Pharmgx Reporter

Input Formats

Workflow

1. Parse: Read raw genetic data, auto-detect format (23andMe vs AncestryDNA)
2. Extract: Pull 31 PGx SNPs across 12 genes from the genotype file
3. Call: Determine star alleles and metaboliser phenotypes per gene
4. Lookup: Match each gene's phenotype to CPIC drug recommendations (AVOID / CAUTION / STANDARD / INSUFFICIENT)
5. Report: Generate report.md with gene profile table, drug summary, and clinical alerts

CLI Reference

# Full report from patient data
python skills/pharmgx-reporter/pharmgx_reporter.py \
  --input <patient_file> --output <report_dir>

# Demo mode (synthetic 31-SNP patient)
python skills/pharmgx-reporter/pharmgx_reporter.py \
  --input skills/pharmgx-reporter/demo_patient.txt --output /tmp/pharmgx_demo

# Single-drug lookup (used by Drug Photo skill)
python skills/pharmgx-reporter/pharmgx_reporter.py \
  --input <patient_file> --drug Plavix

# Via ClawBio runner
python clawbio.py run pharmgx --demo
python clawbio.py run pharmgx --input <file> --output <dir>

Demo

python clawbio.py run pharmgx --demo

Expected output: A multi-section report covering 12 gene profiles with metaboliser phenotypes, a 51-drug recommendation table (bucketed into AVOID / CAUTION / STANDARD / INSUFFICIENT), and a warfarin special alert (multi-gene CYP2C9 + VKORC1 interaction).

Genes Covered

CYP2C19, CYP2D6, CYP2C9, VKORC1, SLCO1B1, DPYD, TPMT, UGT1A1, CYP3A5, CYP2B6, NUDT15, CYP1A2

Drug Classes

Antiplatelet, opioids, statins, anticoagulants, PPIs, antidepressants (TCAs, SSRIs, SNRIs), antipsychotics, NSAIDs, oncology, immunosuppressants, antivirals

Output Structure

output_directory/
├── report.md              # Full pharmacogenomic report
├── result.json            # Machine-readable gene profiles + drug recommendations
└── reproducibility/
    └── commands.sh        # Exact command to reproduce

Dependencies

Required:

• Python 3.10+ (standard library only — no external packages)

Safety

• Local-first: Genetic data never leaves the machine
• Disclaimer: Every report includes the ClawBio medical disclaimer
• CPIC-grounded: All gene–drug mappings trace to published CPIC guidelines
• No hallucinated associations: Only the 31 validated SNPs are used

Integration with Bio Orchestrator

Trigger conditions — the orchestrator routes here when:

• User mentions pharmacogenomics, drug interactions, medications, CYP genes, warfarin, CPIC
• User provides a 23andMe or AncestryDNA file and asks about drugs

Chaining partners:

• drug-photo: Single-drug mode powers the photo → dosage card pipeline
• profile-report: PharmGx results feed into the unified genomic profile
• clinpgx: ClinPGx provides deeper gene-drug lookup when the user wants more detail

Citations

• CPIC Guidelines — Clinical Pharmacogenetics Implementation Consortium
• FDA Table of Pharmacogenomic Biomarkers — FDA-approved PGx drug labels