Read the user's raw DNA file (23andMe, AncestryDNA, MyHeritage or FamilyTreeDNA; .txt, .csv or .zip) on this computer and report, for each curated variant, one of four states: read, no_call, not_in_file, or unexpected_letters (the file's letters fit neither the record nor its complement). For positions the record marks as countable it gives how many copies of the variant allele the file shows, with the record's text and sources. Pass genes for what the user asked about (for example ["CYP2C19"] before discussing clopidogrel). APOE, BRCA1 and HFE are disease-risk genes: they are read only when named in genes, so do not offer or report them unless the user asks for them by name. A count at one position is not a metabolizer status, diplotype, diagnosis or dose: say so, and refer anything that could matter for health to a clinician and a validated test.

Cited pharmacogenomic guidance for a gene, optionally for one drug, from DeepDNA's public API: the guideline (CPIC or DPWG where one exists, otherwise a drug label or the primary literature), a summary and sources. Sends only the gene and drug names. The phenotype groups it lists are the guideline's own: do not place the user in one from read_dna_file counts. Educational information, not a dose or a prescription.