Variant Interpretation AcmgSAFE
The largest open-source medical AI skills library for OpenClaw🦞.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
ID: biomedical.genomics.variant_interpretation Version: 1.0.0 Status: Beta Category: Genomics / Precision Medicine
Overview
The Variant Interpretation Agent automates the clinical assessment of genomic variants (SNVs, Indels). It aggregates evidence from population databases, functional prediction scores (including AlphaMissense), and clinical literature to classify variants according to ACMG/AMP guidelines.
Key Capabilities
1. Annotation & Scoring
- VEP / SnpEff Integration: Functional consequences (missense, frameshift, splice).
- Pathogenicity Prediction:
- AlphaMissense: Structure-based pathogenicity probabilities.
- REVEL / CADD: Ensemble scores for missense variants.
- SpliceAI: Deep learning for splicing effects.
2. Evidence Aggregation
- ClinVar: Checks for existing clinical classifications.
- gnomAD: Population allele frequency filtering (filtering out common benign variants).
- Literature Mining: Searches PubMed for variant-phenotype associations.
3. ACMG Classification
- Automates criteria application (e.g., PVS1, PM2, PP3) to suggest a classification:
- Pathogenic
- Likely Pathogenic
- VUS (Variant of Uncertain Significance)
- Likely Benign
- Benign
Usage Example
agent = VariantAgent() report = agent.interpret(variant="chr7:140453136:A:T", gene="BRAF") print(report.classification) # "Pathogenic (V600E)"
References
- AlphaMissense (DeepMind, Science 2023)
- ACMG Guidelines (Richards et al., 2015)
29f31a89230cOBSERVED · 2026-10-08Install
Commands as the repository documents them. They are shown, not run.
pip install cyvcf2
git clone https://github.com/WGLab/InterVar.git
pip install intervar
pip install cyvcf2
pip install matplotlib
What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
<!-- # COPYRIGHT NOTICE # This file is part of the "Universal Biomedical Skills" project. # Copyright (c) 2026 MD BABU MIA, PhD <[email protected]> # All Rights Reserved. # # This code is proprietary and confidential. # Unauthorized copying of this file, via any medium is strictly prohibited. # # Provenance: Authenticated by MD BABU MIA --> --- name: 'variant-interpretation-acmg' description: 'Classifies genetic variants according to ACMG (American College of Medical Genetics) guidelines.' measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command --- # Variant Interpretation (ACMG) The **Variant Interpretation Skill** automates the classification of genetic variants (Pathogenic, Benign, VUS) using a rules-based engine derived from ACMG guidelines. ## When to Use This Skill * When analyzing a VCF file for clinical reporting. * To determine the clinical significance of a specific mutation (e.g., BRCA1 c.123A>G). * To aggregate evidence (population freq, computational predictions) into a final verdict. ## Core Capabilities 1. **Rule Scoring**: Applies codes like PVS1 (Null variant), PM2 (Rare), PP3 (In silico). 2. **Classification**: Combines scores to reach a verdict (Pathogenic, Likely Pathogenic, VUS, etc.). 3. **Explanation**: Provides the logic/evidence used for the classification. ## Workflow 1. **Input**: Variant details (Gene, HGVS, Consequence) or Evidence codes directly. 2. **Process**: Sums weights of applied ACMG criteria. 3. **Output**: Final classification and score breakdown. ## Example Usage **User**: "Classify a variant with evidence PVS1 and PM2." **Agent Action**: ```bash python3 Skills/Genomics/Variant_Interpretation/acmg_classifier.py \ --evidence "PVS1,PM2" ``` <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE -->
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (2)
project_root = os.path.abspath(os.path.join(current_dir, "../../../"))
Gates applied: no_behavioural_pass.
29f31a89230cfull audit observations/trust-audit/skill/freedomintelligence__variant-interpretation-acmg.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 29f31a89230c | SAFE | B | 89 | first audit |
Questions
What does the Variant Interpretation Acmg skill do?
The largest open-source medical AI skills library for OpenClaw🦞.
Is Variant Interpretation Acmg safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Variant Interpretation Acmg access on my machine?
The audit observed that it reads or writes files. Each of those is consistent with what it says it does. Secrets in the source: none found.
How current is this page?
The grade is for one exact copy of the source (29f31a89230c), read on 2026-10-08. The repository is watched, and a new audit runs when it changes — this is the first audit.