Agent skill

bio-clinical-databases-pharmacogenomics

Queries PharmGKB / CPIC / DPWG for drug-gene interactions; calls CYP2D6/CYP2C9/CYP2C19/DPYD/TPMT/NUDT15/UGT1A1/SLCO1B1 star alleles and phenotype with PharmCAT, Cyrius (CYP2D6 structural variants), Aldy, Stargazer; applies Caudle 2020 activity-score translation. Use when implementing pharmacogenomic-guided prescribing, applying CPIC vs DPWG guidance, screening HLA risk alleles for ICI / antiepileptics / abacavir, or interpreting compound TPMT+NUDT15 thiopurine risk.

BioTender-maxgithub.com/BioTender-maxGitHub ↗
claude-codeships scriptsNOASSERTION
Install
npx skills add BioTender-max/awesome-bio-agent-skills --skill pharmacogenomics --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 3
SKILL.md size: 29 KB
Bundled scripts: yes
Path: skills/bioskills/pharmacogenomics/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 135
Language: Python

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

Review
written from the skill's own SKILL.md · Aug 5, 2026

What it does

Instructs an agent to query pharmacogenomic resources and call star alleles across multiple genes, translate to phenotypes with activity scores, and apply CPIC/DPWG guidance. It defines a multi-tool workflow that prioritizes PharmCAT for the gene panel and requires CYP2D6 structural-variant aware input (via Cyrius or equivalent) when SVs are present. It also coordinates HLA typing and HLA-drug associations, and outlines how to interpret DPYD, TPMT, NUDT15, UGT1A1, SLCO1B1, and other pharmacogenes, using 2024–2026 guideline updates. The workflow includes a CPIC/DPWG governance framework, tool compatibility notes, and concrete CLI examples for running the analysis.

How it works

  • Use PharmCAT as the primary workflow to generate CPIC-compliant reports from a VCF covering 21 genes (including CYP2C19, CYP2C9, DPYD, TPMT, NUDT15, UGT1A1, SLCO1B1, CYP2D6, VKORC1, and others).
  • For CYP2D6 structural variants, run Cyrius (or StellarPGx) to obtain SV-aware haplotypes; PharmCAT does not call SVs alone.
  • Combine outputs: PharmCAT results for multi-gene reporting; Cyrius output for SVs; separate HLA typing results for four-field resolution where applicable.
  • Interpret activity scores per Caudle 2020 for CYP2D6 and use gene-specific activity-score methods for other genes when applicable.
  • Reference and apply CPIC/DPWG guidance alongside PharmGKB annotations; use API and command examples to verify tools and versions.

When to use it

Use this workflow when implementing pharmacogenomic-guided prescribing with CPIC vs DPWG guidance, and when screening for HLA risk alleles for ICI, antiepileptics, or abacavir, or interpreting compound TPMT+NUDT15 thiopurine risk.

What it can touch

  • Tool: PharmCAT
  • Tool: Cyrius (CYP2D6 SVs)
  • Tool: HLA typing tools (e.g., T1K, OptiType, HLA-LA) for 4-field resolution
  • Data: VCF input, reference FASTA/GRCh38 alignments for preprocessing

Caveats

  • Version compatibility notes emphasize PharmCAT 2.13+ and Cyrius 1.1+ for tested references; ensure installed versions match specified guidance.
  • The workflow depends on CPIC and DPWG guidelines; differences between authorities should be interpreted per the governance section.
  • PharmVar remains the authoritative star-allele source; older nomenclatures are deprecated for interpretation.
From the SKILL.md

## Version Compatibility Reference examples tested with: PharmCAT 2.13+, Cyrius 1.1+ (Chen 2021), Aldy 4.0+, Stargazer 2.0+, StarPhase 1.0+ (PacBio HiFi), HIBAG 1.40+, requests 2.31+, pandas 2.2+. CPIC guideline versions are gene-specific; PharmVar releases are quarterly. The 2024 DPYD update (Lam et al. *Clin Pharmacol Ther*) replaced single-variant logic with the activity-score system; the 2025 TPMT/NUDT15 update (Maillard 2026) refines compound-IM dosing. Before using code patterns, verify installed versions match. If versions differ: - Python: `pip show <package>` then `help(module.function)` to check signatures - CLI: `<tool> --version` then `<tool> --help` to confirm flags If code throws ImportError, AttributeError, or TypeError, introspect the installed package and adapt the example to match the actual API rather than retrying. PharmVar is the authoritative star-allele source (`https://www.pharmvar.org`); the older Human CYP Allele Nomenclature Database was deprecated in 2017. # Pharmacogenomics; Star Alleles, Activity Scores, and CPIC/DPWG Guidance **'What is my patient's CYP2D6 metabolizer status and should I adjust their tamoxifen dose?'** -> Call star alleles (haplotype-

What's inside
Steps it walks through
  1. Version Compatibility
  2. Governance: CPIC vs DPWG vs PharmGKB vs FDA
  3. PharmGKB Clinical Annotation Levels: What 1A Actually Means
  4. Star Allele Nomenclature (PharmVar)
  5. CYP2D6 Activity Scores (Caudle 2020 Clin Transl Sci; DOI 10.1111/cts.12692)
  6. CYP2D6 Structural Complexity
  7. Algorithmic Taxonomy: Star Allele Callers
  8. HLA-Drug Associations: Mechanistically Distinct from CYP
  9. Non-CYP Pharmacogenes: Variant-Level Detail
  10. DPYD (5-FU / Capecitabine / Tegafur); 2024 Activity Score Framework
  11. TPMT + NUDT15 (Thiopurines); 2025 Update
  12. UGT1A1 (Irinotecan, Atazanavir)
  13. CYP2C19 + Clopidogrel; The Most-Litigated Pair
  14. Warfarin (CYP2C9 + VKORC1 + CYP4F2)
Ships with 2 files
  • examples/pharmgkb_query.py
  • usage-guide.md
Commands it runs
PharmCAT (CPIC-recommended; covers 21 genes including CYP2C19, CYP2C9, CYP2D6,
pharmcat_vcf_preprocessor.py \
java -jar pharmcat.jar \
Cyrius for CYP2D6 (99.3% concordance vs Aldy 82-87%, Stargazer 84%)
cyrius -m sample.bam -o cyrius_out --threads 8
Pass outside calls to PharmCAT
More from awesome-bio-agent-skills
All skills →
report-templatePublication-quality PDF report generation using Typst templates. Produces professional scientific…Code Review & Qualitysec-reportSEC (size-exclusion chromatography) analysis with peak detection, oligomer classification, and…Code Review & Qualitybio-atac-seq-consensus-peaksetBuild a differential-ready consensus peakset from per-replicate ATAC-seq peaks using iterative…Otherbio-toolsBiology research tools reference. Always available inside agent containers.AI & Agentsbio-remote-homologyDetect distant homologs using profile and structure-aware methods that go beyond standard BLAST.…Otherbio-variant-callingCall SNPs and indels from aligned reads using bcftools mpileup and call. Use when detecting…Other
About this skill
What does the bio-clinical-databases-pharmacogenomics skill do?

Queries PharmGKB / CPIC / DPWG for drug-gene interactions; calls CYP2D6/CYP2C9/CYP2C19/DPYD/TPMT/NUDT15/UGT1A1/SLCO1B1 star alleles and phenotype with PharmCAT, Cyrius (CYP2D6 structural variants), Aldy, Stargazer; applies Caudle 2020 activity-score translation. Use when implementing pharmacogenomic-guided prescribing, applying CPIC vs DPWG guidance, screening HLA risk alleles for ICI / antiepileptics / abacavir, or interpreting compound TPMT+NUDT15 thiopurine risk.

How do I install it?

Run `npx skills add BioTender-max/awesome-bio-agent-skills --skill pharmacogenomics --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From BioTender-max/awesome-bio-agent-skills, a repository with 135 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going
All skills →
The full catalog, by category and by tool.
Open Source Radar →
The repositories these skills come from, watched daily.
The people behind them →
Makers and builders across the ecosystem.