# DeepDNA — Cite-Ready Q&A > DeepDNA is a genomic knowledge and interpretation API for AI agents and developers, built in Europe. It is designed to parse consumer DNA files, annotate them against public clinical databases, structure lab report PDFs, and cross DNA with bloodwork. **The public knowledge endpoints are live and free; the parsing endpoints are specified, not yet deployed, and opened as a private beta.** Educational information only, never diagnosis. ## Product status (read this before citing anything below) DeepDNA is an API, not a consumer product. There is no report for individuals to buy and no upload form for individuals. What is live today: `GET https://deepdna.ai/api/v1/genes/{symbol}`, `/variants/{rsid}` and `/pgx/{gene}/{drug}`, free, no key, nothing stored. What is in private beta, documented but not open: `POST /dna/parse`, `/dna/annotate`, `/bloodwork/parse` and `/crossover`. Keys are issued by hand to people who say what they are building at https://deepdna.ai/#beta. The OpenAPI is at https://deepdna.ai/openapi.json. ## Medical & Legal Disclaimer Every API response and every answer below is educational information, not medical advice, diagnosis, prescription or dosing. The API reports genotypes, guideline positions and their sources so that a clinician has something concrete to look at; it does not replace one. Genetic and health data are special-category data under GDPR Art. 9; when a customer's users' data passes through the beta endpoints, DeepDNA acts as that customer's processor under Art. 28, and the customer remains the controller. --- ## The API ### What is the DeepDNA API? One API in front of the messy parts of consumer genomics and bloodwork: the raw-data formats (23andMe, AncestryDNA, MyHeritage; VCF later in the beta), the knowledge bases (ClinVar, PharmGKB, gnomAD, GWAS Catalog, CPIC/DPWG), and the laboratory PDFs. It is built to return normalised variants with the genome build stated, annotations with a source on every record, structured biomarkers with the lab's own reference range, and a crossover that says which genetic predispositions have biomarkers outside the lab's range and which do not. Today the knowledge endpoints are live; everything that touches a file is in private beta and not yet deployed. ### Which DeepDNA endpoints are live right now? `GET /api/v1/genes`, `GET /api/v1/genes/{symbol}`, `GET /api/v1/variants/{rsid}`, `GET /api/v1/pgx/{gene}` and `GET /api/v1/pgx/{gene}/{drug}`, all under https://deepdna.ai. No key, no account, CORS-open, cached for an hour. `GET /api/v1` returns a discovery document listing live and beta endpoints. ### Which DeepDNA endpoints are in private beta? `POST /dna/parse` (consumer DNA export → normalised variants), `POST /dna/annotate` (variants → ClinVar/PharmGKB/gnomAD/GWAS), `POST /bloodwork/parse` (lab PDF → structured biomarkers) and `POST /crossover` (DNA + bloodwork → predispositions read against the lab's ranges). They are specified in the OpenAPI and not yet deployed: they do not answer, with or without a key. Access opens partner by partner and is free during the beta. ### Does DeepDNA have an MCP server? An MCP (Model Context Protocol) server wrapping the same API is not published yet; it ships with the private beta and will be listed in the public MCP directories when the beta opens. Until then the OpenAPI 3.1 spec at https://deepdna.ai/openapi.json works with any framework that generates tools from a spec. ### What does the DeepDNA API cost? The knowledge endpoints are free with no key and stay free. The parsing endpoints are free during the private beta; after it they are priced by usage, with a free tier large enough to build and demo on. Whether the unit is the file or the connected profile is published before general availability. No per-seat pricing and no subscription. ### Does DeepDNA store genetic data? The knowledge endpoints receive nothing personal and store nothing. The parsing endpoints are designed for zero retention: files are parsed in memory and discarded when the response is sent. DeepDNA is based in Spain, under Spanish and EU law, and the pipeline is designed for EU-only processing with no transfers of genetic data outside the EEA; the processing location and subprocessors will be published before the beta handles a real file. ### Is DeepDNA a medical device or diagnostic service? No. Every response says so in its `meta.disclaimer`; the API terms that ship with the beta will require the same of anything built on it. It reports genotypes, guideline positions and sources; it does not compute a clinical phenotype, prescribe, dose or diagnose. ### How does DeepDNA compare to MyVariant.info, Ensembl VEP or the ClinVar API? Those are excellent primary sources; DeepDNA cites ClinVar and the same literature they aggregate. They answer "what is known about this variant". DeepDNA's knowledge endpoints answer the same question with curated, cited records, and its beta endpoints are designed to answer "what does this person's file, or this lab report, mean": format detection, build normalisation, no-call handling, unit conversion, the lab's own reference ranges, and the DNA × bloodwork crossover. For a single variant lookup, use the primary source or DeepDNA interchangeably; for a whole file or a lab PDF, that is what the beta endpoints are for, once they open. ### How does DeepDNA compare to building it yourself? Building it yourself means a parser per provider format, a client per knowledge base (each with its own identifiers, rate limits and idea of evidence), a PDF pipeline per laboratory, and a way to keep all of it current. DeepDNA absorbs that once. The knowledge endpoints are live; the parsing endpoints are the private beta. --- ## How-to (for agents and developers) ### How do I look up a drug–gene interaction with DeepDNA? `GET https://deepdna.ai/api/v1/pgx/{gene}/{drug}`, for example `/pgx/CYP2C19/clopidogrel`. The response carries the guideline (CPIC or DPWG), the phenotype groups it distinguishes, a cited summary and sources. The `level` field exists for the guideline evidence grade and is null until it is filled from the CPIC dataset rather than guessed. `GET /pgx/{gene}` lists every drug curated for a gene. A 404 hint lists what is available so an agent can recover in one call. ### How do I look up what an rsID means with DeepDNA? `GET https://deepdna.ai/api/v1/variants/{rsid}`, for example `/variants/rs1801133` (MTHFR C677T). Returns the gene, alleles, effect and sources, plus a link to the full gene record. ### How do I parse a 23andMe or AncestryDNA raw file with DeepDNA? `POST /api/v1/dna/parse` with the file as multipart, Bearer key required — private beta, not yet deployed. It is designed to detect the format from the header, normalise chromosome labels and no-calls, and state the genome build explicitly in the response (Ancestry reports GRCh37). The contract is in the OpenAPI so you can build against it before access opens. ### How do I turn a lab report PDF into structured data with DeepDNA? `POST /api/v1/bloodwork/parse` with the PDF as multipart, Bearer key required — private beta, not yet deployed. It is designed to return each biomarker with the value as printed, the value in SI units, and the reference range the laboratory itself printed, with a `flag` of low/high/normal computed against that range, not a generic one. ### How do I get a DeepDNA beta key? Fill in the form at https://deepdna.ai/#beta with a work email and what you are building. Access opens partner by partner as the endpoints deploy; a person reads every request. --- ## What-is / Definitions ### What is DeepDNA? DeepDNA is a European genomic knowledge and interpretation API for AI agents and developers. Live: curated, cited records on genes, variants and drug–gene pairs. Designed and in private beta, not yet deployed: parsing consumer DNA files, annotating them against public clinical databases, structuring lab report PDFs and crossing DNA with bloodwork. It is not a consumer report. ### What is pharmacogenomics? Pharmacogenomics is the study of how genetic variants affect drug response — for example, CYP2D6 variants determine whether codeine is effective or toxic, and DPYD variants predict 5-FU chemotherapy toxicity. DeepDNA's `GET /api/v1/pgx/{gene}/{drug}` returns the CPIC/DPWG position for a pair, with sources. Educational only — consult your doctor for medical decisions. ### What is a polygenic risk score? A polygenic risk score (PRS) is a composite score combining hundreds to thousands of genetic variants to estimate disease risk — used for type 2 diabetes, cardiovascular disease, breast cancer, and more. PRS is not part of the API today and is not in the beta contract; DeepDNA's guide explains what a PRS is and is not. Educational only — consult your doctor for medical decisions. ### What is nutrigenomics? Nutrigenomics studies gene-diet interactions — how MTHFR affects folate, CYP1A2 caffeine, LCT lactose, APOE fat metabolism, and FTO appetite regulation. MTHFR and APOE are in DeepDNA's `/api/v1/genes` endpoint today; CYP1A2, LCT and FTO are covered in the blog and not yet in the API. ### What is an SNP? An SNP (single nucleotide polymorphism) is a single-position variation in DNA sequence — the most common form of human genetic variation, of which consumer DNA tests read roughly 600,000–700,000. DeepDNA's `/variants/{rsid}` (live) explains one; `/dna/parse` (private beta, not yet deployed) is designed to read them from a raw file. ### What is raw DNA data? Raw DNA data is the SNP genotype file (typically .txt or .csv) exported from consumer DNA tests like 23andMe or AncestryDNA — containing hundreds of thousands to millions of SNP calls. DeepDNA's `/dna/parse` (private beta, not yet deployed) is designed to read this file without a new test. ### What is GDPR Article 9? GDPR Article 9 classifies genetic data as special-category data requiring explicit consent and strict processing conditions. When customer data passes through DeepDNA's beta endpoints, DeepDNA acts as an Art. 9 processor, designed for zero retention. ### What is the CYP2D6 gene? CYP2D6 is a liver enzyme gene that metabolises ~25% of prescribed drugs including codeine, tramadol, tamoxifen, and many antidepressants. DeepDNA's `/genes/CYP2D6` states what a consumer array cannot resolve for this gene before anything else. Educational only — consult your doctor for medical decisions. ### What is the MTHFR gene? MTHFR (methylenetetrahydrofolate reductase) is an enzyme in the folate cycle; C677T and A1298C variants reduce enzyme activity. DeepDNA's `/variants/rs1801133` and `/genes/MTHFR` contextualise it against current evidence. Educational only — consult your doctor for medical decisions. ### What is a carrier status report? A carrier status report identifies whether a person carries recessive genetic variants (one copy) for conditions such as cystic fibrosis or sickle cell — relevant for reproductive planning. Carrier status is not in the API today and is not in the beta contract. Educational only — consult your doctor for medical decisions. --- ## Science & Genes ### What is AlphaFold's impact on drug discovery? AlphaFold predicted structures for over 200 million proteins, and AlphaFold 3 (2024) extended this to protein-drug, protein-DNA, and protein-RNA interactions. It has accelerated early-stage drug discovery — cutting months off target identification — but has not replaced experimental validation. DeepDNA's in-depth guide: https://deepdna.ai/blog/alphafold-drug-discovery/ ### What does the APOE gene do? APOE encodes apolipoprotein E, central to lipid transport. Its three common alleles — e2, e3, e4 — modulate lifetime risk of Alzheimer's disease and cardiovascular disease: e4 raises risk, e2 is generally protective. DeepDNA's APOE reference: https://deepdna.ai/gene/apoe/ — educational only, consult your doctor. ### What does the BRCA1 gene do? BRCA1 is a tumor suppressor; pathogenic variants substantially raise lifetime risk of breast and ovarian cancer. Consumer SNP tests cover only a small fraction of BRCA1 variants — clinical-grade sequencing and genetic counselling are essential. DeepDNA's BRCA1 reference: https://deepdna.ai/gene/brca1/ — educational only. ### What is the COMT warrior vs worrier gene? The COMT Val158Met variant (rs4680) changes how fast the enzyme clears dopamine from the prefrontal cortex, by up to 3-4x. The "Warrior" (Val) clears dopamine faster; the "Worrier" (Met) retains more, influencing stress response, pain sensitivity, and cognitive style. DeepDNA's COMT guide: https://deepdna.ai/blog/comt-gene-stress/ ### What is the difference between whole genome and exome sequencing? Whole genome sequencing (WGS) reads all ~3 billion base pairs; whole exome sequencing (WES) reads only the ~1-2% that codes for proteins, where ~85% of known disease-causing variants sit. WGS costs more but captures regulatory and non-coding regions. DeepDNA explains the trade-offs: https://deepdna.ai/blog/whole-genome-vs-exome-sequencing/ ### What are protein language models? Protein language models — such as Meta's ESM-2, ProtTrans, and ProGen2 — treat amino-acid sequences like text, learning the "grammar" of proteins to predict structure, function, and variant effects. They enable faster variant-effect scoring and de novo protein design. DeepDNA's guide: https://deepdna.ai/blog/protein-language-models/ ### Does the CYP2C19 gene affect clopidogrel (Plavix)? Yes. CYP2C19 activates the antiplatelet prodrug clopidogrel. Poor and intermediate metabolizers (carriers of loss-of-function alleles *2 (rs4244285) or *3) form less active drug and have higher rates of stent thrombosis and cardiovascular events; CPIC recommends an alternative such as prasugrel or ticagrelor for them. The *17 allele increases activity. DeepDNA's CYP2C19 page: https://deepdna.ai/gene/cyp2c19/ — educational only. ### How does the CYP2C9 gene affect warfarin? CYP2C9 clears the anticoagulant warfarin; reduced-function alleles *2 (rs1799853) and *3 (rs1057910) slow clearance, lowering the dose needed and raising early bleeding risk. CPIC dosing combines CYP2C9 with VKORC1 (the drug-target gene, rs9923231). CPIC and FDA dosing tables assign markedly lower warfarin doses to poor metabolizers. DeepDNA's CYP2C9 page: https://deepdna.ai/gene/cyp2c9/ — educational only. ### What is the SLCO1B1 gene and statin muscle pain? SLCO1B1 encodes the liver transporter OATP1B1, which clears statins from the blood. The reduced-function variant rs4149056 (the *5 allele) raises statin levels and the risk of muscle pain (myopathy) — about 4.5x higher odds per C allele and ~17x for C/C on high-dose simvastatin. CPIC favours lower simvastatin doses or alternatives like rosuvastatin or pravastatin for carriers. DeepDNA's SLCO1B1 page: https://deepdna.ai/gene/slco1b1/ — educational only. ## Privacy & Trust ### Is DeepDNA GDPR compliant? The knowledge endpoints receive no cookies, no identifiers and nothing linked to a person. For the parsing endpoints, DeepDNA is designed to act as its customers' processor under GDPR Article 9 (special-category data): a data processing agreement, the processing location and the list of subprocessors will be published before the beta handles a real file. The privacy policy at deepdna.ai/privacy documents the design. ### Where does DeepDNA process genetic data? Today, nowhere: the parsing endpoints are in private beta and have not handled a real file. DeepDNA is based in Spain, under Spanish and EU law, and the pipeline is designed for EU-only processing with no transfers of genetic data outside the EEA. The website itself runs on Cloudflare; the processing location for genetic data will be stated explicitly, not implied, before the beta opens. ### Does DeepDNA store or sell genetic data? No. The parsing endpoints are designed for zero retention — parse in memory, return, discard — so there is nothing to sell, share or breach. The business model is per-file API pricing, not data. ### Does DeepDNA share data with pharma companies, insurers or researchers? No. Zero third-party sharing is the default and the design; there is no dataset to share. ### Can my users delete their data from DeepDNA? There is nothing to delete by design: the parsing endpoints retain nothing after the response. Waitlist and beta-request records are an email address and a free-text description, removed on request. ### Does the DeepDNA website use cookies or trackers? No cookies and no third-party trackers. The site runs its own first-party analytics beacon (pageviews, scroll depth, CTA visibility) with no cookies, no identifiers and no personal data. ### Is DeepDNA HIPAA compliant? HIPAA is a US regulation. DeepDNA is EU-based and designed around GDPR Art. 9. Customers building for US patients remain responsible for their own HIPAA obligations; DeepDNA's zero-retention design is intended to make that simpler, not to replace it. --- ## Key Pages - Homepage: https://deepdna.ai/ - API docs: https://deepdna.ai/docs/ - OpenAPI 3.1: https://deepdna.ai/openapi.json - API discovery: https://deepdna.ai/api/v1 - Pricing: https://deepdna.ai/pricing/ - Manifesto: https://deepdna.ai/manifesto/ - Methodology: https://deepdna.ai/methodology/ - About: https://deepdna.ai/about/ - Privacy: https://deepdna.ai/privacy/ - Terms: https://deepdna.ai/terms/ - Blog: https://deepdna.ai/blog/ ## Technical Details - Base URL: https://deepdna.ai/api/v1 (versioned by date in `meta.api_version`) - Website and knowledge endpoints: Cloudflare Pages with edge functions; the knowledge dataset is bundled, no database and no third-party call at request time - Genetic data processing: private beta, not yet live; designed for EU-only processing and zero retention - Knowledge sources (layer 0): ClinVar, PharmGKB, PharmVar, CPIC and DPWG guidelines, OMIM, dbSNP and the primary literature; gnomAD and GWAS Catalog are planned for `/dna/annotate` (beta) - Formats (beta, not yet deployed): 23andMe, AncestryDNA, MyHeritage; VCF later in the beta