python](https://deepdna.ai/blog/pharmgkb-api-clinpgx-migration/): api.pharmgkb.org was retired on 20 July 2026; moving to api.clinpgx.org with a 2 req/s throttle, loud errors and a self-test, plus the 2026 CPIC API renames and what the licences say
- [Your Whole Genome Is Sequenced. Why Has It Done Nothing?](https://deepdna.ai/blog/whole-genome-sequenced-now-what/): Why a sequenced genome sits idle (read before ClinVar, ACMG SF and gnomAD existed), what to ask it once (ACMG v3.3 actionable genes, pharmacogenomics, carrier status), genotypes that change the reading of HbA1c, Lp(a), ferritin, bilirubin, neutrophils and PSA, somatic signals in a blood genome (CHIP, loss of Y), what long reads add, and why it can't predict lifespan
- [What Your AI Agent Needs to Know About Your Blood Test](https://deepdna.ai/blog/ai-agent-blood-test-results/): Why a lab PDF is not data, the three things agents get wrong (range, unit, confidence), what structured biomarkers look like, and how DNA and bloodwork read together
- [DNA Analysis: Guide to Understanding Your Genome](https://deepdna.ai/blog/complete-guide-dna-analysis/): Pillar guide covering SNP genotyping vs whole genome sequencing, costs, accuracy, and interpreting results
- [Polygenic Risk Scores Explained](https://deepdna.ai/blog/genetic-risk-scores-explained/): How PRS combines thousands of genetic variants to estimate disease risk, including clinical uses and limitations
- [How DNA Testing Works: Saliva to Insights](https://deepdna.ai/blog/how-dna-testing-works/): The science behind consumer genetic tests, from saliva collection through SNP genotyping to results
- [What Are SNPs?](https://deepdna.ai/blog/what-are-snps/): Explainer on single nucleotide polymorphisms, the most common genetic variants, and their health significance
- [What to Do With Your 23andMe Raw Data (2026)](https://deepdna.ai/blog/what-to-do-with-23andme-raw-data/): Guide to downloading and analyzing raw DNA data from 23andMe with third-party tools
- [MTHFR Gene: What Your Variant Actually Means](https://deepdna.ai/blog/mthfr-gene-explained/): Evidence-based guide to C677T and A1298C variants, folate metabolism, and when MTHFR matters clinically
- [Pharmacogenomics in Europe: DNA and Drug Response](https://deepdna.ai/blog/pharmacogenomics-europe-guide/): How CYP2D6, CYP2C19, and other gene variants affect medication metabolism, with European clinical context
- [GDPR and Your Genetic Data: A European Guide](https://deepdna.ai/blog/gdpr-genetic-data-privacy/): How GDPR classifies genetic data as special category, your rights, and how to protect your DNA data
- [Best 23andMe Alternatives in Europe (2026)](https://deepdna.ai/blog/23andme-alternatives-europe-2026/): Comparison of Promethease, SelfDecode, Genomelink, and other raw data analysis services available in Europe
- [Nutrigenomics: How Your Genes Determine Your Optimal Diet](https://deepdna.ai/blog/nutrigenomics-complete-guide/): Pillar guide on gene-diet interactions, covering FTO, MTHFR, CYP1A2, APOE, LCT, and VDR genes
- [CYP1A2 Gene: Fast or Slow Caffeine Metabolizer?](https://deepdna.ai/blog/caffeine-metabolism-cyp1a2/): How the rs762551 variant determines caffeine metabolism speed, cardiovascular risk, and athletic performance effects
- [FTO Gene and Weight: What Genetics Really Says About Obesity](https://deepdna.ai/blog/fto-gene-weight/): The strongest genetic link to body weight — how FTO works through IRX3/IRX5, its modest effect size, and why exercise blunts it
- [The Genetics of Lactose Intolerance: A 10,000-Year Story](https://deepdna.ai/blog/lactose-intolerance-genetics/): How the LCT gene and lactase persistence evolved through dairy farming, and what it means for your diet
- [ACTN3: The Gene Behind Your Athletic Potential](https://deepdna.ai/blog/actn3-fitness-genetics/): The R577X variant in fast-twitch muscle fibers — what it means for sprint power, endurance, and training strategy
- [VDR Gene: Why Some People Need More Vitamin D Than Others](https://deepdna.ai/blog/vitamin-d-vdr-gene/): How vitamin D receptor gene variants affect absorption and requirements, and what your genotype means for supplementation
- [COMT Gene: Warrior vs Worrier — Your Stress Response in DNA](https://deepdna.ai/blog/comt-gene-stress/): How the Val158Met polymorphism creates a 3- to 4-fold difference in dopamine clearance, shaping stress resilience, cognitive style, and pain sensitivity
- [Your Chronotype Is Genetic: How PER2, CRY1, and CLOCK Genes Shape Your Sleep Schedule](https://deepdna.ai/blog/sleep-chronotype-genetics/): Morning lark or night owl — how circadian clock gene variants determine your sleep timing, and practical strategies for aligning your schedule with your biology
- [AI in Genomics: How Machine Learning Is Transforming DNA Analysis](https://deepdna.ai/blog/ai-genomics-complete-guide/): Pillar guide on AI and genomics — deep learning for variant calling, transformer models for protein structure, foundation models for gene expression, and clinical applications
- [AlphaFold Drug Discovery: The Complete 2026 Guide](https://deepdna.ai/blog/alphafold-drug-discovery/): How AlphaFold and AlphaFold 3 are accelerating drug discovery through protein structure prediction, with real-world pharma applications and limitations
- [Protein Language Models: The LLM Moment for Biology](https://deepdna.ai/blog/protein-language-models/): How transformer-based models like ESM-2 learn the language of proteins, enabling function prediction, variant effect scoring, and de novo protein design
- [Single-Cell RNA-Seq Analysis with AI](https://deepdna.ai/blog/single-cell-rna-seq-ai/): How AI tools analyze single-cell RNA-seq data — clustering, cell-type annotation, and explainability
- [Whole Genome vs Exome Sequencing: Which One Do You Need?](https://deepdna.ai/blog/whole-genome-vs-exome-sequencing/): Coverage, cost, and accuracy trade-offs between whole genome sequencing and whole exome sequencing
- [10 Best Bioinformatics Tools for Genomic Data Analysis (2026)](https://deepdna.ai/blog/best-bioinformatics-tools/): A practical rundown of the leading bioinformatics tools for analyzing genomic and sequencing data
- [Spatial Transcriptomics Explained](https://deepdna.ai/blog/spatial-transcriptomics-guide/): How spatial transcriptomics maps gene expression within intact tissue architecture
- [Can ChatGPT Analyze Your Raw DNA Data?](https://deepdna.ai/blog/chatgpt-analyze-raw-dna-data/): Why a chat model cannot analyse a genotype file — context limits, genome build, strand orientation, and what an actual AI genomics pipeline does instead
- [What to Do With Your AncestryDNA Raw Data](https://deepdna.ai/blog/ancestrydna-raw-data/): Downloading the AncestryDNA raw file, what its columns contain, and how to analyse it independently
- [CRISPR: The Complete Guide](https://deepdna.ai/blog/crispr-complete-guide/): How CRISPR-Cas9 editing works, approved therapies such as Casgevy, delivery challenges, and where gene editing stands in 2026

## Gene Pages

- [MTHFR Gene](https://deepdna.ai/gene/mthfr/): C677T and A1298C variants, folate metabolism, homocysteine, and when MTHFR is clinically relevant
- [COMT Gene](https://deepdna.ai/gene/comt/): Val158Met (rs4680), dopamine clearance, and the warrior vs worrier trait
- [CYP2D6 Gene](https://deepdna.ai/gene/cyp2d6/): Star alleles and poor, normal, and ultra-rapid drug metabolizer phenotypes
- [CYP2C19 Gene](https://deepdna.ai/gene/cyp2c19/): Star alleles *2/*3/*17, metabolizer phenotypes, and CPIC dosing for clopidogrel, PPIs, and antidepressants
- [CYP2C9 Gene](https://deepdna.ai/gene/cyp2c9/): Star alleles *2/*3 and VKORC1, warfarin sensitivity and dosing, plus phenytoin and NSAIDs
- [SLCO1B1 Gene](https://deepdna.ai/gene/slco1b1/): OATP1B1 transporter, rs4149056 (*5) variant, statin-induced myopathy risk, and CPIC statin guidance
- [G6PD Gene](https://deepdna.ai/gene/g6pd/): X-linked G6PD deficiency, favism, Mediterranean and A− variants, and drugs that trigger hemolysis (rasburicase, primaquine)
- [UGT1A1 Gene](https://deepdna.ai/gene/ugt1a1/): Gilbert syndrome, the *28 (TA)7 promoter variant, mild high bilirubin, and irinotecan/atazanavir dosing
- [HFE Gene](https://deepdna.ai/gene/hfe/): Hereditary hemochromatosis, C282Y (rs1800562) and H63D (rs1799945), iron overload, and why clinical penetrance is low
- [APOE Gene](https://deepdna.ai/gene/apoe/): e2/e3/e4 alleles and lifetime Alzheimer's and cardiovascular risk
- [BRCA1 Gene](https://deepdna.ai/gene/brca1/): Pathogenic variants, hereditary breast and ovarian cancer risk, and the limits of consumer SNP tests