Genomics
Interpret genomic variants with ACMG classification, pharmacogenomics, and clinical annotation from ClinVar and gnomAD.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/ivangdavila/genomicsSetup
On first use, read setup.md for integration guidelines. Ask user consent before creating ~/genomics/ workspace.
When to Use
User has processed genomic data (VCF files) and needs clinical interpretation. Agent handles variant classification, pharmacogenomics recommendations, and annotation lookup. NOT for raw data processing — use bioinformatics skill for alignment and variant calling.
Architecture
Memory lives in ~/genomics/. See memory-template.md for structure.
~/genomics/
├── memory.md # Context + preferences + interpretation history
└── cases/ # Active interpretation cases
Quick Reference
| Topic | File |
|---|---|
| Setup process | setup.md |
| Memory template | memory-template.md |
Core Rules
1. Classify Variants Using ACMG Guidelines
Every variant needs systematic classification:
| Category | Criteria |
|---|---|
| Pathogenic | PVS1, PS1-4, PM1-6, PP1-5 weighted |
| Likely Pathogenic | Strong + moderate evidence |
| VUS | Insufficient or conflicting evidence |
| Likely Benign | BS1-4, BP1-7 weighted |
| Benign | Strong benign evidence |
Never classify without evidence. State "insufficient data" when appropriate.
2. Check Population Frequency First
Before clinical interpretation, verify frequency:
| Source | Use For |
|---|---|
| gnomAD v4 | Global population frequency |
| gnomAD non-cancer | Somatic analysis |
| Population-specific | Ancestry-appropriate filtering |
MAF >1% in any population = likely benign for rare disease.
3. Cross-Reference Multiple Databases
| Database | Information |
|---|---|
| ClinVar | Clinical classifications + submitter evidence |
| OMIM | Gene-disease relationships |
| HGMD | Literature-reported mutations |
| UniProt | Protein function + domains |
Single-source interpretation is insufficient. Triangulate evidence.
4. Report Pharmacogenomics Actionably
For drug-gene interactions, provide:
- Diplotype (e.g., CYP2D6 *1/*4)
- Predicted phenotype (poor/intermediate/normal/ultra-rapid metabolizer)
- Drug list affected
- Dosing guidance (CPIC/DPWG when available)
5. Separate Germline from Somatic Context
| Context | Key Differences |
|---|---|
| Germline | Family implications, carrier testing, predictive |
| Somatic | Tumor-specific, therapy selection, no inheritance |
Always state which context you're interpreting.
6. Acknowledge Uncertainty
- Novel variants often lack evidence
- VUS ≠ benign — requires ongoing monitoring
- Reclassification happens (ClinVar updates monthly)
- Computational predictions are supportive, not definitive
Pharmacogenomics Reference
High-Priority Drug-Gene Pairs (CPIC Level A)
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-ivangdavila-genomics": {
"enabled": true,
"auto_update": true
}
}
}Related Skills
Animations
Create performant web animations with proper accessibility and timing.
Arduino
Develop Arduino projects avoiding common wiring, power, and code pitfalls.
Bulgarian
Write Bulgarian that sounds human. Not formal, not robotic, not AI-generated.
Arabic
Write Arabic that sounds human. Not formal, not robotic, not AI-generated.
Assistant
Manage tasks, communications, and scheduling with proactive and organized support.