Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Cnv Caller Agent · FreedomIntelligence | DecimalAI

Cnv Caller Agent

SkillScore88Maintained

cnv-caller-agent

AI-enhanced copy number variation calling and analysis from sequencing data for cancer genomics, constitutional CNV detection, and chromosomal aberration characterization.

scienceby FreedomIntelligence

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Research pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/cnv-caller-agent/SKILL.md

decimalai skills pull cnv-caller-agent --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/cnv-caller-agent/SKILL.md https://app.decimal.ai/s/cnv-caller-agent/SKILL.md

Raw file: /s/cnv-caller-agent/SKILL.md ↗ · machine-readable summary at /s/cnv-caller-agent.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

26 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 50d ago

Yes — +19% lift · at higher cost+66% tokens0% turns88% of whole cases pass with skill (23/26)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-03	✗→✓	▲ Improved	21%	0%
case-07	✗→✓	▲ Improved	113%	0%
case-12	✗→✓	▲ Improved	90%	0%
case-20	✗→✓	▲ Improved	178%	0%
case-23	✗→✓	▲ Improved	-31%	0%

Showing 5 of 26 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

FreedomIntelligence / OpenClaw-Medical-Skills

skills/cnv-caller-agent/SKILL.md

View on GitHub ↗

Imported 8/1/2026Version v2

Skill contents

SKILL.md

<!--

COPYRIGHT NOTICE

This file is part of the "Universal Biomedical Skills" project.

Copyright (c) 2026 MD BABU MIA, PhD <md.babu.mia@mssm.edu>

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

-->

CNV Caller Agent

The CNV Caller Agent provides comprehensive AI-enhanced copy number variation analysis from WGS, WES, and targeted sequencing for cancer genomics and constitutional CNV detection.

When to Use This Skill

When calling somatic CNVs from tumor-normal paired sequencing.
To detect constitutional CNVs from germline sequencing.
For allele-specific copy number analysis.
When characterizing focal amplifications and deletions in cancer.
To assess tumor purity and ploidy from CNV data.

Core Capabilities

Somatic CNV Calling: Detect tumor-specific copy number alterations.

Germline CNV Detection: Identify constitutional CNVs for rare disease.

Allele-Specific Analysis: Determine allele-specific copy number and LOH.

Purity/Ploidy Estimation: Estimate tumor content and genome doubling.

Focal Event Detection: Identify amplifications and deletions of driver genes.

Segmentation Optimization: AI-enhanced breakpoint detection.

Workflow

Input: BAM files (tumor/normal), or targeted panel data.

Coverage Normalization: GC correction, mappability adjustment.

Segmentation: Identify regions of consistent copy number.

Allele-Specific: Calculate B-allele frequency for heterozygosity.

Purity/Ploidy: Estimate sample parameters.

Calling: Assign integer copy number states.

Output: Segmented CNV calls, purity/ploidy, driver events.

Example Usage

User: "Call somatic copy number alterations from this tumor-normal WES pair."

Agent Action:

bash
python3 Skills/Genomics/CNV_Caller_Agent/cnv_caller.py \
    --tumor tumor.bam \
    --normal normal.bam \
    --reference GRCh38.fa \
    --method facets \
    --targets exome_targets.bed \
    --driver_genes cancer_genes.txt \
    --output cnv_results/

CNV Calling Methods

| Tool | Application | Key Features | |------|-------------|--------------| | FACETS | Tumor WES | Purity/ploidy, allele-specific | | ASCAT | Tumor WGS/arrays | Allele-specific, multi-clone | | CNVkit | WES/targeted | Hybrid reference approach | | GATK CNV | WES/WGS | GATK ecosystem integration | | Purple | WGS | GRIDSS integration, comprehensive | | CONICS | scRNA-seq | Single-cell CNV inference |

Key Output Metrics

| Metric | Description | Interpretation | |--------|-------------|----------------| | Purity | Tumor fraction | Sample quality | | Ploidy | Average copy number | Genome doubling | | LOH | Loss of heterozygosity | Regions of allele loss | | SCNA burden | Total altered fraction | Genomic instability | | Focal events | Amplifications/deletions | Driver candidates |

Cancer Driver CNVs

| Gene | Alteration | Cancer Type | |------|------------|-------------| | ERBB2 (HER2) | Amplification | Breast, gastric | | MYC | Amplification | Many cancers | | EGFR | Amplification | Lung, GBM | | CDK4/MDM2 | Amplification | Sarcoma, GBM | | CDKN2A | Deletion | Many cancers | | RB1 | Deletion | Many cancers | | PTEN | Deletion | Prostate, GBM |

AI/ML Enhancements

Segmentation:

Deep learning for breakpoint detection
Noise reduction in low-coverage data
Improved sensitivity for focal events

Quality Prediction:

Sample quality scoring
Artifact detection
Confidence estimation

Driver Prioritization:

GISTIC-style analysis
Functional impact scoring
Pan-cancer frequency context

Allele-Specific Copy Number

Total CN = Major allele + Minor allele

Examples:
- Normal: 1 + 1 = 2 (diploid)
- CN gain: 2 + 1 = 3 (trisomy)
- CN-LOH: 2 + 0 = 2 (normal total, LOH)
- Homozygous deletion: 0 + 0 = 0
- High amplification: 10 + 0 = 10 (focal amp)

Prerequisites

Python 3.10+
CNV calling tools (FACETS, CNVkit, etc.)
Reference genome and annotations
Sufficient memory for WGS (16GB+)

Related Skills

Variant_Interpretation - For CNV annotation
HRD_Analysis_Agent - For HRD scoring from CNV
Pan_Cancer_MultiOmics_Agent - For pan-cancer CNV context

Quality Considerations

Coverage depth: Higher = better resolution
Tumor purity: Low purity challenges calling
Normal match: Best with matched normal
Target design: Uniform coverage for panels
GC bias: Proper normalization critical

Author

AI Group - Biomedical AI Platform

Illustrative Want to see what cnv-caller-agent would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Latest benchmark · publisher runVerified

8/2/2026, 17:38 UTC · 26 cases

Lift

+19%

88% vs 69%

Agent turns

1.0 vs 1.0

Tokens

+66%

2,174.71 vs 1,308.38

fail → pass · 5pass → pass · 18fail → fail · 3

Per-case results (26)

Case	Status	Duration (ms)			Turns			Tokens			Tool calls
Case	Status	Without	With	Δ	Without	With	Δ	Without	With	Δ	Without	With	Δ
case-22 Before performing genomic segmentation on raw sequencing coverage counts, what two critical biological and technical bias corrections must be applied to normalize read depth?	pass→pass	6,233	4,911	-21%	1	1	0%	950	1,984	+109%	0	0	—
case-01 I need to analyze a tumor-normal exome sequencing pair to identify somatic copy number changes. Please process the alignment files and generate a comprehensive output that details the estimated tumor purity, ploidy, and integer copy number states across segmented genomic intervals, along with a list of focal amplifications or deletions affecting driver genes.	fail→fail	18,528	6,793	-63%	1	1	0%	3,403	1,640	-52%	0	0	—
case-02 I have a pair of tumor and matched normal WGS BAM files from a breast cancer patient. Please perform copy number profiling to evaluate genomic instability. I need an output containing sample purity and ploidy metrics, the total altered fraction across the genome, and identified focal driver amplifications like ERBB2 and MYC.	fail→fail	22,713	4,925	-78%	1	1	0%	4,297	1,546	-64%	0	0	—
case-03 I want to run a paired tumor-normal copy number analysis. Provide the exact shell command to execute the agent script on tumor.bam and normal.bam, using GRCh38.fa and exome capture targets bed, looking at cancer drivers in cancer_genes.txt into output folder cnv_results/.	fail→pass	8,939	3,870	-57%	1	1	0%	1,698	2,062	+21%	0	0	—
case-04 When invoking the genomics agent CLI for targeted panel or exome data, what option specifies the capture region file exome_targets.bed? Show the exact flag.	pass→pass	10,427	1,796	-83%	1	1	0%	2,087	1,578	-24%	0	0	—
case-05 In the agent CLI command structure, which option flag passes the reference genome FASTA path GRCh38.fa?	pass→pass	13,098	1,598	-88%	1	1	0%	2,221	1,519	-32%	0	0	—
case-06 I have exome sequencing data from a tumor-normal pair and want to estimate purity, ploidy, and allele-specific copy numbers. Which method argument should be passed to the agent script to select FACETS?	pass→pass	6,117	2,528	-59%	1	1	0%	995	1,699	+71%	0	0	—
case-07 We are analyzing single-cell RNA-seq expression matrices to infer large-scale chromosomal copy number alterations across individual tumor cells. Which computational tool listed in the workflow recommendations is specifically designed for single-cell RNA-seq CNV inference?	fail→pass	4,635	2,348	-49%	1	1	0%	807	1,720	+113%	0	0	—
case-08 For whole-genome sequencing of tumor samples, we need a high-precision caller integrated with structural variant calling from GRIDSS that provides comprehensive purity and ploidy estimation. Which tool from the comparison table should be chosen?	pass→pass	4,531	3,378	-25%	1	1	0%	840	1,865	+122%	0	0	—
case-09 We are processing hybrid capture targeted gene panels without matched normal samples by building a pooled reference. Which CNV calling tool is specifically suited for hybrid reference approaches on WES and targeted panel data?	pass→pass	11,401	5,941	-48%	1	1	0%	1,798	2,361	+31%	0	0	—
case-10 In an allele-specific copy number breakdown where total copy number is 2, but the major allele count is 2 and the minor allele count is 0, what specific copy number state and genomic phenomenon does this represent?	pass→pass	9,309	6,164	-34%	1	1	0%	1,638	2,289	+40%	0	0	—
case-11 A tumor suppressor gene locus displays a major allele count of 0 and a minor allele count of 0 in the allele-specific output. What copy number event has occurred?	pass→pass	3,893	3,670	-6%	1	1	0%	640	1,877	+193%	0	0	—
case-12 An oncogene shows major allele copy number 10 and minor allele copy number 0. What specific class of copy number alteration is present?	fail→pass	6,471	5,215	-19%	1	1	0%	1,128	2,145	+90%	0	0	—
case-13 A metastatic breast cancer biopsy exhibits high-level focal amplification on chromosome 17q12 affecting ERBB2. What receptor tyrosine kinase protein symbol is commonly used interchangeably with ERBB2 in clinical reports?	pass→pass	2,204	2,686	+22%	1	1	0%	304	1,763	+480%	0	0	—
case-14 In well-differentiated liposarcomas, focal co-amplifications frequently involve chromosome 12q13-15. Which cell cycle kinase and p53-inhibiting ubiquitin ligase gene pair is characteristically amplified in this region?	pass→pass	3,560	3,996	+12%	1	1	0%	649	2,003	+209%	0	0	—
case-15 A glioblastoma specimen shows focal 9p21.3 deletion leading to loss of p16INK4a. Which tumor suppressor gene locus is deleted?	pass→pass	4,163	3,615	-13%	1	1	0%	826	1,835	+122%	0	0	—
case-16 In castration-resistant prostate cancer, baseline genomic profiling reveals a focal deletion on 10q23 leading to hyperactivation of the PI3K/AKT pathway. What driver gene is lost?	pass→pass	3,949	4,334	+10%	1	1	0%	691	2,057	+198%	0	0	—
case-17 In glioblastoma multiforme (GBM) and non-small cell lung cancer, focal amplification of chromosome 7p11.2 frequently drives oncogenesis. Which receptor tyrosine kinase gene resides at this locus?	pass→pass	2,803	3,555	+27%	1	1	0%	541	1,817	+236%	0	0	—
case-18 A pan-cancer genomic analysis identifies broad and focal copy number gains on chromosome 8q24.21 across multiple epithelial tumor types. Which master transcriptional regulator gene is localized in this amplicon?	pass→pass	3,667	3,494	-5%	1	1	0%	589	1,889	+221%	0	0	—
case-19 A retinoblastoma and small cell lung cancer study highlights focal homozygous deletions on 13q14.2 leading to loss of cell cycle restriction point control. Which key tumor suppressor gene is inactivated?	pass→pass	4,009	3,526	-12%	1	1	0%	742	1,892	+155%	0	0	—
case-20 We need to quantify the overall level of chromosomal instability across a tumor genome by computing the total proportion of the autosomal genome involved in copy number gains or losses. What specific output metric captures this genomic instability fraction?	fail→pass	4,998	6,191	+24%	1	1	0%	845	2,349	+178%	0	0	—
case-21 Outline the standard multi-step sequence for processing tumor BAM files down to final integer copy number calls in a CNV analysis pipeline. What step precedes allele-specific B-allele frequency calculation?	fail→fail	12,532	12,421	-1%	1	1	0%	2,211	3,583	+62%	0	0	—
case-23 When setting up the execution environment for this copy number analysis agent, what minimum major/minor version of Python is specified as a prerequisite?	fail→pass	12,066	1,487	-88%	1	1	0%	2,140	1,473	-31%	0	0	—
case-24 We have aligned reads from a constitutional DNA sample and need to detect single nucleotide polymorphisms (SNPs) and small insertions/deletions (indels) under 50 base pairs. How should GATK HaplotypeCaller or DeepVariant be configured to output a single-sample VCF for small germline variants?	pass→pass	15,187	12,506	-18%	1	1	0%	2,943	3,719	+26%	0	0	—
case-25 We are analyzing a paired-end WGS dataset to detect genomic structural rearrangements like balanced interchromosomal translocations and inversions by identifying split-read and discordant paired-end signatures. Provide a command using GRIDSS to call structural variant breakends.	pass→pass	5,685	5,716	+1%	1	1	0%	1,092	2,322	+113%	0	0	—
case-26 We have RNA-seq read counts from 10 treatment and 10 control cell line samples. Please provide a DESeq2 or edgeR R script to perform differential gene expression analysis and calculate fold changes and adjusted p-values.	pass→pass	15,620	14,837	-5%	1	1	0%	3,026	4,392	+45%	0	0	—

These cases were also screened by the skill’s intent / safety pass.See the Trust review ↗Reproduce this benchmark in Colab ↗

How this skill was measured

DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 26 cases were attempted, and 24 counted toward the lift figure. The other 2 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +19 percentage points is the difference between those two pass rates over the 24 comparable cases.

Model measured: gemini-3.6-flash
Graded by: gemini-3.6-flash
Grading method: judged
Verification: verified
Pass rate without the skill: 69.2%
Pass rate with the skill: 88.5%
Cases attempted: 26
Cases counted toward lift: 24
Cases that regressed: 0
Skill version measured: v2
Run completed: 8/2/2026, 17:38 UTC

Measured example — same prompt, with vs. without the skill · from the benchmark run · case case-03

Prompt

I want to run a paired tumor-normal copy number analysis. Provide the exact shell command to execute the agent script on tumor.bam and normal.bam, using GRCh38.fa and exome capture targets bed, looking at cancer drivers in cancer_genes.txt into output folder cnv_results/.

Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.

Show both answers

SkillScore blends 4 signals1 of 4 complete

BenchmarkPass rate WITH skill on a verified run88

Live evalNeeds ≥10 evaluated traces in 30 days

AI ratingNeeds ≥10 rated traces

AdoptionNeeds ≥10 serves across ≥2 orgs in 30 days

Efficiency · separate axis (at equal correctness)+0% turns+72% tokens

Shown for transparency; not credited unless a verified run shows no correctness regression.

Backed by 1 of 4 signals — each added signal makes the score more robust.

Verified on gemini-3.6-flash · re-tested 50 days ago

Model	Method	Date	Lift
gemini-3.6-flash	verified	7/24/2026	+9%

Other measured skills in the registry, with their headline benchmark lift.